CN117592819A - Dynamic supervision method and device for land-sea complex oriented to ocean pasture - Google Patents
Dynamic supervision method and device for land-sea complex oriented to ocean pasture Download PDFInfo
- Publication number
- CN117592819A CN117592819A CN202410069291.3A CN202410069291A CN117592819A CN 117592819 A CN117592819 A CN 117592819A CN 202410069291 A CN202410069291 A CN 202410069291A CN 117592819 A CN117592819 A CN 117592819A
- Authority
- CN
- China
- Prior art keywords
- solution
- final
- evaluation
- sensor deployment
- marine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 87
- 238000011156 evaluation Methods 0.000 claims abstract description 145
- 238000012544 monitoring process Methods 0.000 claims abstract description 73
- 238000005457 optimization Methods 0.000 claims abstract description 46
- 230000007613 environmental effect Effects 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000004071 biological effect Effects 0.000 claims abstract description 11
- 239000002245 particle Substances 0.000 claims description 69
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 14
- 230000035945 sensitivity Effects 0.000 claims description 13
- 238000013500 data storage Methods 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 8
- 238000009434 installation Methods 0.000 claims description 5
- 238000013139 quantization Methods 0.000 claims description 4
- 238000009304 pastoral farming Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 43
- 238000004422 calculation algorithm Methods 0.000 description 36
- 230000008569 process Effects 0.000 description 30
- 108090000623 proteins and genes Proteins 0.000 description 10
- 230000007704 transition Effects 0.000 description 10
- 230000008901 benefit Effects 0.000 description 6
- 230000002068 genetic effect Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000005520 cutting process Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000004931 aggregating effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000002131 composite material Substances 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000012854 evaluation process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006798 recombination Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000013016 learning Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012892 rational function Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
- 230000009326 social learning Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000035899 viability Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Marine Sciences & Fisheries (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Operations Research (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention provides a dynamic supervision method and device of land-sea complexes for ocean pastures, which relate to the technical field of data processing, and the method comprises the following steps: determining an optimization target and constraint conditions, generating a final solution by using a greedy strategy according to a linear programming model, and taking the final solution as an initial population; carrying out iterative solution according to the initial population, and searching the neighborhood of each solution to obtain a final solution; according to the final solution, evaluating the performances of different sensor deployment schemes to obtain an evaluation result; according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme; according to the adjustment scheme, environmental parameters and biological activities of the marine ranch are monitored in real time by sensors deployed in the marine ranch. The invention can realize comprehensive and real-time monitoring of the marine pasture.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a dynamic supervision method and device of land-sea complexes for ocean pastures.
Background
With the increasing exhaustion of ocean resources and the deterioration of ecological environment, ocean pastures are receiving a great deal of attention as a sustainable ocean resource utilization mode. However, marine rangelands are faced with complex natural environments and diverse biological activities, and therefore, how to effectively monitor and manage marine rangelands is an urgent problem.
The traditional marine pasture supervision method is often dependent on manual inspection and periodic sampling, so that the efficiency is low, and the environmental parameters and biological activity information of the marine pasture are difficult to acquire timely and accurately. With the development of sensor technology, real-time monitoring of ocean pastures by using a sensor network becomes a feasible solution. However, how to reasonably deploy a sensor network to cover the ocean farm to the maximum and obtain accurate data remains a technical challenge.
Disclosure of Invention
The invention aims to solve the technical problem of providing a dynamic supervision method and device for land-sea complexes facing to ocean pastures, which can realize comprehensive and real-time monitoring of the ocean pastures.
In order to solve the technical problems, the technical scheme of the invention is as follows:
in a first aspect, a method of dynamic supervision of a land-sea complex for a marine ranch, the method comprising:
According to the geographic position and environmental characteristics of the marine pasture, a linear programming model of the sensing monitoring network is established;
determining an optimization target and constraint conditions, generating a final solution by using a greedy strategy according to a linear programming model, and taking the final solution as an initial population;
carrying out iterative solution according to the initial population, and searching the neighborhood of each solution to obtain a final solution;
according to the final solution, evaluating the performances of different sensor deployment schemes to obtain an evaluation result;
according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme;
according to the adjustment scheme, environmental parameters and biological activities of the marine ranch are monitored in real time by sensors deployed in the marine ranch.
Further, according to the geographic position and environmental characteristics of the marine pasture, a linear programming model of the sensing monitoring network is established, and the method comprises the following steps:
setting basic parameters and variables of a linear programming model;
based on basic parameters and variables of linear programming model byDetermining a final objective function, wherein +.>Indicating the number of monitoring points +.>Indicating the number of types of sensors available, < +. >Represent the firstiInstallation cost of individual monitoring points, < >>Represent the firstjImportance weights of the monitoring points, +.>Represent the firstiMaintenance costs of seed sensors, +.>Represent the firstiThe seed sensor is at the firstjThe energy consumption of each monitoring point; />、/>And->Is the weight coefficient of the weight of the object,/>representing the maximized objective function.
Further, the constraint conditions include a multi-sensor compatibility condition, an environmental factor constraint condition, a resource constraint condition, and a communication coverage constraint condition;
wherein, the calculation formula of the multi-sensor compatibility condition is as followsThe calculation formula of the resource limitation condition isWherein->Is the firstiThe seed sensor is at the firstjData storage requirement of individual monitoring points, +.>Is a monitoring pointjData storage capacity of>For threshold value->For scoring matrix->Is the firstjBattery capacity of individual monitoring points, +.>Is the firstiThe seed sensor is at the firstjThe energy consumption of each monitoring point.
Further, generating a final solution using a greedy strategy according to the linear programming model, comprising:
determining an optimization target of the greedy strategy, and determining greedy rules according to the optimization target;
determining constraint conditions for limiting the decision range according to greedy rules;
gradually making a decision according to the greedy rule and the constraint condition to obtain a current solution;
Judging whether the current solution meets all constraint conditions or not to obtain a judging result;
the operation is repeated until all decision variables are determined to obtain the final solution.
Further, performing iterative solution according to the initial population, and searching a neighborhood of each solution to obtain a final solution, including:
according to the characteristics of the marine pasture, randomly generating a group of solutions as an initial population;
evaluating the adaptability of each solution in the current population according to the objective function and the constraint condition;
selecting a solution in the current population as a parent to carry out random pairing according to the fitness, and carrying out cross operation to generate a new solution;
performing random variation on the new solution to obtain a variation solution;
selecting part of variation solutions, carrying out neighborhood search, and generating neighborhood solutions;
fusing the neighborhood solution into the variant solution to obtain a fused solution;
and evaluating the fitness of each solution in the fusion solutions, and repeating the iterative loop until the termination condition is met, so as to output the final solution in the current population as a final sensor deployment scheme.
Further, according to the final solution, evaluating the performance of different sensor deployment schemes to obtain an evaluation result, including:
Determining an evaluation standard according to specific requirements and targets of the marine pasture;
carrying out quantization processing on each evaluation standard to obtain a quantized value;
constructing an evaluation matrix according to the quantized values for each sensor deployment scheme, wherein each element in the evaluation matrix represents a performance score of the sensor deployment scheme on a corresponding evaluation standard;
calculating corresponding information entropy according to each evaluation standard;
calculating the weight of each evaluation standard according to the information entropy;
combining the evaluation matrix with the weight, and calculating the comprehensive performance score of each sensor deployment scheme;
sequencing all the sensor deployment schemes according to the comprehensive performance scores to obtain a sequencing table;
and performing sensitivity evaluation according to the ranking table to obtain an evaluation result.
Further, according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme, including:
regarding each sensor deployment scheme as a particle, randomly initializing a group of particles in a solution space, wherein each particle has a position vector and a speed vector, the position vector represents the sensor deployment scheme, and the speed vector determines the moving direction and speed of the particle in the solution space;
Calculating the fitness value of each particle according to the evaluation standard and the weight;
according to each particle, comparing the current fitness value of the particle with the historical final fitness value to obtain a comparison result;
determining particles of the final fitness value according to the comparison result, and updating the global final position;
updating the speed and position of each particle using the individual final position and the global final position information;
and (3) iterating the loop until the termination condition is met, and continuously adjusting the position of the particle swarm in each iteration to obtain a final adjustment scheme.
In a second aspect, a dynamic supervision device for land-sea complexes for marine ranches comprises:
the acquisition module is used for establishing a linear programming model of the sensing monitoring network according to the geographic position and the environmental characteristics of the marine pasture; determining an optimization target and constraint conditions, generating a final solution by using a greedy strategy according to a linear programming model, and taking the final solution as an initial population;
the processing module is used for carrying out iterative solution according to the initial population and searching the neighborhood of each solution to obtain a final solution; according to the final solution, evaluating the performances of different sensor deployment schemes to obtain an evaluation result; according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme; according to the adjustment scheme, environmental parameters and biological activities of the marine ranch are monitored in real time by sensors deployed in the marine ranch.
In a third aspect, a computing device includes:
one or more processors;
and a storage means for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the method.
In a fourth aspect, a computer readable storage medium has a program stored therein, which when executed by a processor, implements the method.
The scheme of the invention at least comprises the following beneficial effects:
the invention can determine the optimal deployment position of the sensor by establishing a linear programming model of the sensing monitoring network according to the geographic position and environmental characteristics of the marine pasture, generating a final solution as an initial population by using a greedy strategy and further obtaining a final solution by iterative solution and neighborhood search, thereby improving the supervision level and coverage range of the marine pasture.
According to the method, the initial sensor deployment scheme is generated, the scheme is further adjusted according to the evaluation result, so that an adjustment scheme with better performance is obtained, and the dynamic adjustment strategy can ensure the effectiveness and adaptability of the sensor deployment scheme in practical application.
By arranging the sensor in the ocean pasture according to the adjustment scheme, the invention can monitor the environmental parameters and biological activities of the ocean pasture in real time, provide timely and accurate data support for the management and decision of the ocean pasture, and is beneficial to guaranteeing the ecological environment and sustainable utilization of resources of the ocean pasture.
Through automatic sensor deployment and real-time monitoring, the method can greatly reduce the requirements of manual inspection and periodic sampling, thereby reducing the operation cost and improving the working efficiency.
Drawings
Fig. 1 is a schematic flow chart of a dynamic supervision method of land-sea complexes for marine ranches, provided by an embodiment of the invention.
Fig. 2 is a schematic diagram of a dynamic supervision device of land-sea complex for a marine ranch according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention proposes a dynamic supervision method of land-sea complexes for ocean pastures, the method comprising the steps of:
step 11, establishing a linear programming model of the sensing monitoring network according to the geographic position and the environmental characteristics of the marine pasture;
step 12, determining an optimization target and constraint conditions, generating a final solution by using a greedy strategy according to a linear programming model, and taking the final solution as an initial population;
step 13, carrying out iterative solution according to the initial population, and searching the neighborhood of each solution to obtain a final solution;
step 14, evaluating the performances of different sensor deployment schemes according to the final solution to obtain an evaluation result;
step 15, according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme;
step 16, according to the adjustment scheme, monitoring environmental parameters and biological activities of the marine ranch in real time by sensors deployed in the marine ranch.
According to the embodiment of the invention, the design of the sensing monitoring network can be ensured to be more in line with the actual requirements of the marine pasture according to the geographic position and the environmental characteristics, and the linear programming model is helpful for simplifying the complex problem, so that the optimization of the sensor deployment is more efficient and feasible; the optimization target and the constraint condition are determined to help guide the searching process, so that the generated solution meets the actual requirement, the greedy strategy can generate a feasible solution in a shorter time, and the feasible solution is used as a starting point of the subsequent iterative optimization, so that the solving efficiency is improved; the solutions in the initial population can be gradually improved by iterative solution and neighborhood search, and a sensor deployment scheme with better performance is found, so that the problem of sinking into a local optimal solution is avoided, the global searching capability is improved, and the possibility of finding a better solution is improved; by evaluating the performances of different sensor deployment schemes, objective comparison and sequencing can be carried out on various schemes, and the evaluation result provides decision support, so that the sensor deployment scheme which is most suitable for the requirements of the ocean pasture is selected; the performance of the sensor deployment scheme can be further improved according to the evaluation result, the higher supervision requirement is met, and the flexibility and the adaptability of the method are enhanced according to the feedback and the actual requirement in the evaluation by the adjustment scheme; the real-time monitoring can timely acquire the environmental parameters and biological activity information of the marine pasture, provide timely and accurate data support for pasture management, ensure the comprehensiveness and reliability of monitoring data through sensor deployment in an adjustment scheme, and improve the management efficiency and resource utilization benefit of the marine pasture.
In a preferred embodiment of the present invention, the step 11 may include:
step 111, setting basic parameters and variables of a linear programming model;
step 112, based on the basic parameters and variables of the linear programming model, byDetermining a final objective function, wherein +.>Indicating the number of monitoring points,/>indicating the number of types of sensors available, < +.>Represent the firstiInstallation cost of individual monitoring points, < >>Represent the firstjImportance weights of the monitoring points, +.>Represent the firstiMaintenance costs of seed sensors, +.>Represent the firstiThe seed sensor is at the firstjThe energy consumption of each monitoring point; />、/>And->Is a weight coefficient, +.>Representing the maximized objective function.
In the embodiment of the invention, the basic parameters and the variables of the linear programming model are set, so that a foundation is provided for the subsequent objective function construction, the consistency and the accuracy of the linear programming model are ensured, the characteristics of the actual problem can be better reflected by reasonable parameter and variable setting, the linear programming model is more close to the actual application scene, and the practicability and the reliability of the model are improved; the objective function is comprehensively based on a plurality of factors including importance of monitoring points, installation cost, maintenance cost, energy consumption and the like of the sensor, so that a sensor deployment scheme is more comprehensive and optimized, and the weight coefficient is adjusted 、/>And->The method can flexibly adjust the importance of different factors according to actual demands, enhances the flexibility and applicability of the linear programming model, maximizes the objective function, and can ensure that a sensor deployment scheme with the maximum overall benefit is found on the premise of meeting constraint conditions, thereby improving the supervision level of the marine pasture and the resource utilization efficiency.
In a preferred embodiment of the present invention, the constraints include multi-sensor compatibility conditions, environmental factor constraints, resource constraints, and communication coverage constraints;
wherein, the calculation formula of the multi-sensor compatibility condition is as followsThe calculation formula of the resource limitation condition isWherein->Is the firstiThe seed sensor is at the firstjData storage requirement of individual monitoring points, +.>Is a monitoring pointjData storage capacity of>For threshold value->For scoring matrix->Is the firstjBattery capacity of individual monitoring points, +.>Is the firstiThe seed sensor is at the firstjEnergy consumption of individual monitoring points->For the number of monitoring points +.>Is the number of types of sensors available.
In the embodiment of the invention, the compatibility between different sensors deployed on the same monitoring point is ensured by setting the compatibility condition of the multiple sensors, and the data conflict or system fault caused by incompatibility between the sensors can be avoided by limiting the data storage requirement, thereby being beneficial to improving the stability and reliability of the whole sensor network. Environmental factor constraints influence sensor performance and viability according to environmental conditions specific to the marine ranch, such as temperature, humidity, salinity, etc., by incorporating these constraints into an optimization model, it can be ensured that selected sensors can operate normally in the harsh environment of the marine ranch, thereby providing accurate and reliable monitoring data. By limiting the resource capacity of each monitoring point, in particular the battery capacity and the data storage capacity, by limiting the sum of the sensor energy consumption and the data storage requirements deployed at each monitoring point not to exceed the resource capacity of the monitoring point, the continuous operation and the data storage capacity of the sensor network can be ensured, and monitoring interruption or data loss caused by resource exhaustion is avoided, so that the sustainability and the data integrity of the whole system are improved. The communication coverage constraint condition ensures that each monitoring point in the sensor network can effectively communicate with a data center or other monitoring points, and the deployment position of the sensor can be optimized by considering the propagation characteristics of wireless signals, interference factors and performance limitations of communication equipment, so that wider and more reliable communication coverage is realized, real-time data transmission and remote monitoring are facilitated, and the efficiency and response speed of marine pasture management are improved. In summary, these constraints together ensure feasibility, stability and efficiency of the sensor deployment scheme, so that the entire sensor monitoring network can better adapt to the special environment of the marine pasture, and provide accurate and reliable monitoring data to support effective management and resource utilization of the pasture.
In a preferred embodiment of the present invention, the step 12 may include:
step 121, determining an optimization target of the greedy strategy, and determining greedy rules according to the optimization target;
step 122, determining constraint conditions for limiting the decision range according to the greedy rule;
step 123, making a decision step by step according to the greedy rule and the constraint condition to obtain a current solution;
step 124, judging whether the current solution meets all constraint conditions to obtain a judging result;
the operation is repeated until all decision variables are determined, step 125, to arrive at the final solution.
In embodiments of the present invention, determining an optimization objective and greedy rules provides directions for the overall decision process, the optimization objective ensures that the solution is going towards the desired direction, while greedy rules provide an efficient way to select a locally optimal solution in each step. The constraint condition limits the decision scope, ensures that the selection of each step is legal and feasible, and helps to avoid invalid or infeasible solutions in the solving process, thereby improving the algorithm efficiency. The step-by-step decision making process allows the algorithm to make full use of the known information in each step to make the current optimal selection. This helps to quickly find a near optimal solution in a complex optimization problem. By continuously checking whether the current solution meets all constraint conditions, the validity of the solution can be ensured to be always maintained in the solving process, and the situation that the solution is not feasible only when the algorithm is finished is avoided, so that the computing resources and time are saved. Repeating the above steps until all decision variables are determined ensures a complete solution of the whole optimization problem, providing an efficient way to find a viable solution within a limited number of steps, especially for large-scale or complex optimization problems.
In another preferred embodiment of the present invention, the step 121 may include:
step 1211, determining an optimization objective for the greedy strategyWherein->Representing an overall optimization objective; />、/>、/>And->Are all weight coefficients, +.>Representing deployment sensorsiMonitoring pointjIs>Representing deployment sensorsiMonitoring pointjCost function of>Representing deployment sensorsiMonitoring pointjRisk function of->Representing deployment sensorsiMonitoring pointjLong-term maintenance cost function of->The decision variables are represented by the values of the decision variables,and->Respectively of the sensor typeAnd the number of monitoring points;
step 1212, determining a dynamic programming framework, including, in particular, defining statesS k Is shown in the firstkThe system state of the stage and the state transition equation areWherein, the method comprises the steps of, wherein,x k is at the firstkThe decision of the stage is made,gis a state transition function, +.>Is an external factor at the time point->For sub-problems->Specific value of->Is a coefficient indicating the degree of influence of external factors on state transition,/->、/>And +.>Is a parameter->Is a random variable;
step 1213, selecting a local optimum decision at each stage based on the current state and possible state transitions in the future, and selecting a decision using greedy rules based on state transitions and boundary conditions in the dynamic programming framework; according to the dynamic programming and greedy strategy solving, the method specifically comprises the steps of setting an initial state and a dynamic programming form, updating the state step by step according to greedy rules and state transfer equations until reaching a final stage, and returning a solution corresponding to the final state to serve as an approximate solution of the optimization problem.
In the embodiment of the invention, step 1211, an optimization target of a greedy strategy is determined, a multi-target optimization formula is set, and according to the benefits, the cost, the risk and the maintenance cost of sensor deployment, the method can balance a plurality of key factors, ensure that the benefits are pursued to be maximized, and simultaneously, according to the sustainability of cost control, risk reduction and long-term maintenance, avoid the unilateralness possibly caused by single-target optimization, and make the decision more comprehensive and reasonable. Step 1212, determining a dynamic programming framework, defining consideration of state variables, state transition equations and external influence factors under the dynamic programming framework, wherein the dynamic programming framework can process the problems with overlapping sub-problems and optimal sub-structural characteristics, so that a large number of repeated calculations are effectively avoided, and meanwhile, the model is closer to an actual scene by introducing the external influence factors and randomness, so that the robustness and adaptability of decision making are improved. In step 1213, a local optimum is selected at each stage, and based on the current state and possible state transitions in the future, a local optimum is selected using greedy rules, which enable a greedy strategy to select the currently seen optimum at each stage, thus quickly yielding a viable solution. According to the dynamic programming and greedy strategy solving, from an initial state, the state is gradually updated by utilizing greedy rules and state transition equations, and finally, an approximate solution of the problem is obtained, and the method combining the dynamic programming and greedy strategies can reduce the complexity of calculation while guaranteeing the quality of the solution, and ensures the consistency and the optimality of decision through the state transition of the dynamic programming; greedy strategies provide a means to make decisions quickly at each stage. The combination of the two ensures that the algorithm is not only efficient, but also has a certain optimality guarantee. The invention combines the advantages of greedy strategy and dynamic programming, not only can quickly find a feasible solution in a complex problem space, but also ensures the comprehensiveness and optimality of decision making through multi-objective optimization and the design of state transition equations.
In a preferred embodiment of the present invention, the step 13 may include:
step 131, randomly generating a group of solutions as an initial population according to the characteristics of the marine pasture;
step 132, evaluating the adaptability of each solution in the current population according to the objective function and the constraint condition;
step 133, selecting solutions in the current population as parents to carry out random pairing according to the fitness, and carrying out cross operation to generate new solutions;
step 134, performing random variation on the new solution to obtain a variant solution;
step 135, selecting partial variant solutions, and performing neighborhood search to generate neighborhood solutions;
step 136, fusing the neighborhood solution into the variant solution to obtain a fused solution;
and step 137, evaluating the fitness of each solution in the fusion solutions, and repeating the iterative loop until the termination condition is met, so as to output the final solution in the current population as the final sensor deployment scheme.
In an embodiment of the present invention, the purpose of step 131 is to generate a set of diverse initial solutions that represent possible sensor deployment scenarios, and the goal of the overall optimization process is to find the optimal solution among these scenarios. In particular operations, the generation of the initial population may be performed according to the specific environment and requirements of the marine ranch, and these characteristics may include the size, shape, depth, water flow rate, water temperature, salinity, etc. of the ranch, environmental factors, targets to be monitored (such as fish shoal activities, water quality parameters, etc.), and available sensor types and their performances. The number and location of the sensors will be randomly selected when the initial population is generated. For example, for each possible monitoring point (which may be each grid point that is gridded according to pasture or a predefined specific location), the algorithm will randomly decide whether to deploy the sensor at that point, and what type of sensor to deploy. Thus, each initial solution represents a unique sensor deployment scenario, including the number, type, and location of sensors. To maintain the diversity of the initial population, a number of solutions (e.g., tens or hundreds) are generated, each with significant differences. This diversity helps the algorithm explore a wider solution space in the subsequent search process, increasing the likelihood of finding a globally optimal solution. In summary, step 131 provides a starting point for subsequent searches and evolutions by randomly generating a diverse set of initial solutions.
The purpose of step 132 is to evaluate the performance of each solution in the population based on predefined objective functions and constraints to determine its fitness in the optimization problem. First, the objective function is the core of the optimization problem, which defines the cost that needs to be maximized or minimized. In marine ranch sensor deployment problems, the objective function may include aspects of maximizing monitoring coverage, minimizing deployment costs, maximizing data transmission rates, and the like. The algorithm calculates the performance index corresponding to each solution according to the objective function, so as to obtain a numeric evaluation result. Second, constraints are constraints that must be met in an optimization problem. In marine ranch sensor deployment problems, constraints may include limitations on the number of sensors, limitations on communication distance, selection of sensor types, and so forth. The algorithm will check whether each solution satisfies these constraints and if not, may punish it or exclude it directly from subsequent searches. In evaluating fitness, the algorithm may comprehensively consider the influence of the objective function and the constraints. In general, a solution that satisfies the constraint and has a better objective function value will be given a higher fitness value, while a solution that does not satisfy the constraint or has a worse objective function value will be given a lower fitness value. In this way, the algorithm can distinguish the quality of different solutions according to fitness values and guide the subsequent search and evolution process.
Finally, after evaluating the fitness of all solutions in the current population, the algorithm will perform a sorting or selecting operation according to these fitness values to determine which solutions are more likely to be good solutions, and go to the next round of search and evolution process. Thus, through continuous iteration and optimization, the algorithm can finally find the sensor deployment scheme meeting the optimization target and constraint conditions.
Step 133 aims to explore more possible superior solutions in the solution space by selecting the superior solution as the parent and performing a crossover operation to generate new offspring solutions. First, the algorithm will select a part of solutions with higher fitness from the current population as the parent according to the result of fitness evaluation. These parent solutions are considered to be superior solutions in genetic algorithms, which carry genetic information that facilitates the optimization problem. Next, the algorithm will randomly pair the selected parent solutions. The pairing mode can be simple random selection, or can be selected according to a certain strategy (such as roulette selection, tournament selection and the like) so as to increase the diversity of pairing.
Once parent de-pairing is complete, the algorithm performs a crossover operation. The crossover operation simulates the genetic recombination process in biological genetics, and generates new offspring solutions by exchanging and combining part of the genes of the parent solutions. In sensor deployment problems, the interleaving operation may include exchanging information of the position, type, etc. of partial sensors, or combining partial sensor deployment schemes of parent solutions. Through crossover operation, the algorithm can introduce new genetic information while retaining the excellent genes of the father, thereby generating offspring solutions with new characteristics. These new solutions may potentially explore better regions in the solution space, providing more possibilities for finding globally optimal solutions. When the multipoint cross operation is carried out, the method specifically comprises the following steps:
In step 1331, the number of crossover points is determined, and first, the number of cut points at the time of crossover operation is determined. This number is dynamically adjusted according to the nature of the problem; after determining the number of crossover points, for each pair of paired parent solutions, a corresponding number of cut points are randomly selected that divide the parent solution's gene sequence into a plurality of segments, e.g., if the parent solution is a sequence of sensor locations and types, the cut points are randomly selected locations in the sequence.
Step 1332, exchanging gene segments, after selecting a cutting point, exchanging gene segments of parent solutions between corresponding cutting points, exchanging segments of one parent solution after a certain cutting point with segments of another parent solution after the same cutting point, and ensuring that partial gene information of the two parent solutions can be combined in a offspring solution in the exchanging process.
After exchanging the gene segments, step 1333, the resulting segments are recombined in the original order (or possibly an adjusted order) to form a new offspring solution, which contains both genetic information from both parent solutions and has new properties because of the gene exchange at the crossover point. In performing a multi-point crossover, for example, when the cut point selection is at the beginning or end of the sequence, the exchanged segments need to be adjusted to ensure that the resulting offspring solutions are still valid; after the generation of new offspring solutions, it is necessary to check whether these solutions meet the constraint conditions of the problem, and if not, it is necessary to adjust or regenerate the offspring solutions. Through multi-point crossing operation, more possible combinations can be explored in a solution space, and meanwhile, excellent genetic information in parent solutions is reserved, so that limitation of local optimal solutions can be jumped out in the process of searching global optimal solutions, and searching efficiency is improved. In summary, step 133 generates new offspring solutions by selecting parent solutions with higher fitness and performing random pairing and interleaving operations. This step plays a key role in the genetic algorithm, pushing the population to evolve towards a better solution.
The purpose of step 134 is to randomly mutate the new solution generated by the crossover operation to increase the diversity of the population and prevent the algorithm from prematurely sinking into the locally optimal solution. Specifically, the mutation operation randomly selects a portion of the genes in the new solution (in the sensor deployment problem, the genes may represent the location, type, etc. of the sensor) and makes small, random changes to them. Such modifications may be changing the position of the sensor, replacing the type of sensor, adjusting parameters of the sensor, etc. By the mutation operation, a new, possibly better, region in the solution space can be explored while maintaining population diversity. This helps the algorithm jump out of the locally optimal solution, avoiding premature convergence, and thus increasing the chance of finding a globally optimal solution. In summary, step 134 generates variant solutions with new characteristics by randomly mutating the new solutions, increasing diversity for the search and evolution process of the algorithm, and helping to prevent sinking to local optima.
Step 135, selecting a part of mutated solutions, and performing local search around the mutated solutions to find better solutions nearby, where the neighborhood search can explore the local solution space deeper, so that the algorithm can perform fine search in the area where the high-quality solutions are found, and the quality of the solutions is improved.
Step 136, combining the solutions obtained by the neighborhood search with the variant solutions to form a new fusion solution set, and integrating the solutions obtained by different search strategies to obtain the solutions, wherein the algorithm can comprehensively utilize global and local search information and improve the diversity and quality of the solutions. In step 137, in each iteration, the algorithm evaluates the fitness of the fusion solution, updates the population according to the evaluation result, and repeats the process until a preset termination condition is met (for example, the maximum iteration number is reached or the quality of the solution is not significantly improved any more), and through iteration loop and fitness evaluation, the algorithm can gradually optimize the quality of the solution, and finally output a sensor deployment scheme meeting the optimization target and constraint conditions. This iterative process ensures that the algorithm can find as high a quality solution as possible with limited computational resources.
In another preferred embodiment of the present invention, the step 135 may include:
step 1351, sorting all the variant solutions according to the fitness values of the variant solutions, and selecting the first N solutions with the highest fitness values as the starting points of neighborhood search after sorting; defining a neighborhood operation set for each selected variant solution; applying each operation in the neighborhood operation set to each selected variant solution to generate a set of neighborhood solutions; and evaluating the fitness of each neighborhood solution according to the objective function and the constraint condition.
In the embodiment of the invention, by selecting the variation solution with higher fitness as the starting point of the neighborhood search, the calculation resource can be more effectively utilized, and the solution with higher quality can be found in the limited search time; by applying multiple neighborhood operations to each selected variant solution, a set of diversified neighborhood solutions can be generated, which helps to avoid the search process from falling into a locally optimal solution, thereby improving the global search capability of the algorithm; the neighborhood search performs local search in the vicinity of the known high-quality solution, and simultaneously explores an unknown region to a certain extent, and the strategy of balanced exploration and utilization is helpful for finding a better solution in the searching process; the step is independent of specific optimization problems and can be widely applied to various different types of optimization problems. The step can be applied to carry out efficient neighborhood search only by designing a proper neighborhood operation set according to the characteristics and the disaggregated structure of the problem.
In another preferred embodiment of the present invention, the step 136 may include:
step 1361, according to the fusion strategy and the evaluation result, the neighborhood solution is fused into the variation solution set, specifically including, if a replacement strategy is adopted, selecting a part of solutions with poor performance in the variation solution set according to the evaluated fitness or diversity standard, and replacing them with equivalent neighborhood solutions; if an addition strategy is adopted, the neighborhood solution is directly added into a variation solution set as a new candidate solution, the size limitation of the set is checked, and a certain reduction strategy (such as truncation, clustering and the like) is applied when necessary to keep the manageability of the set; for the selective combining strategy, a new solution set is formed by selecting a portion from the neighborhood solution and the existing variant solution according to a specific selection mechanism (e.g., tournament selection, roulette selection, etc.).
In another preferred embodiment of the present invention, the step 137 may include:
step 1371, evaluating the fitness of the fusion solutions, and for each solution in the fusion solutions, applying an objective function to calculate the fitness value thereof; after the fitness of the fusion solution is evaluated, whether a preset termination condition is met is checked, wherein the termination condition can be that the maximum iteration number is reached, the quality of the solution is not obviously improved (i.e. the fitness value converges), or the solution meeting the specific requirement is found, and the like. If the termination condition is not met, returning to the start of the iteration loop, generating a new neighborhood solution by using the current fusion solution set, and fusing and evaluating again. This process is repeated until the termination condition is met; once the termination condition is met, the iteration will be stopped and the most fitting solution from the current population (i.e., the set of fused solutions) will be selected as the final sensor deployment solution, which represents the optimal or near optimal sensor configuration found throughout the search process, which will be used to guide the actual sensor deployment effort.
By continuously iterating the search and fusing the high-quality neighborhood solutions, the algorithm can find a solution closer to global optimum in a complex search space, thereby improving the quality and performance of the sensor deployment scheme. The automatic algorithm reduces the need of manual intervention, can process a large number of potential sensor configuration schemes in a short time, and outputs an optimized deployment strategy, thereby greatly improving the efficiency and accuracy of the decision process. The method can adapt to different sensor deployment problems and scenes, and only the objective function and the constraint condition are required to be adjusted according to specific situations. Furthermore, the scalability of the algorithm allows it to handle larger scale and more complex sensor network deployment problems. By optimizing sensor deployment, limited sensor resources can be more effectively utilized, wider coverage, better connectivity, or lower energy consumption can be achieved, thereby extending the life cycle of the sensor network and reducing the operating cost.
In a preferred embodiment of the present invention, the step 14 may include:
step 141, determining an evaluation standard according to specific requirements and targets of the marine ranches;
step 142, performing quantization processing on each evaluation criterion to obtain a quantized value;
step 143, for each sensor deployment scenario, constructing an evaluation matrix according to the quantized values, wherein each element in the evaluation matrix represents a performance score of the sensor deployment scenario on a corresponding evaluation standard;
step 144, calculating corresponding information entropy according to each evaluation standard;
step 145, calculating the weight of each evaluation criterion according to the information entropy;
step 146, combining the evaluation matrix with the weights, and calculating the comprehensive performance score of each sensor deployment scheme;
step 147, sorting all sensor deployment schemes according to the comprehensive performance scores to obtain a sorting table;
and step 148, performing sensitivity evaluation according to the ranking table to obtain an evaluation result.
In the embodiment of the present invention, step 141 determines the standard for evaluating the sensor deployment scheme according to the specific requirements (such as monitoring water quality, temperature, salinity, etc.) and the targets (such as improving cultivation efficiency, preventing diseases, etc.) of the marine ranch, so as to ensure that the evaluation process is closely connected with the actual requirements of the marine ranch, and make the evaluation more targeted and practical. In step 142, the qualitative assessment criteria are converted into quantifiable values, such as quantifying the "water quality monitoring accuracy" criteria to specific accuracy percentages, and the quantification process makes the comparison of different schemes under the same criteria more objective and accurate. The evaluation matrix is a two-dimensional table, wherein rows represent different sensor deployment schemes and columns represent different evaluation criteria, step 143. Each element represents a performance score of a particular solution on a particular criteria, and the matrix structure clearly demonstrates the performance of each solution on the respective evaluation criteria, facilitating subsequent comprehensive evaluation.
The information entropy is used to measure the uncertainty or randomness of the data, step 144. Here, it is used to evaluate the distribution of scores of different schemes under each criterion, and the importance of each evaluation criterion, i.e. which criteria have a large difference between different schemes, can be known through information entropy, so that more attention is required. Step 145, based on the calculation result of the information entropy, assigning a weight to each evaluation criterion, wherein the weight represents the relative importance of the criterion in the overall evaluation, and the introduction of the weight ensures that the importance difference of different criteria can be considered in the comprehensive evaluation. And 146, multiplying the score of each scheme on each standard by the weight of the standard, and then summing to obtain the comprehensive performance score of each scheme, wherein the comprehensive performance score reflects the overall performance of each scheme on all evaluation standards, and provides a comprehensive basis for scheme selection. Step 147, sorting all schemes according to the order of the comprehensive performance scores from high to low (or from low to high), and generating a sorting table, wherein the sorting table intuitively displays the good and bad orders of different schemes, so that a decision maker can conveniently and quickly select the best scheme. In step 148, the sensitivity assessment aims at analyzing the stability of the ranking results when the weights or scores of certain assessment criteria change, and helps to know the sensitivity of the assessment results to the weight and score changes, and the sensitivity assessment enhances the robustness and reliability of the assessment process and provides more information about the stability of the scheme selection for the decision maker.
In another preferred embodiment of the present invention, the step 142 may include:
step 1421, determining a scoring standard function for each evaluation standard, where the scoring standard function has a calculation formula:
the scoring criteria function maps the performance of the sensor deployment scenario on the criteria to a particular quantitative value, and a quantitative score is calculated for each sensor deployment scenario on the evaluation criteria by the scoring criteria function, wherein,is a quantitative score of the sensor deployment solution on some evaluation criteria; />Is the actual representation of the sensor deployment scenario on the evaluation criteria; />，/>，/>，/>，/>，/>，/>And->Is a parameter of the scoring standard function, by threshold +.>A piecewise function is defined when +.>When using +.>Scoring; when->When using +.>The linear function scores, which allows the scoring function to behave differently over a range of different performance values, provides extremely high flexibility and sensitivity to particular performance values, and can more accurately capture subtle differences in sensor deployment scenarios across different evaluation criteria.
In another preferred embodiment of the present invention, the step 143 may include:
Step 1431, constructing an original evaluation matrix asSWherein each elementS ij Represent the firstiThe deployment scheme of the sensor is in the first placejThe performance scores on the evaluation criteria specifically include setting the original evaluation matrix asSThe elements areS ij Processing the matrix to obtain a new evaluation matrixRNew evaluation matrixRElements of (2)R ij The calculation formula of (2) is as follows:
wherein,、/>and->Is a parameter which can be adjusted according to the actual situation and is used for controlling the relative importance of different parts and the shape and the steepness of the function, wherein +.>Is a logarithmic-exponential complex function which first of all will +.>Transformed by an exponential function, then logarithmized, and passed +.>Performing power operation; />Is a rational function by +.>Control->Is influenced by>Performing power operation, multiplying the two parts to obtain a new evaluation matrixRWherein each element->All reflect the original evaluation matrixSCorresponding element of (a)S ij Is a non-linear transformation of (a).
Step 1432, based on the importance of each evaluation criterion, byConstructing a weight vector, wherein the weight vector of each evaluation index is +.>The method is calculated according to the information quantity provided by the method (measured by entropy) relative to the information quantity provided by all other indexes, and the method can objectively determine the weight and avoid the deviation of subjective weighting.
Step 1433, evaluate the matrix against the originalSEach element in the matrix is weighted to obtain a weighted evaluation matrixWherein each element->The calculation formula of (2) is as follows: />Wherein, gaussian function->For adjusting the relative importance between different evaluation criteria, wherein +.>And->Is a parameter of Gaussian function, which can be adjusted according to the actual situation>Represents the firstiScheme 1jNormalized values under the individual evaluation criteria.
Through weighting processing, the performances of each scheme under different evaluation indexes are integrated, so that a more comprehensive and unified evaluation result is formed; the introduction of gaussian functions provides a flexible means to adjust the relative importance between different evaluation criteria. By adjusting parameters of Gaussian functionsAnd->Different levels of emphasis or suppression of the evaluation values at different locations (i.e., different schemes) can be achieved, and the flexibility enables the evaluation process to better adapt to different decision requirements and actual situations. The gaussian function itself has a non-linear nature, which means that the evaluation differences between different schemes can be scaled up or down non-linearly during the weighted evaluation process, which helps to capture and highlight those schemes that are particularly prominent or particularly poor under certain evaluation criteria. Use of standardized values >The data under different evaluation indexes can be compared and weighted on a unified scale, and evaluation deviation possibly caused by dimension and magnitude differences among different indexes is eliminated. By and weight->The importance of each evaluation index in the comprehensive evaluation is reflected by multiplication, so that indexes with larger influence on decision results can obtain larger weight in the final evaluation.
In another preferred embodiment of the present invention, the step 144 may include:
step 1441, calculating the ratio of the normalized value of each scheme to the sum of the normalized values of all schemes under the evaluation criterion；
Step 1442, calculate the firstjMean of all protocol normalized values under each evaluation criterionFor each scheme, calculate the scheme normalization value +.>Absolute difference from mean->The method comprises the steps of carrying out a first treatment on the surface of the According to absolute difference, average and small positive number +.>(to prevent zero denominator or zero values within the logarithm), calculating additional logarithm terms;
step 1443, scaling each schemeMultiplying the standard logarithmic term and the additional logarithmic term corresponding to the standard logarithmic term, and then adding the results of all schemes to obtain a weighted logarithmic term sum;
step 1444, dividing the weighted sum of the logarithms by the standard logarithm term and taking the inverse of the weighted sum to obtain the first jInformation entropy of individual evaluation criteriaE j Wherein, the method comprises the steps of, wherein,；
wherein, the information entropyReflect the firstjThe uncertainty or diversity of each scheme under each evaluation criterion, a higher entropy value of information means that the scheme under the criterion is distributed more uniformly, while a lower value means that some schemes perform particularly prominently or particularly poorly under the criterion, and this information can be used to understand the amount of information provided by each evaluation criterion and make more intelligent weight distribution and comprehensive evaluation in a multi-criterion decision process.
In another preferred embodiment of the present invention, the step 145 may include:
step 1451, dividing the information entropy value of each evaluation criterion by the sum of the information entropy values of all evaluation criteria, thereby obtaining a relative information entropy ratio; according to the information entropy proportion, calculating the weight of each evaluation standard; after the preliminary weight assignments are obtained, the weights are adjusted according to the actual situation, and finally, the calculated weights should be verified to ensure that they are logically reasonable and that any weight assignment constraints are not violated (e.g., the sum of the weights equals 1). Through the above steps, each evaluation criterion can be assigned an information entropy-based weight that will be used in subsequent comprehensive evaluation to reflect the relative importance of the different evaluation criteria to the final decision result.
In another preferred embodiment of the present invention, the step 146 may include:
step 1461 byNormalizing the evaluation matrix to eliminate dimensional differences between different evaluation criteria, wherein +.>Is the first in the original evaluation matrixiScheme 1jScore under individual criteria,/->Is normalized score.
Step 1462, aggregating a plurality of weights for each evaluation criterion to obtain a composite weightWherein, the method comprises the steps of, wherein,kindex representing decision maker->Representing the number of decision makers.
Step 1463, combining the normalized evaluation matrix with the comprehensive weights, and calculating a comprehensive performance score for each sensor deployment scenarioWherein->Represent the firstkThe decision maker is the firstjWeight assigned to individual evaluation criteria,/>Represent the firstiComprehensive performance scores for individual sensor deployment scenarios;mto evaluate the standard quantity.
In the embodiment of the invention, step 1461 successfully eliminates the dimension difference between different evaluation standards by carrying out standardization processing on the evaluation matrix, ensures that each evaluation standard has comparability in numerical value, avoids evaluation deviation caused by different dimensions, and is beneficial to improving the accuracy and fairness of evaluation. Step 1462 obtains comprehensive weights by aggregating weights of a plurality of decision makers for each evaluation criterion, and the method fully considers the opinion and preference of different decision makers, so that the evaluation result is more comprehensive and objective. Meanwhile, the influence of subjective bias of a single decision maker on the evaluation result can be reduced by aggregating the weights of a plurality of decision makers. Step 1463 combines the normalized evaluation matrix with the composite weights to calculate a composite performance score for each sensor deployment scenario. This step comprehensively considers the respective evaluation criteria and the weights of the decision maker, and provides a comprehensive score for each scheme, so that the advantages and disadvantages of the schemes can be reflected more accurately. In addition, through comprehensive performance scoring, different schemes can be conveniently ranked and compared, and powerful support is provided for a decision maker.
In a preferred embodiment of the present invention, the step 148 may include:
step 1481, determining a target and a range of sensitivity assessment; determining a sensitivity analysis mode according to the evaluation target and the range; according to the analysis mode, the key parameters or conditions in the sorting table are changed, and the sorting result is recalculated, for example, the weight of a certain evaluation standard can be adjusted gradually, and the change condition of the sorting position is observed. And comparing the sequencing results before and after the change, and analyzing the influence degree and trend of the sensitivity factors on the sequencing. It is determined which changes in parameters have a significant impact on the ranking result and which changes in parameters have a lesser impact on the ranking result. The stability and reliability of the ranking results are evaluated to determine if there are sensitivity factors that require special attention. Based on the results of the sensitivity assessment, the decision maker is provided with information about the stability and reliability of the ranking results. Through the steps, sensitivity evaluation can be carried out according to the sorting table, so that evaluation results on stability and reliability of the sorting results are obtained, a decision maker can be helped to better understand the reliability and application range of the sorting results, and accordingly a more intelligent and robust decision can be made.
In a preferred embodiment of the present invention, the step 15 may include:
step 151, regarding each sensor deployment scheme as a particle, randomly initializing a group of particles in the solution space, wherein each particle has a position vector and a velocity vector, the position vector represents the sensor deployment scheme, and the velocity vector determines the moving direction and velocity of the particle in the solution space;
step 152, calculating fitness values of each particle according to the evaluation criteria and weights, including, for each particle in the particle group, calculating its performance index under each evaluation criteria according to its position vector (i.e. sensor deployment scheme), combining these performance indexes with corresponding weights using fitness functions, calculating fitness values of the particle, associating the calculated fitness values with the particle, and recording fitness values of each particle, which will be used in the subsequent particle group optimization process to compare, select and update the positions of the particles;
step 153, comparing the current fitness value of the particle with the historical final fitness value according to each particle to obtain a comparison result, including comparing the current fitness value of each particle with the historical optimal fitness value thereof. If the current fitness value is better (i.e., higher or lower, depending on the definition of the fitness function) than the historical best fitness value, then the particle finds a better solution in the current iteration, if the current fitness value is better than the historical best fitness value, then the historical best fitness value of the particle is updated to the current fitness value, and the corresponding individual best position is updated to the current position vector;
Step 154, determining particles of the final fitness value according to the comparison result, and updating the global final position;
step 155, updating the speed and position of each particle using the individual final position and the global final position information;
step 156, iterating the loop until the termination condition is satisfied, and in each iteration, continuously adjusting the position of the particle swarm to obtain a final adjustment scheme.
In the embodiment of the invention, step 151 ensures the global searching capability of the algorithm by randomly initializing a group of particles in the solution space, each particle represents a sensor deployment scheme, and the optimal solution can be found in the whole solution space by continuously adjusting the position and the speed of the particle, so that the situation of sinking into local optimal solution is avoided. Step 152 calculates the fitness value of each particle according to the evaluation criteria and weights, providing a quantitative indicator for the merits of the particles, which enables the performance of each sensor deployment scenario to be evaluated quickly and optimized according to the performance, and by comparing the current fitness value of the particle with the historical final fitness value (step 153), it is possible to determine which particles perform better in the optimization process and thus adjust more specifically. Step 154 determines particles with final fitness values and updates the global final position, providing an optimized direction for other particles, helping to accelerate the convergence speed of the algorithm, causing the population of particles to more quickly aggregate near the global optimal solution. Step 155 updates the velocity and position of each particle with the individual final position and global final position information, embodying the self-learning and social learning capabilities of the particle. The learning mode considers the experience of the particles, and also refers to the experience of the optimal particles in the population, thereby being beneficial to more effectively searching the particles in the solution space. The particle swarm optimization algorithm has strong flexibility and expandability, and can be easily adapted to the sensor deployment problems of different scales and complexity. By adjusting algorithm parameters (such as particle number, iteration number, etc.), the global searching capability and the local searching capability of the optimization process can be balanced to adapt to the requirements of different problems. Step 156 continuously adjusts the particle position through an iterative loop until a termination condition is met. This iterative optimization process can ensure that the algorithm finds the globally optimal solution as much as possible under limited computational resources. With the increase of the iteration times, the particle swarm gradually approaches to the global optimal solution, and the quality of the sensor deployment scheme is improved.
As shown in fig. 2, the embodiment of the present invention further provides a dynamic supervision apparatus 20 of land-sea complex for a marine ranch, comprising:
the acquisition module 21 is used for establishing a linear programming model of the sensing monitoring network according to the geographic position and the environmental characteristics of the marine pasture; determining an optimization target and constraint conditions, generating a final solution by using a greedy strategy according to a linear programming model, and taking the final solution as an initial population;
the processing module 22 is configured to perform iterative solution according to the initial population, and search a neighborhood of each solution to obtain a final solution; according to the final solution, evaluating the performances of different sensor deployment schemes to obtain an evaluation result; according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme; according to the adjustment scheme, environmental parameters and biological activities of the marine ranch are monitored in real time by sensors deployed in the marine ranch.
Optionally, establishing a linear programming model of the sensing monitoring network according to the geographic position and the environmental characteristics of the marine pasture, including:
setting basic parameters and variables of a linear programming model;
based on basic parameters and variables of linear programming model by Determining a final objective function, wherein +.>Indicating the number of monitoring points +.>Indicating the number of types of sensors available, < +.>Represent the firstiInstallation cost of individual monitoring points, < >>Represent the firstjImportance weights of the monitoring points, +.>Represent the firstiMaintenance costs of seed sensors, +.>Represent the firstiThe seed sensor is at the firstjThe energy consumption of each monitoring point; />、/>And->Is a weight coefficient, +.>Representing the maximized objective function.
Optionally, the constraint condition includes a multi-sensor compatibility condition, an environmental factor constraint condition, a resource constraint condition, and a communication coverage constraint condition;
wherein, the calculation formula of the multi-sensor compatibility condition is as followsThe calculation formula of the resource limitation condition isWherein->Is the firstiThe seed sensor is at the firstjData storage requirement of individual monitoring points, +.>Is a monitoring pointjData storage capacity of>For threshold value->For scoring matrix->Is the firstjBattery capacity of individual monitoring points, +.>Is the firstiThe seed sensor is at the firstjEnergy consumption of individual monitoring points->For the number of monitoring points +.>Is the number of types of sensors available. />
Optionally, generating the final solution using a greedy strategy according to the linear programming model includes:
determining an optimization target of the greedy strategy, and determining greedy rules according to the optimization target;
Determining constraint conditions for limiting the decision range according to greedy rules;
gradually making a decision according to the greedy rule and the constraint condition to obtain a current solution;
judging whether the current solution meets all constraint conditions or not to obtain a judging result;
the operation is repeated until all decision variables are determined to obtain the final solution.
Optionally, performing iterative solution according to the initial population, and searching a neighborhood of each solution to obtain a final solution, including:
according to the characteristics of the marine pasture, randomly generating a group of solutions as an initial population;
evaluating the adaptability of each solution in the current population according to the objective function and the constraint condition;
selecting a solution in the current population as a parent to carry out random pairing according to the fitness, and carrying out cross operation to generate a new solution;
performing random variation on the new solution to obtain a variation solution;
selecting part of variation solutions, carrying out neighborhood search, and generating neighborhood solutions;
fusing the neighborhood solution into the variant solution to obtain a fused solution;
and evaluating the fitness of each solution in the fusion solutions, and repeating the iterative loop until the termination condition is met, so as to output the final solution in the current population as a final sensor deployment scheme.
Optionally, evaluating the performance of different sensor deployment schemes according to the final solution to obtain an evaluation result, including:
determining an evaluation standard according to specific requirements and targets of the marine pasture;
carrying out quantization processing on each evaluation standard to obtain a quantized value;
constructing an evaluation matrix according to the quantized values for each sensor deployment scheme, wherein each element in the evaluation matrix represents a performance score of the sensor deployment scheme on a corresponding evaluation standard;
calculating corresponding information entropy according to each evaluation standard;
calculating the weight of each evaluation standard according to the information entropy;
combining the evaluation matrix with the weight, and calculating the comprehensive performance score of each sensor deployment scheme;
sequencing all the sensor deployment schemes according to the comprehensive performance scores to obtain a sequencing table;
and performing sensitivity evaluation according to the ranking table to obtain an evaluation result.
Optionally, according to the evaluation result, adjusting different sensor deployment schemes to obtain an adjustment scheme, including:
regarding each sensor deployment scheme as a particle, randomly initializing a group of particles in a solution space, wherein each particle has a position vector and a speed vector, the position vector represents the sensor deployment scheme, and the speed vector determines the moving direction and speed of the particle in the solution space;
Calculating the fitness value of each particle according to the evaluation standard and the weight;
according to each particle, comparing the current fitness value of the particle with the historical final fitness value to obtain a comparison result;
determining particles of the final fitness value according to the comparison result, and updating the global final position;
updating the speed and position of each particle using the individual final position and the global final position information;
and (3) iterating the loop until the termination condition is met, and continuously adjusting the position of the particle swarm in each iteration to obtain a final adjustment scheme.
It should be noted that the apparatus is an apparatus corresponding to the above method, and all implementation manners in the above method embodiment are applicable to this embodiment, so that the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or any combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art upon reading the present specification.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. A dynamic supervision method of land-sea complexes for ocean pastures, the method comprising:
according to the geographic position and environmental characteristics of the marine pasture, a linear programming model of the sensing monitoring network is established;
determining an optimization target and constraint conditions, generating a final solution by using a greedy strategy according to a linear programming model, and taking the final solution as an initial population;
carrying out iterative solution according to the initial population, and searching the neighborhood of each solution to obtain a final solution;
according to the final solution, evaluating the performances of different sensor deployment schemes to obtain an evaluation result;
according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme;
according to the adjustment scheme, environmental parameters and biological activities of the marine ranch are monitored in real time by sensors deployed in the marine ranch.
2. The dynamic supervision method of land-sea complex for ocean pasture according to claim 1, wherein the establishing a linear programming model of the sensing monitoring network according to the geographic position and environmental characteristics of the ocean pasture comprises:
setting basic parameters and variables of a linear programming model;
based on basic parameters and variables of linear programming model byDetermining a final objective function, wherein +.>Indicating the number of monitoring points +.>Representation canWith the number of types of sensors, +.>Represent the firstiInstallation cost of individual monitoring points, < >>Represent the firstjImportance weights of the monitoring points, +.>Represent the firstiMaintenance costs of seed sensors, +.>Represent the firstiThe seed sensor is at the firstjThe energy consumption of each monitoring point; />、/>And->Is a weight coefficient, +.>Representing the maximized objective function.
3. A method of dynamic supervision of a land-sea complex for a marine ranch according to claim 2, characterized in that the constraints include multi-sensor compatibility conditions, environmental factor constraints, resource constraints, and communication coverage constraints;
wherein, the calculation formula of the multi-sensor compatibility condition is as followsThe calculation formula of the resource limitation condition is +. >Wherein->Is the firstiThe seed sensor is at the firstjData storage requirement of individual monitoring points, +.>Is a monitoring pointjData storage capacity of>For threshold value->For scoring matrix->Is the firstjBattery capacity of individual monitoring points, +.>Is the firstiThe seed sensor is at the firstjThe energy consumption of each monitoring point.
4. A method of dynamic supervision of a land-sea complex for marine ranching according to claim 3, characterized by generating a final solution using a greedy strategy according to a linear programming model, comprising:
determining an optimization target of the greedy strategy, and determining greedy rules according to the optimization target;
determining constraint conditions for limiting the decision range according to greedy rules;
gradually making a decision according to the greedy rule and the constraint condition to obtain a current solution;
judging whether the current solution meets all constraint conditions or not to obtain a judging result;
the operation is repeated until all decision variables are determined to obtain the final solution.
5. The method of dynamic supervision of a land-sea complex for a marine ranch according to claim 4, wherein iteratively solving the initial population and searching for a neighborhood of each solution to obtain a final solution comprises:
According to the characteristics of the marine pasture, randomly generating a group of solutions as an initial population;
evaluating the adaptability of each solution in the current population according to the objective function and the constraint condition;
selecting a solution in the current population as a parent to carry out random pairing according to the fitness, and carrying out cross operation to generate a new solution;
performing random variation on the new solution to obtain a variation solution;
selecting part of variation solutions, carrying out neighborhood search, and generating neighborhood solutions;
fusing the neighborhood solution into the variant solution to obtain a fused solution;
and evaluating the fitness of each solution in the fusion solutions, and repeating the iterative loop until the termination condition is met, so as to output the final solution in the current population as a final sensor deployment scheme.
6. The method of dynamic supervision of a land-sea complex for a marine ranch according to claim 5, wherein evaluating the performance of different sensor deployment scenarios based on the final solution to obtain an evaluation result comprises:
determining an evaluation standard according to specific requirements and targets of the marine pasture;
carrying out quantization processing on each evaluation standard to obtain a quantized value;
constructing an evaluation matrix according to the quantized values for each sensor deployment scheme, wherein each element in the evaluation matrix represents a performance score of the sensor deployment scheme on a corresponding evaluation standard;
Calculating corresponding information entropy according to each evaluation standard;
calculating the weight of each evaluation standard according to the information entropy;
combining the evaluation matrix with the weight, and calculating the comprehensive performance score of each sensor deployment scheme;
sequencing all the sensor deployment schemes according to the comprehensive performance scores to obtain a sequencing table;
and performing sensitivity evaluation according to the ranking table to obtain an evaluation result.
7. The method of dynamic supervision of a land-sea complex for a marine ranch according to claim 6, wherein adjusting different sensor deployment scenarios according to the evaluation result to obtain an adjustment scenario comprises:
regarding each sensor deployment scheme as a particle, randomly initializing a group of particles in a solution space, wherein each particle has a position vector and a speed vector, the position vector represents the sensor deployment scheme, and the speed vector determines the moving direction and speed of the particle in the solution space;
calculating the fitness value of each particle according to the evaluation standard and the weight;
according to each particle, comparing the current fitness value of the particle with the historical final fitness value to obtain a comparison result;
Determining particles of the final fitness value according to the comparison result, and updating the global final position;
updating the speed and position of each particle using the individual final position and the global final position information;
and (3) iterating the loop until the termination condition is met, and continuously adjusting the position of the particle swarm in each iteration to obtain a final adjustment scheme.
8. A dynamic supervision device of land-sea complex for ocean pasture, comprising:
the acquisition module is used for establishing a linear programming model of the sensing monitoring network according to the geographic position and the environmental characteristics of the marine pasture; determining an optimization target and constraint conditions, generating a final solution by using a greedy strategy according to a linear programming model, and taking the final solution as an initial population;
the processing module is used for carrying out iterative solution according to the initial population and searching the neighborhood of each solution to obtain a final solution; according to the final solution, evaluating the performances of different sensor deployment schemes to obtain an evaluation result; according to the evaluation result, different sensor deployment schemes are adjusted to obtain an adjustment scheme; according to the adjustment scheme, environmental parameters and biological activities of the marine ranch are monitored in real time by sensors deployed in the marine ranch.
9. A computing device, comprising:
one or more processors;
storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1 to 7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410069291.3A CN117592819B (en) | 2024-01-18 | 2024-01-18 | Dynamic supervision method and device for land-sea complex oriented to ocean pasture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410069291.3A CN117592819B (en) | 2024-01-18 | 2024-01-18 | Dynamic supervision method and device for land-sea complex oriented to ocean pasture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117592819A true CN117592819A (en) | 2024-02-23 |
| CN117592819B CN117592819B (en) | 2024-03-26 |
Family
ID=89913635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410069291.3A Active CN117592819B (en) | 2024-01-18 | 2024-01-18 | Dynamic supervision method and device for land-sea complex oriented to ocean pasture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117592819B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130218499A1 (en) * | 2010-07-27 | 2013-08-22 | Thales | Method for Optimally Determining the Characteristics and Arrangement of a Set of Sensors for Monitoring an Area |
| US20160239743A1 (en) * | 2015-02-15 | 2016-08-18 | Partdb Inc. | Method and apparatus for managing failure modes for condition based maintenance in marine resource production equipment |
| CN109000708A (en) * | 2018-05-03 | 2018-12-14 | 广西师范学院 | A kind of the land-sea synthesis Dynamic and Multi dimensional monitoring method and system of aquafarm |
| CN110784842A (en) * | 2019-11-04 | 2020-02-11 | 常州信息职业技术学院 | Data collection method based on multi-AUV position prediction in underwater acoustic sensor network |
| CN115795401A (en) * | 2023-02-08 | 2023-03-14 | 青岛海洋地质研究所 | Ocean pasture full-factor monitoring sensor multi-data fusion system |
| CN116647817A (en) * | 2023-06-19 | 2023-08-25 | 上海海事大学 | Marine ecological environment monitoring wireless sensor network node positioning method |
| CN116884523A (en) * | 2023-09-07 | 2023-10-13 | 山东科技大学 | Multi-parameter prediction method for water quality of marine pasture |
-
2024
- 2024-01-18 CN CN202410069291.3A patent/CN117592819B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130218499A1 (en) * | 2010-07-27 | 2013-08-22 | Thales | Method for Optimally Determining the Characteristics and Arrangement of a Set of Sensors for Monitoring an Area |
| US20160239743A1 (en) * | 2015-02-15 | 2016-08-18 | Partdb Inc. | Method and apparatus for managing failure modes for condition based maintenance in marine resource production equipment |
| CN109000708A (en) * | 2018-05-03 | 2018-12-14 | 广西师范学院 | A kind of the land-sea synthesis Dynamic and Multi dimensional monitoring method and system of aquafarm |
| CN110784842A (en) * | 2019-11-04 | 2020-02-11 | 常州信息职业技术学院 | Data collection method based on multi-AUV position prediction in underwater acoustic sensor network |
| CN115795401A (en) * | 2023-02-08 | 2023-03-14 | 青岛海洋地质研究所 | Ocean pasture full-factor monitoring sensor multi-data fusion system |
| CN116647817A (en) * | 2023-06-19 | 2023-08-25 | 上海海事大学 | Marine ecological environment monitoring wireless sensor network node positioning method |
| CN116884523A (en) * | 2023-09-07 | 2023-10-13 | 山东科技大学 | Multi-parameter prediction method for water quality of marine pasture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117592819B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102183621B (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
| CN109215344B (en) | Method and system for urban road short-time traffic flow prediction | |
| CN110969290A (en) | Runoff probability prediction method and system based on deep learning | |
| CN109919356B (en) | BP neural network-based interval water demand prediction method | |
| CN109116299B (en) | Fingerprint positioning method, terminal and computer readable storage medium | |
| CN113361761A (en) | Short-term wind power integration prediction method and system based on error correction | |
| CN112733417A (en) | Abnormal load data detection and correction method and system based on model optimization | |
| CN112364560A (en) | Intelligent prediction method for working hours of mine rock drilling equipment | |
| CN113971089A (en) | Method and device for selecting equipment nodes of federal learning system | |
| CN114302418A (en) | Method and device for detecting network element equipment performance and computer readable medium | |
| CN114578087B (en) | Wind speed uncertainty measurement method based on non-dominant sorting and stochastic simulation algorithm | |
| CN114065646B (en) | Energy consumption prediction method based on hybrid optimization algorithm, cloud computing platform and system | |
| CN103885867A (en) | Online evaluation method of performance of analog circuit | |
| CN117744501B (en) | Water network system regulation node optimal scheduling and decision-making method considering ecological flow | |
| CN111445065A (en) | Energy consumption optimization method and system for refrigeration group control of data center | |
| CN117592819B (en) | Dynamic supervision method and device for land-sea complex oriented to ocean pasture | |
| CN115207921B (en) | Position optimization method and system for photovoltaic access power distribution network | |
| CN115622034A (en) | Internet of things meter power load identification method based on improved genetic neural network | |
| CN110232517B (en) | Mobile crowd sensing user profit selection method | |
| CN113642226A (en) | Training method of fair machine learning model based on multi-objective evolutionary algorithm | |
| CN116579069B (en) | Intelligent design method and device for temperature control strategy of large-volume concrete structure | |
| CN117314128B (en) | Smart city energy management method and system based on digital twin technology | |
| CN116720662B (en) | Distributed energy system applicability evaluation method based on set pair analysis | |
| CN117574690B (en) | Biochar preparation analysis method based on negative carbon emission and related device | |
| Wei et al. | A two-stage diversity enhancement differential evolution algorithm for multi-objective optimization problem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |