CN118101720B

CN118101720B - New energy data acquisition control method and system based on edge cloud

Info

Publication number: CN118101720B
Application number: CN202410502021.7A
Authority: CN
Inventors: 罗希伦; 吴长东; 薛尚君; 刘思聪
Original assignee: Guoneng Xinkong Internet Technology Co Ltd
Current assignee: Guoneng Xinkong Internet Technology Co Ltd
Priority date: 2024-04-25
Filing date: 2024-04-25
Publication date: 2024-07-09
Anticipated expiration: 2044-04-25
Also published as: CN118101720A

Abstract

The invention provides a new energy data acquisition control method and system based on edge cloud, which relate to the technical field of digital information transmission and comprise the following steps: setting acquisition control constraints and constructing an acquisition control scheme library; acquiring communication distance information and performing data acquisition cost degree analysis to obtain a plurality of acquisition cost degrees; optimizing an acquisition control scheme to obtain a first optimization library; acquiring historical acquisition data for operation health degree analysis to acquire a plurality of operation health degrees; optimizing the acquisition control scheme to obtain a second optimizing library, and combining the first optimizing library to obtain a third optimizing library; and performing operation data complexity analysis to obtain a plurality of data complexity, optimizing in a third optimizing library to obtain an optimal acquisition control scheme, and performing configuration control. The method solves the technical problems of resource waste and cost increase caused by long communication distance and large consumption of computing power resources in the process of data acquisition and cloud analysis of the traditional data acquisition method.

Description

New energy data acquisition control method and system based on edge cloud

Technical Field

The invention relates to the technical field of digital information transmission, in particular to a new energy data acquisition control method and system based on edge cloud.

Background

Photovoltaic power generation is used as a clean and renewable energy form, plays an increasingly important role in the energy field, photovoltaic modules are generally widely distributed and cover a large area, and all data are generally transmitted to a power station data center or a cloud for analysis and processing in a traditional data acquisition mode, so that the problems of long communication distance, high data transmission delay, data loss and the like are faced when the data acquisition and analysis are carried out.

Disclosure of Invention

The application provides a new energy data acquisition control method based on edge cloud, which aims to solve the technical problems of resource waste and cost increase caused by long communication distance and large consumption of computational resources in the process of data acquisition and cloud analysis in the traditional data acquisition method.

In view of the above problems, the application provides a new energy data acquisition control method and system based on edge cloud.

The application discloses a first aspect, which provides a new energy data acquisition control method based on edge cloud, comprising the following steps: according to the calculation power requirements of data acquisition and analysis of a plurality of new energy modules in a new energy power station to be subjected to data acquisition and calculation power resources of data acquisition cloud analysis by a cloud, setting acquisition control constraints, and constructing an acquisition control scheme library for configuring the data acquisition and analysis of the plurality of new energy modules at the cloud or an edge end; collecting communication distance information of the plurality of new energy modules and a power station data center, and performing data acquisition cost degree analysis to obtain a plurality of acquisition cost degrees; according to the acquisition cost degrees, optimizing an acquisition control scheme in the acquisition control scheme library to obtain a first optimization library; acquiring historical acquisition data of the plurality of new energy modules before a preset time node, and analyzing the running health degrees of the plurality of new energy modules to obtain a plurality of running health degrees, wherein the historical acquisition data comprises historical environment data and historical power generation data; optimizing the acquisition control scheme in the acquisition control scheme library according to the plurality of operation healthdegrees to obtain a second optimization library, and combining the first optimization library to obtain a third optimization library; and according to the historical acquisition data, carrying out operation data complexity analysis of the plurality of new energy modules to obtain a plurality of data complexity, and carrying out optimization in the third optimization library by combining the plurality of acquisition cost degrees and the plurality of operation health degrees to obtain an optimal acquisition control scheme, and carrying out configuration control on data acquisition of the plurality of new energy modules.

The second aspect of the present disclosure provides a new energy data acquisition control system based on edge cloud, where the system is used in the above new energy data acquisition control method based on edge cloud, and the system includes: the scheme library construction module is used for setting acquisition control constraints according to the calculation power requirements of data acquisition analysis of a plurality of new energy modules in a new energy power station to be subjected to data acquisition and calculation power resources of cloud analysis of data acquisition by a cloud, and constructing an acquisition control scheme library for configuring the data acquisition analysis of the plurality of new energy modules at the cloud or an edge end; the cost degree analysis module is used for acquiring the communication distance information between the plurality of new energy modules and the power station data center, and performing data acquisition cost degree analysis to obtain a plurality of acquisition cost degrees; the first scheme optimizing module is used for optimizing the acquisition control scheme in the acquisition control scheme library according to the acquisition cost degrees to obtain a first optimizing library; the health degree analysis module is used for acquiring historical acquisition data of the plurality of new energy modules before a preset time node, analyzing the running health degree of the plurality of new energy modules and acquiring a plurality of running health degrees, wherein the historical acquisition data comprise historical environment data and historical power generation data; the second scheme optimizing module is used for optimizing the acquisition control scheme in the acquisition control scheme library according to the plurality of operation healthsof to obtain a second optimizing library, and combining the first optimizing library to obtain a third optimizing library; the configuration control module is used for analyzing the complexity of the operation data of the plurality of new energy modules according to the historical acquisition data to obtain a plurality of data complexities, and optimizing the operation complexities in the third optimizing library by combining the acquisition cost complexities and the operation health complexities to obtain an optimal acquisition control scheme, and carrying out configuration control on the data acquisition of the plurality of new energy modules.

In a third aspect of the present disclosure, there is provided a computer device comprising a memory storing a computer program and a processor implementing any of the steps of the first aspect of the present disclosure when the computer program is executed by the processor.

In a fourth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs any of the steps of the first aspect of the present disclosure.

One or more technical schemes provided by the application have at least the following technical effects or advantages:

The data acquisition analysis task is reasonably distributed at the edge end or the cloud end through analyzing the communication distance information and the cost degree, so that the data loss is reduced to the greatest extent, the data acquisition cost is reduced, and the data acquisition efficiency and reliability are improved; by combining historical acquisition data and operation health degree analysis, important attention and optimization are carried out on unhealthy operation modules, so that potential problems are found and solved in time, and the operation stability and maintainability of the new energy module are improved; by optimizing the acquisition control scheme and comprehensively considering the factors such as cost, health degree and the like, the purposes of reducing the data acquisition cost and improving the data acquisition efficiency are achieved, and the resource utilization is more efficient. In conclusion, the new energy data acquisition control method based on the edge cloud achieves the technical effects of improving data acquisition efficiency, reducing cost and improving system stability.

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

Drawings

Fig. 1 is a schematic flow chart of a new energy data acquisition control method based on edge cloud according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a new energy data acquisition control system based on edge cloud according to an embodiment of the present application;

fig. 3 is an internal structure diagram of a computer device according to an embodiment of the present application.

Reference numerals illustrate: the system comprises a scheme library construction module 10, a cost analysis module 20, a first scheme optimization module 30, a health analysis module 40, a second scheme optimization module 50 and a configuration control module 60.

Detailed Description

The embodiment of the application solves the technical problems of resource waste and cost increase caused by long communication distance and large consumption of computational resources in the process of data acquisition and cloud analysis of the traditional data acquisition method by providing the new energy data acquisition control method based on the edge cloud.

Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

As shown in fig. 1, an embodiment of the present application provides a new energy data acquisition control method based on edge cloud, where the method includes:

according to the calculation power requirements of data acquisition and analysis of a plurality of new energy modules in a new energy power station to be subjected to data acquisition and calculation power resources of data acquisition cloud analysis by a cloud, setting acquisition control constraints, and constructing an acquisition control scheme library for configuring the data acquisition and analysis of the plurality of new energy modules at the cloud or an edge end;

Firstly, evaluating the calculation power requirements of data acquisition and analysis of a plurality of new energy modules in a new energy power station, wherein the calculation power requirements comprise the data acquisition quantity, the analysis complexity and other factors of each module are analyzed to determine calculation power resources required by each module in the data acquisition and analysis process. And then, evaluating available cloud computing resources, including analyzing service level agreements of cloud service providers and the type and scale of cloud services subscribed by the new energy power station, so as to determine the total amount of available cloud computing resources.

According to the evaluation, the acquisition control constraint is set, and the sum of the calculation power demands of the new energy module for data acquisition and analysis at the cloud is ensured not to exceed the total calculation power resources of the cloud, so that the calculation power resources can be effectively allocated to meet the demands under the condition of limited resources.

After the calculation force demand and cloud resources are determined, an acquisition control scheme library is constructed, wherein the library comprises configuration schemes of data acquisition analysis tasks aiming at each new energy module at the cloud or edge end, and different configuration scheme combinations exist according to acquisition control constraint.

Furthermore, according to the power demand of data collection and analysis performed by a plurality of new energy modules in a new energy power station to be subjected to data collection and the power resource of cloud analysis performed by a cloud, a collection control constraint is set, and a collection control scheme library for configuring the data collection and analysis of a plurality of new energy modules at the cloud or an edge is constructed, and the method comprises the following steps:

acquiring a plurality of calculation force requirements of data acquisition and analysis of a plurality of new energy modules in a new energy power station to be subjected to data acquisition;

acquiring computing power resources of a cloud end of a new energy power station for data acquisition and analysis;

the sum of the calculation force demands configured on the cloud for data acquisition and analysis is smaller than or equal to the calculation force resources, and the calculation force demands are constructed as acquisition control constraints;

and randomly configuring data acquisition analysis tasks of the plurality of new energy modules at the edge ends or cloud ends of the plurality of new energy modules, generating a plurality of acquisition control schemes meeting the acquisition control constraint, and constructing and obtaining the acquisition control scheme library.

And determining a plurality of new energy modules in the new energy power station to be subjected to data acquisition, wherein the modules comprise photovoltaic modules, wind driven generators and the like, and each module has different positions, types and characteristics. For each new energy module, determining data acquisition and analysis tasks to be performed, wherein the tasks comprise acquisition of environmental parameters such as temperature, humidity, illumination and the like, acquisition of generating capacity data, detection of abnormal conditions and the like.

For each data acquisition and analysis task, the required computational effort resource is evaluated, the computational effort requirement depends on factors such as the frequency of data acquisition, the data volume, the analysis complexity and the like, for example, if a large amount of sensor data is required to be analyzed in real time, the required computational effort is higher; if only simple data storage and periodic analysis is performed, the computational effort requirements are relatively low. And finally, determining a plurality of calculation force demands of the plurality of new energy modules for data acquisition and analysis.

And (3) defining cloud computing power resources required by the new energy power station for data acquisition and analysis, wherein the resources comprise a computing server, storage equipment, network bandwidth and the like. For a data acquisition analysis task of a new energy power station, evaluating the data processing requirement of the new energy power station on the cloud, including evaluating the data volume, the data processing complexity, the frequency of data analysis and the like of each module, determining the cloud computing power scale required by the new energy power station according to the data processing requirement, including the number, the performance, the storage capacity, the network bandwidth and the like of computing resources, and determining the cloud computing power resource based on the cloud computing power scale so as to meet the requirement of the power station on data processing.

Summarizing the sum of the calculation power demands of all new energy modules configured on the cloud for data acquisition and analysis, comparing the acquired calculation power resources with the summarized calculation power demands, and ensuring that the total amount of the cloud calculation power resources is enough to meet the data acquisition and analysis demands of all the modules.

If the total amount of the cloud computing power resources is enough to meet the data acquisition and analysis requirements of all the modules, the total amount can be used as an acquisition control constraint, and the purpose of the total amount is to ensure that the sum of the computing power requirements for carrying out data acquisition and analysis on the cloud computing power resources is not more than the total amount of the cloud computing power resources.

If the aggregate computing power demand exceeds the total computing power resources of the cloud, the computing power allocation policy needs to be adjusted to meet the limitation of resources, such as reallocating computing power resources or optimizing some data acquisition analysis tasks to reduce the computing power demand.

For a plurality of new energy modules to be subjected to data acquisition, a plurality of acquisition control schemes are randomly generated, and the schemes relate to different combination modes of configuring data acquisition analysis tasks at an edge end or a cloud end. And checking whether each generated acquisition control scheme meets the acquisition control constraint established before, namely ensuring that the sum of calculation force requirements for data acquisition analysis configured at the cloud is smaller than or equal to the calculation force resource. For the acquisition control schemes meeting the acquisition control constraint, the acquisition control schemes are recorded and incorporated into an acquisition control scheme library, and the schemes represent different data acquisition analysis task configuration modes, so that the cloud resource limit can be met, and meanwhile, the effectiveness and the high efficiency of data acquisition are ensured.

Collecting communication distance information of the plurality of new energy modules and a power station data center, and performing data acquisition cost degree analysis to obtain a plurality of acquisition cost degrees;

And acquiring the communication distance from each new energy module in the new energy power station to the power station data center by using a sensor, GPS positioning or other distance measurement technologies, and acquiring communication distance information. For each new energy module, carrying out data acquisition cost degree analysis, wherein the calculation of the data acquisition cost degree can be based on indexes such as communication cost, energy consumption, time cost and the like, wherein the communication cost can comprise the cost of communication equipment, the cost of data transmission and the like; the energy consumption can be estimated according to the amount of electricity consumed in the data transmission process; the time cost may take into account the impact of delays in data transmission on system performance. And obtaining a plurality of acquisition cost degrees aiming at a plurality of new energy modules through analysis, wherein each cost degree corresponds to one new energy module, and the larger the distance is, the larger the cost degree is.

Further, collecting the communication distance information between the plurality of new energy modules and the power station data center, and performing data collection cost degree analysis to obtain a plurality of collection cost degrees, including:

Collecting communication distance information of the plurality of new energy modules and a power station data center, wherein the power station data center is in communication connection with the cloud;

And carrying out classified mapping on the data acquisition cost degree according to the communication distance information to obtain the acquisition cost degrees, wherein the classified mapping is carried out based on a data acquisition cost mapping table, and the data acquisition cost mapping table is constructed by a plurality of sample communication distance information and a plurality of sample data acquisition cost degree mapping.

Sensors are installed in the power station or at proper positions around the power station for measuring the communication distance between the new energy module and the power station data center, and the sensors can be wireless communication modules, GPS positioning equipment and the like. And starting the sensor to measure the communication distance, obtaining the distance information between each new energy module and the power station data center, and ensuring the stable communication connection between the power station data center and the cloud.

And collecting a plurality of sample communication distance information and corresponding data acquisition cost degree, wherein the data acquisition cost degree comprises communication cost, energy consumption, time cost and the like, the sample data can be obtained from existing power station data or through field measurement, and a mapping model is built by fitting data according to the collected sample data by using a statistical analysis method or a machine learning algorithm.

And according to the established mapping model, the communication distance information is subjected to classified mapping, namely, each communication distance is mapped to the corresponding data acquisition cost degree, so that the data acquisition cost can be estimated according to the communication distance. And obtaining corresponding data acquisition cost degrees according to the established mapping relation for the communication distance between each new energy module and the power station data center, and obtaining a plurality of acquisition cost degrees for subsequent optimization.

According to the acquisition cost degrees, optimizing an acquisition control scheme in the acquisition control scheme library to obtain a first optimization library;

Setting an optimization target, namely reducing the sum of acquisition cost of data acquisition and analysis at the cloud, means that the optimization algorithm aims to find a group of acquisition control schemes so that the cost of data acquisition and analysis tasks executed at the cloud is as low as possible. Various optimization algorithms, such as genetic algorithms, simulated annealing algorithms, particle swarm algorithms, etc., can be employed to achieve this goal, which can search the solution space for an optimal combination of solutions that minimizes the optimization objective.

In the optimization process, the schemes in the collection control scheme library are used as initial solutions, then the schemes are gradually adjusted through continuous iteration to find optimal solutions, for each candidate scheme, the sum of collection cost degrees of data collection analysis at the cloud is calculated and used as an objective function of an optimization algorithm, and the optimization algorithm adjusts scheme configuration through evaluating cost degrees of different schemes until an optimal scheme combination minimizing the objective function is found.

When the optimization algorithm converges, a first optimization library is obtained, wherein the first optimization library comprises a group of acquisition control schemes which enable the sum of acquisition cost of data acquisition analysis to be minimum.

Further, according to the plurality of acquisition cost degrees, optimizing an acquisition control scheme in the acquisition control scheme library to obtain a first optimized library, including:

constructing a cost optimization function, wherein the cost optimization function is as follows:

；

Wherein FC is the cost fitness, m is the number of new energy modules configured at the cloud end in the data acquisition analysis in the acquisition control scheme, For the weight of the ith new energy module set according to the power generation level of the plurality of new energy modules,The acquisition cost degree of the ith new energy module configured at the cloud end is analyzed for data acquisition in the acquisition control scheme;

randomly selecting a plurality of initial acquisition control schemes in the acquisition control scheme library;

respectively acquiring a plurality of initial cost fitness degrees according to the configuration positions of the data acquisition and analysis of the plurality of new energy modules in the initial acquisition control scheme and combining the plurality of acquisition cost degrees;

Classifying the plurality of initial acquisition control schemes according to the plurality of initial cost fitness to obtain a plurality of acquisition control scheme groups, wherein each acquisition control scheme group comprises one acquisition control scheme with the largest initial cost fitness;

According to the preset adjustment quantity and the acquisition control scheme with the largest initial cost fitness as an adjustment direction, adjusting other acquisition control schemes in the acquisition control scheme groups to obtain updated acquisition control scheme groups;

Continuously optimizing and updating the plurality of acquisition control scheme groups, and deleting the acquisition control scheme group with the minimum sum of cost fitness after the preset optimizing times are reached;

and continuing to optimize to reach convergence times, outputting an acquisition control scheme group with the largest sum of cost fitness, and obtaining a first optimization library.

The cost optimization function is as follows:

；

Wherein FC represents cost fitness; m is the number of new energy modules configured at the cloud end in the data acquisition analysis in the acquisition control scheme; The weight of the ith new energy module is set according to the power generation level, and the contribution degree of the new energy module to the whole cost is reflected; The acquisition cost degree of the ith new energy module arranged at the cloud represents the cost required by data acquisition analysis of the module arranged at the cloud.

Randomly sampling in an acquisition control scheme library, selecting a plurality of initial acquisition control schemes, and randomly selecting different schemes from the scheme library through a random number generator to obtain the plurality of initial acquisition control schemes as starting points of an optimization algorithm.

Traversing the selected multiple initial acquisition control schemes, processing each scheme, adopting the cost optimization function for each initial scheme according to the configuration position and the corresponding acquisition cost degree of data acquisition analysis of each new energy module, multiplying the weight of each module by the acquisition cost degree corresponding to the configuration position, adding the costs of all the modules to obtain the total cost fitness of the scheme, and outputting the cost fitness of all the initial schemes to obtain multiple initial cost fitness serving as an index for evaluating the advantages and disadvantages of each scheme.

And sorting the plurality of initial acquisition control schemes according to the corresponding initial cost fitness, arranging the plurality of initial acquisition control schemes from large to small, dividing schemes with similar cost fitness into the same group according to the sorted initial cost fitness, and selecting a scheme with the largest cost fitness as a representative scheme of the group for each scheme group with the same cost fitness.

The number of schemes to be adjusted, namely the number of schemes to be adjusted in each acquisition control scheme group, is preset according to specific requirements. According to the acquisition control scheme with the largest initial cost adaptability, the acquisition control scheme is used as an optimization direction, namely, the scheme with the largest cost adaptability is used as an adjustment direction, and other schemes except the scheme with the largest cost adaptability in each acquisition control scheme group are adjusted according to the selected adjustment direction, for example, adjustment is performed by modifying the data acquisition configuration position, optimizing the communication route, adjusting the data processing strategy and the like. And for each acquisition control scheme group, adding the adjusted scheme into the scheme group to replace the original scheme, and obtaining a plurality of updated acquisition control scheme groups.

The optimization times are preset, namely, how many times the acquisition control scheme group is subjected to optimization updating is determined. And carrying out multiple optimization updating on each acquisition control scheme group until the preset optimization times are reached, after each optimization updating, recalculating the sum of the cost fitness of all schemes in each acquisition control scheme group, after the preset optimization times are reached, finding the scheme group with the minimum sum of the cost fitness from all the acquisition control scheme groups, deleting all the schemes in the scheme group and all the schemes in the scheme group, and removing the scheme group from the candidate schemes. Therefore, the quality of the scheme can be continuously improved, the scheme with better performance is reserved, and meanwhile, less excellent schemes are reduced, so that the optimal solution can be searched more effectively.

Presetting a convergence number, continuously optimizing the solution before the convergence number is reached, recalculating the sum of the cost fitness of each acquisition control scheme group after each optimization, checking whether the preset convergence number is reached, selecting the scheme group with the largest sum of the cost fitness from all the acquisition control scheme groups after the preset convergence number is reached, and outputting the scheme group as a first optimization library.

Acquiring historical acquisition data of the plurality of new energy modules before a preset time node, and analyzing the running health degrees of the plurality of new energy modules to obtain a plurality of running health degrees, wherein the historical acquisition data comprises historical environment data and historical power generation data;

the preset time node is a time set according to actual conditions and specific requirements, such as the past week, month, and the like. Acquiring historical acquisition data of the plurality of new energy modules before a preset time node, wherein the data comprise historical environment data and historical power generation data, the historical environment data comprise acquisition records of environmental parameters such as temperature, humidity and illumination, and the historical power generation data refer to power generation capacity records of each new energy module in a historical time period.

Performing operation health analysis by using historical environment data and historical power generation data, wherein the analysis can adopt a machine learning model method, and the influence of environmental conditions on the performance of the new energy module, such as the influence of temperature on the photovoltaic power generation efficiency and the like, is established by analyzing the historical environment data; and (3) evaluating the power generation condition of each new energy module by analyzing the historical power generation data, wherein the power generation condition comprises the stability, the change trend and the like of the generated energy. And obtaining a plurality of operation health indexes aiming at each new energy module through operation health analysis, wherein the indexes can reflect the information of the operation state, performance and the like of each module.

Further, acquiring historical acquisition data of the plurality of new energy modules before a preset time node, performing operation health analysis of the plurality of new energy modules, and obtaining a plurality of operation health, wherein the historical acquisition data comprises:

Acquiring a plurality of historical acquisition data of the plurality of new energy modules before a preset time node, and calculating to acquire a plurality of average historical acquisition data, wherein each average historical acquisition data comprises average historical environment data and average historical power generation data;

acquiring a sample environment data set and a sample power generation data set according to the power generation data record of the new energy module;

Adopting the sample environment data set and the sample power generation data set to construct a theoretical power generation analyzer, and analyzing a plurality of average historical environment data to obtain a plurality of theoretical power generation data;

and calculating and obtaining the operation health degree of the new energy modules according to the theoretical power generation data and the average historical power generation data.

And acquiring a plurality of historical acquisition data of each new energy module in front of a preset time node from a record or data storage system of the new energy power station, wherein the data comprise historical environment data such as temperature, humidity, wind speed and the like, and historical power generation data such as generated energy, power and the like. For the historical environment data, averaging the data of each time point to obtain average historical environment data; and for the historical power generation data, averaging the power generation data of each time point to obtain average historical power generation data.

Traversing the power generation data record of the new energy module, and acquiring corresponding environmental data to form a sample environmental data set aiming at each time point. The generated energy or power data is extracted from the generated energy data record of the new energy module, and the data can be generated energy data in a continuous time period or generated power data at a discrete time point as a sample generated energy data set.

A theoretical power generation analysis model is designed that predicts power generation data based on given environmental data, and this power generation model may be a machine learning based model, such as a neural network. And training the model by adopting the sample environment data set and the sample power generation data set as training data, and optimizing model parameters in the training process until the model converges or reaches preset iteration times, so as to finally obtain the theoretical power generation analyzer.

And aiming at each new energy module, using the constructed theoretical power generation analyzer, inputting the corresponding average historical environment data, operating the theoretical power generation analyzer, analyzing the environment data, predicting the power generation data of each time point, and obtaining the theoretical power generation data of each time point according to the output of the theoretical power generation analyzer, wherein the data represent the power generation data which should be theoretically generated by the new energy module under the given environment condition.

For each new energy module, comparing the corresponding theoretical power generation data with average historical power generation data, and calculating the deviation between the theoretical power generation data and the average historical power generation data, wherein the deviation can be realized by calculating the difference between the actual power generation data and the theoretical power generation data, the smaller difference value indicates that the power generation performance of the module is closer to the theoretical expectation, and the larger difference value indicates that the abnormality exists.

The deviation condition of each new energy module is comprehensively considered, the operation health degree of each module is evaluated, for example, the health state of each module is judged by using a scoring interval, for example, the modules are classified into the normal, abnormal or maintenance-requiring grades according to the deviation.

Optimizing the acquisition control scheme in the acquisition control scheme library according to the plurality of operation healthdegrees to obtain a second optimization library, and combining the first optimization library to obtain a third optimization library;

And optimizing in the collection control scheme library according to the plurality of operation health indexes, namely, adjusting the configuration of the data collection analysis tasks to improve the operation health of the modules for data collection analysis at the edge, for example, reassigning tasks, and configuring the data collection analysis tasks of the modules with higher operation health at the edge so as to reduce the execution requirement of the data collection analysis tasks at the cloud end, thereby improving the operation health of the edge.

And optimizing to obtain a second optimizing library, wherein the second optimizing library comprises acquisition control schemes which are adjusted according to the operation health degree, and the acquisition control schemes enable the operation health degree of the module for carrying out data acquisition analysis at the edge to be improved.

And acquiring a union set of the first optimizing library and the second optimizing library as the third optimizing library, wherein a final acquisition control scheme is included, and the requirements and the cost of a module for carrying out data acquisition and analysis at a cloud end are considered while the operation health degree of the data acquisition and analysis at an edge end is improved.

Further, according to the plurality of operation healthdegrees, optimizing the collection control scheme in the collection control scheme library to obtain a second optimization library, including:

Constructing a health optimization function, wherein the formula is as follows:

；

wherein FH is health fitness, n is the number of new energy modules configured at the edge end in the data acquisition analysis in the acquisition control scheme, For the weight of the jth new energy module set according to the power generation level of the new energy modules,The acquisition cost of a j new energy module arranged at the side end is analyzed for data acquisition in an acquisition control scheme;

optimizing in the acquisition control scheme library according to the health optimization function to obtain the second optimization library;

And acquiring a union of the first optimization library and the second optimization library as the third optimization library.

The health optimization function is as follows:

；

wherein FH is fitness; n is the number of new energy modules configured at the edge end by data acquisition and analysis in the acquisition control scheme; the weight of the jth new energy module is set according to the power generation level, and the larger the weight is, the higher the importance of the module is; The collection cost degree of the j new energy module is represented by the cost configured at the edge, and the smaller the cost degree is, the lower the data collection analysis cost of the module at the edge is. The objective of the health optimization function is to maximize the fitness FH, that is, optimize the acquisition control scheme, so that the health condition of the new energy module configured at the edge end is optimized by data acquisition analysis.

Traversing each acquisition control scheme in the acquisition control scheme library, calculating the health fitness of each acquisition control scheme according to a health optimization function, selecting a scheme with the highest health fitness from all the acquisition control schemes, adding the scheme into a second optimization library, repeating the steps until all the acquisition control schemes are traversed, and integrating the acquisition control schemes with the highest health fitness to form the second optimization library.

And merging all the acquisition control schemes in the first optimization library and the second optimization library, and taking the merged acquisition control scheme set as a third optimization library.

And according to the historical acquisition data, carrying out operation data complexity analysis of the plurality of new energy modules to obtain a plurality of data complexity, and carrying out optimization in the third optimization library by combining the plurality of acquisition cost degrees and the plurality of operation health degrees to obtain an optimal acquisition control scheme, and carrying out configuration control on data acquisition of the plurality of new energy modules.

The complexity of the operation data of the plurality of new energy modules is analyzed by using the historical collection data, and the analysis can comprise analysis of statistical characteristics, time sequence modes, abnormal conditions and the like of the historical data so as to acquire the complexity of the data of each module.

The method comprises the steps of combining a plurality of indexes such as the complexity of running data, the acquisition cost, the running health and the like, and optimizing in a third optimizing library, wherein the factors such as the complexity of the data, the acquisition cost, the running state of equipment and the like are comprehensively considered, a multi-objective optimizing algorithm such as a multi-objective genetic algorithm, multi-objective particle swarm optimization and the like is adopted, so that a plurality of optimizing targets are simultaneously considered, an optimal acquisition control scheme is found, the data complexity of data acquisition and analysis at a cloud is improved, so that a complex data analysis task can be placed at the cloud with stronger calculation power, and the accuracy and the safety of new energy data acquisition and analysis are improved.

And searching and iterating an optimization algorithm to obtain an optimal acquisition control scheme, wherein the optimal acquisition control scheme considers factors such as data complexity, acquisition cost, operation health degree and the like, so that the efficiency and performance of data acquisition analysis in the whole system reach an optimal state. And carrying out configuration control on the data acquisition of each new energy module based on the optimal acquisition control scheme, so that the data acquisition and analysis can be effectively carried out under the condition of limited resources.

Further, according to the historical collected data, performing operation data complexity analysis of the plurality of new energy modules to obtain a plurality of data complexity, and optimizing in the third optimizing library in combination with the plurality of collection cost degrees and the plurality of operation health degrees to obtain an optimal collection control scheme, including:

acquiring a sample historical acquisition data set according to the historical operation data record of the new energy module, and acquiring a sample data complexity set;

Constructing an operation data complexity analyzer according to the sample historical acquisition data set and the sample data complexity set, and identifying historical acquisition data of a plurality of new energy modules to obtain a plurality of data complexity;

Constructing a total optimization function, wherein the total optimization function is as follows:

；

Where FIT is the total fitness, FD is the complex fitness, Is the weight of the ith new energy module,、AndCost weight, health weight and complex weight, respectively, and sum to 1,Analyzing the data complexity of the ith new energy module configured at the cloud for data acquisition in the acquisition control scheme;

And optimizing in the third optimizing library according to the total optimizing function to obtain an acquisition control scheme with the maximum total fitness as the optimal acquisition control scheme.

And acquiring a history operation data record of the new energy module, wherein the history operation data record comprises history environment data and history power generation data. The collected data is extracted from the historical operation data to form a sample historical collection data set, the data complexity of each data sample in the set is calculated, the data complexity can be evaluated according to indexes such as the change amplitude, the frequency and the correlation of the data, the calculated data complexity is formed into a sample data complexity set, and each data sample corresponds to one data complexity value.

An operational data complexity analyzer is designed, which can be a model based on a machine learning method, such as decision trees, random forests, support vector machines, neural networks, and the like. And training the model by adopting the sample history acquisition data set and the sample data complexity set, and selecting and optimizing the model by adopting cross verification and other technologies in the training process so as to improve the generalization capability and accuracy of the model and finally obtain the running data complexity analyzer meeting the requirements.

And analyzing the historical collected data of the plurality of new energy modules by using the constructed data complexity analyzer, and predicting each data sample by using the data complexity analyzer according to the characteristics and the model of the data sample to give corresponding data complexity values, and finally outputting a plurality of data complexity of the plurality of new energy modules, wherein each module corresponds to one data complexity value to reflect the complexity degree of the historical collected data.

The overall optimization function is as follows:

；

Wherein, FIT is the total fitness and represents the comprehensive evaluation of the acquisition control scheme; FC is the cost fitness and FH is the health fitness; 、 And Cost weight, health weight and complex weight, respectively, and their sum is 1;

FD is a complex fitness, representing a fitness in terms of data complexity; analyzing the data complexity of the ith new energy module configured at the cloud for data acquisition in the acquisition control scheme; The weight of the ith new energy module.

By constructing such a total optimization function, factors such as cost, health, data complexity and the like can be comprehensively considered, so that the acquisition control scheme can be more comprehensively evaluated and optimized.

And calculating the total fitness of each acquisition control scheme in the third optimization library by using a total optimization function, wherein the total fitness is a weighted sum of the cost fitness, the health fitness and the complex fitness, and selecting the acquisition control scheme corresponding to the maximum value from the calculated total fitness as the optimal acquisition control scheme.

In summary, the new energy data acquisition control method based on the edge cloud provided by the embodiment of the application has the following technical effects:

1. the data acquisition analysis task is reasonably distributed at the edge end or the cloud end through analyzing the communication distance information and the cost degree, so that the data loss is reduced to the greatest extent, the data acquisition cost is reduced, and the data acquisition efficiency and reliability are improved;

2. By combining historical acquisition data and operation health degree analysis, important attention and optimization are carried out on unhealthy operation modules, so that potential problems are found and solved in time, and the operation stability and maintainability of the new energy module are improved;

3. By optimizing the acquisition control scheme and comprehensively considering the factors such as cost, health degree and the like, the purposes of reducing the data acquisition cost and improving the data acquisition efficiency are achieved, and the resource utilization is more efficient.

In conclusion, the new energy data acquisition control method based on the edge cloud achieves the technical effects of improving data acquisition efficiency, reducing cost and improving system stability.

Based on the same inventive concept as the new energy data acquisition control method based on the edge cloud in the foregoing embodiment, as shown in fig. 2, the present application provides a new energy data acquisition control system based on the edge cloud, where the system includes:

The scheme library construction module 10 is used for setting acquisition control constraints according to the calculation power requirements of data acquisition and analysis of a plurality of new energy modules in a new energy power station to be subjected to data acquisition and calculation power resources of cloud analysis of data acquisition by a cloud, and constructing an acquisition control scheme library for configuring the data acquisition and analysis of the plurality of new energy modules at the cloud or an edge;

The cost degree analysis module 20 is used for collecting the communication distance information between the plurality of new energy modules and the power station data center, and performing data collection cost degree analysis to obtain a plurality of collection cost degrees;

the first scheme optimizing module 30 is configured to optimize an acquisition control scheme in the acquisition control scheme library according to the plurality of acquisition cost degrees, so as to obtain a first optimized library;

The health degree analysis module 40 is configured to obtain historical collected data of the plurality of new energy modules before a preset time node, perform operation health degree analysis of the plurality of new energy modules, and obtain a plurality of operation health degrees, where the historical collected data includes historical environmental data and historical power generation data;

The second scheme optimizing module 50 is configured to perform optimization of the acquisition control scheme in the acquisition control scheme library according to the plurality of operation healthnesses, obtain a second optimized library, and combine with the first optimized library to obtain a third optimized library;

The configuration control module 60 is configured to perform analysis on the complexity of the operation data of the plurality of new energy modules according to the historical acquisition data, obtain a plurality of data complexities, and perform optimization in the third optimization library in combination with the plurality of acquisition cost degrees and the plurality of operation health degrees, obtain an optimal acquisition control scheme, and perform configuration control on the data acquisition of the plurality of new energy modules.

Further, the system also comprises an acquisition control scheme library construction module for executing the following operation steps:

Further, the system also comprises an acquisition cost acquisition module for executing the following operation steps:

Further, the system also comprises a first optimized library acquisition module for executing the following operation steps:

；

Further, the system also includes an operation health acquisition module to perform the following operation steps:

Further, the system also comprises a third optimized library acquisition module for executing the following operation steps:

Constructing a health optimization function, wherein the formula is as follows:

；

Further, the system further comprises an optimal acquisition control scheme acquisition module for executing the following operation steps:

；

In the present specification, through the foregoing detailed description of the new energy data collection control method based on the edge cloud, those skilled in the art can clearly know the new energy data collection control system based on the edge cloud in this embodiment, and since the new energy data collection control system corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant places refer to the description of the method section.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in FIG. 3. The computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the processor of the computer device is configured to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium storing an operating system, a computer program and a database, and an internal memory providing an environment for the operating system and the computer program in the non-volatile storage medium to run; the network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by the processor to realize the new energy data acquisition control method based on the edge cloud.

It will be appreciated by those skilled in the art that the structure shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The new energy data acquisition control method based on the edge cloud is characterized by comprising the following steps of:

According to the historical acquisition data, carrying out operation data complexity analysis of the plurality of new energy modules to obtain a plurality of data complexity, and carrying out optimization in the third optimization library by combining the plurality of acquisition cost degrees and the plurality of operation health degrees to obtain an optimal acquisition control scheme, and carrying out configuration control on data acquisition of the plurality of new energy modules;

and according to the acquisition cost degrees, optimizing an acquisition control scheme in the acquisition control scheme library to obtain a first optimization library, wherein the optimization library comprises:

；

continuing to optimize to reach convergence times, outputting an acquisition control scheme group with the largest sum of cost fitness, and obtaining a first optimization library;

and according to the operation healthness, optimizing the acquisition control scheme in the acquisition control scheme library to obtain a second optimization library, wherein the second optimization library comprises:

Constructing a health optimization function, wherein the formula is as follows:

；

Acquiring a union of the first optimization library and the second optimization library as the third optimization library;

The method comprises the steps of carrying out operation data complexity analysis of a plurality of new energy modules according to historical acquisition data to obtain a plurality of data complexity, and carrying out optimization in a third optimization library by combining the plurality of acquisition cost degrees and the plurality of operation health degrees to obtain an optimal acquisition control scheme, wherein the method comprises the following steps:

；

2. The method according to claim 1, wherein setting the acquisition control constraint according to the power demand of the data acquisition analysis performed by the plurality of new energy modules in the new energy power station to be subjected to data acquisition and the power resource of the data acquisition cloud analysis performed by the cloud, and constructing an acquisition control scheme library for configuring the data acquisition analysis of the plurality of new energy modules at the cloud or the edge, comprises:

3. The method of claim 1, wherein collecting the communication distance information between the plurality of new energy modules and the power station data center and performing data collection cost degree analysis to obtain a plurality of collection cost degrees, comprises:

4. The method of claim 1, wherein obtaining historical acquisition data of the plurality of new energy modules before a preset time node, performing an operation health analysis of the plurality of new energy modules, and obtaining a plurality of operation health, the historical acquisition data comprising:

5. The new energy data acquisition control system based on edge cloud, which is characterized by being used for implementing the new energy data acquisition control method based on edge cloud according to any one of claims 1-4, wherein the system comprises:

the scheme library construction module is used for setting acquisition control constraints according to the calculation power requirements of data acquisition analysis of a plurality of new energy modules in a new energy power station to be subjected to data acquisition and calculation power resources of cloud analysis of data acquisition by a cloud, and constructing an acquisition control scheme library for configuring the data acquisition analysis of the plurality of new energy modules at the cloud or an edge end;

The cost degree analysis module is used for acquiring the communication distance information between the plurality of new energy modules and the power station data center, and performing data acquisition cost degree analysis to obtain a plurality of acquisition cost degrees;

the first scheme optimizing module is used for optimizing the acquisition control scheme in the acquisition control scheme library according to the acquisition cost degrees to obtain a first optimizing library;

The health degree analysis module is used for acquiring historical acquisition data of the plurality of new energy modules before a preset time node, analyzing the running health degree of the plurality of new energy modules and acquiring a plurality of running health degrees, wherein the historical acquisition data comprise historical environment data and historical power generation data;

The second scheme optimizing module is used for optimizing the acquisition control scheme in the acquisition control scheme library according to the plurality of operation healthsof to obtain a second optimizing library, and combining the first optimizing library to obtain a third optimizing library;

the configuration control module is used for analyzing the complexity of the operation data of the plurality of new energy modules according to the historical acquisition data to obtain a plurality of data complexities, and optimizing the operation complexities in the third optimizing library by combining the acquisition cost complexities and the operation health complexities to obtain an optimal acquisition control scheme, and carrying out configuration control on the data acquisition of the plurality of new energy modules.

6. Computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the new energy data collection control method based on edge cloud of any one of claims 1 to 4.

7. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the new energy data collection control method based on edge cloud as claimed in any one of claims 1 to 4.