CN113905386B - Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm - Google Patents

Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm Download PDF

Info

Publication number
CN113905386B
CN113905386B CN202111034979.0A CN202111034979A CN113905386B CN 113905386 B CN113905386 B CN 113905386B CN 202111034979 A CN202111034979 A CN 202111034979A CN 113905386 B CN113905386 B CN 113905386B
Authority
CN
China
Prior art keywords
node
gateway
particle
particle swarm
deployment
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.)
Active
Application number
CN202111034979.0A
Other languages
Chinese (zh)
Other versions
CN113905386A (en
Inventor
羊彦
吴庭强
张南
洪国旗
刘浩琪
符雯迪
王梓卿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northwestern Polytechnical University
Original Assignee
Northwestern Polytechnical University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northwestern Polytechnical University filed Critical Northwestern Polytechnical University
Priority to CN202111034979.0A priority Critical patent/CN113905386B/en
Publication of CN113905386A publication Critical patent/CN113905386A/en
Application granted granted Critical
Publication of CN113905386B publication Critical patent/CN113905386B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/18—Network planning tools
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • 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
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The invention discloses a Mesh gateway deployment optimization method based on a self-adaptive hybrid particle swarm algorithm, and provides a method for solving the problem that the gateway deployment of a global particle swarm algorithm in a dynamic network falls into a local optimal solution by utilizing an improved hybrid particle swarm algorithm, namely the self-adaptive hybrid particle swarm optimization algorithm. Firstly, based on the specific distribution of the positions of routing nodes, establishing a topological relation between a gateway node and adjacent nodes, establishing a model to calculate a fitness function of the gateway node, searching a global optimal solution by adopting a self-adaptive hybrid particle swarm optimization algorithm for improving inertial weight and social factors, finally recording various optimal positions according to the node particle deployment history, adjusting the speed of the optimal solution, and carrying out iterative updating by adopting an improved iterative function to obtain the optimal solution. The method can quickly converge to approach the global optimum value, and can prevent the local optimum solution from being trapped in to a larger extent, thereby solving the problem of low convergence precision or even non-convergence, and simultaneously improving the adaptability to the deployment of the dynamic network gateway.

Description

Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a Mesh gateway deployment optimization method.
Background
In the rapid development process of the 5G network, the internet of things is regarded as a wave of information technology revolution after the internet, and the importance of the wireless Mesh network is more and more prominent in the world of everything interconnection. Meanwhile, in the multi-gateway characteristic of the wireless Mesh network, a gateway deployment optimization algorithm is crucial, the service quality of the whole network is directly influenced, and how to effectively deploy the gateway can improve the service quality of the Mesh network to the greatest extent.
The document "PSO-based wireless Mesh gateway optimization deployment algorithm [ J ]. academic report of sensing technology, 2008" proposes a method for deploying a Mesh gateway by solving based on a particle swarm algorithm. The method comprises the steps of initializing a network model, routing particle coding information and solving by adopting a PSO iterative formula. However, the method adopts fixed inertia weight, and does not distinguish social factors. The method is very sensitive to the particle initialization speed and position, the problems of dispersion, combination optimization and the like cannot be effectively solved, the parameter setting needs to be set according to the actual situation, the adaptability to the dynamic network gateway deployment is low, the dynamic network gateway deployment is easy to fall into the local optimal solution, and the convergence precision is low or even the convergence is not caused.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a Mesh gateway deployment Optimization method based on a self-Adaptive Hybrid Particle Swarm algorithm, and the problem that the gateway deployment of a global Particle Swarm algorithm (PSO) in a dynamic network falls into a local optimal solution is solved by utilizing an improved Hybrid Particle Swarm algorithm, namely an Adaptive Hybrid Particle Swarm Optimization (AHPSO) algorithm. Firstly, based on the specific distribution of the positions of routing nodes, establishing a topological relation between a gateway node and adjacent nodes, establishing a model to calculate an adaptive function of the gateway node, then searching a global optimal solution for the gateway node by adopting an improved inertial weight and social factor AHPSO algorithm, finally recording various optimal positions according to the node particle deployment history, adjusting the speed of the optimal solution, and carrying out iterative updating by adopting an improved iterative function to obtain the optimal solution. The method can quickly converge to approach the global optimum value, and can prevent the local optimum solution from being trapped in to a larger extent, thereby solving the problem of low convergence precision or even non-convergence, and simultaneously improving the adaptability to the deployment of the dynamic network gateway.
The technical scheme adopted by the invention for solving the technical problem comprises the following steps:
step 1: initializing information of node particles, deploying m gateway nodes, wherein each node particle has n dimensions, and the coordinate of the ith gateway node particle is expressed as: x i ＝(x i1 ,x i2 ,x i3 ,…x in ) The velocity of the ith gateway node particle is expressed as: v i ＝(v i1 ,v i2 ,v i3 ,…v in ) Setting a maximum iteration number num and a convergence threshold value epsilon;
step 2: definition and gateway w k The set formed by the nodes with the distance less than the communication radius is a gateway adjacency set GAS k (ii) a Any node in the network to the gateway w k The hop count of (a) is expressed as:
Figure BDA0003246771610000021
wherein v is i 、v j Respectively representing an ith node and a jth node;
the fitness function f (x) is then expressed as:
Figure BDA0003246771610000022
wherein S represents the scale of the Mesh network;
and step 3: updating individual optimal solution, namely historical optimal position P of node particles in the deployment process by using fitness function f (X) i ＝(p i1 ,p i2 ,p i3 ,…p in ) Then, the global optimal solution, namely the historical optimal position P of the whole particle swarm in the flight process is updated g ＝(p g1 ,p g2 ,p g3 ,…p gn ) Then, the optimal value of the neighborhood of the particle is updated
Figure BDA0003246771610000023
Figure BDA0003246771610000024
And 4, step 4: updating iteration times N, and determining an inertia weight omega by adopting an improved sigmoid function, wherein the inertia weight omega is expressed as follows:
Figure BDA0003246771610000025
in the formula: e is a natural constant, K is the maximum value of the sigmoid curve, and K e The curvature of the sigmoid curve, namely the change rate of the curve;
and 5: iterative equations (4) and (5) are substituted with the inertial weight ω into the velocity and position updates for the ith node particle:
Figure BDA0003246771610000026
Figure BDA0003246771610000027
wherein, V i t+1 Velocity, V, of the node particle at time t +1 i t Is the velocity of the node particle at time t,
Figure BDA0003246771610000028
the position of the node particle at time t +1,
Figure BDA0003246771610000029
the position of the node particle at the time t; c 1 The individual learning factor is node particles, and the value of the individual learning factor is an acceleration constant; c 2 The social learning factor is a node particle, and the value of the social learning factor is an acceleration constant; ξ and η are random numbers in the range of 0 to 1; q is the relative proportion of the global social factor and the local social factor, 0<q<1；
Step 6: and (4) judging whether the maximum iteration number num is reached or the difference value between two continuous calculation results is smaller than a convergence threshold epsilon, finishing the iteration when any condition is met, otherwise, repeating the step 4 and the step 5, and obtaining the optimal solution after repeated iteration updating.
Preferably, the maximum iteration number num is 240-260, and the convergence threshold epsilon is 0.0003-0.001.
The invention has the following beneficial effects:
compared with the gateway deployment by adopting the PSO algorithm, the AHPSO algorithm has the advantages that the overall optimization effect is better than that of the traditional PSO algorithm, the PSO algorithm is slightly influenced by the network structure, but is greatly influenced by the initial value of the randomization, and is relatively easy to fall into local optimization. After the AHPSO algorithm adopts self-adaptive weight and local search, the topological structure of the wireless Mesh network is effectively associated to a certain extent, the speed change of particles is updated, and the increased local search ensures that the algorithm has high search precision, is not easy to fall into a local optimal solution and has strong stability.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a deployment distribution diagram drawn according to the actual scene routing node position according to the embodiment of the present invention.
Fig. 3 is a diagram of a deployment optimization result of a gateway routing node according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
A Mesh gateway deployment optimization method based on a self-adaptive hybrid particle swarm algorithm comprises the following steps:
step 1: initializing information of node particles, deploying m gateway nodes, wherein each node particle has n dimensions, and the coordinate of the ith gateway node particle is expressed as: x i ＝(x i1 ,x i2 ,x i3 ,…x in ) The velocity of the ith gateway node particle is expressed as: v i ＝(v i1 ,v i2 ,v i3 ,…v in ) Setting a maximum iteration number num and a convergence threshold epsilon;
step 2: definition and gateway w k The set formed by the nodes with the distance less than the communication radius is a gateway adjacency set GAS k (ii) a Any node in the network to the gateway w k The hop count of (a) is expressed as:
Figure BDA0003246771610000031
the fitness function f (x) is then expressed as:
Figure BDA0003246771610000032
and 3, step 3: updating individual optimal solution, namely historical optimal position P of node particles in the deployment process by using fitness function f (X) i ＝(p i1 ,p i2 ,p i3 ,…p in ) Then, the global optimal solution, namely the historical optimal position P of the whole particle swarm in the flight process, is updated g ＝(p g1 ,p g2 ,p g3 ,…p gn )；
And 4, step 4: updating iteration times N, and determining an inertia weight omega by adopting an improved sigmoid function, wherein the inertia weight omega is expressed as follows:
Figure BDA0003246771610000033
in the formula: e is a natural constant, K is the maximum value of the sigmoid curve, and K e The curvature of the sigmoid curve is the change rate of the curve;
and 5: iterative equations (4) and (5) are substituted with the inertial weight ω into the velocity and position updates for the ith node particle:
Figure BDA0003246771610000041
Figure BDA0003246771610000042
wherein, V i t+1 Velocity, V, of the node particle at time t +1 i t Is the velocity of the node particle at time t,
Figure BDA0003246771610000043
the position of the node particle at time t +1,
Figure BDA0003246771610000044
is the position of the node particle at time t; c 1 An individual learning factor which is a node particle and has an acceleration constant; c 2 The social learning factor is a node particle, and the value of the social learning factor is an acceleration constant; ξ and η are random numbers in the range of 0 to 1; q is the relative proportion of the global social factor and the local social factor, 0<q<1；
Step 6: and (4) judging whether the maximum iteration number num is reached or the difference value between two continuous calculation results is smaller than a convergence threshold epsilon, finishing the iteration when any condition is met, otherwise, repeating the step 4 and the step 5, and obtaining the optimal solution after repeated iteration updating.
Preferably, the maximum iteration number num ranges from 240 to 260, and the convergence threshold epsilon ranges from 0.0003 to 0.001.
The specific embodiment is as follows:
referring to fig. 1, firstly, collecting node distribution positions of a Mesh network multi-gateway characteristic scene, processing to obtain a node distribution diagram, then establishing a calculation model of minimum hop count, namely an optimization problem of Mesh gateway deployment, converting the calculation model into an optimal solution problem, solving by adopting an improved hybrid particle swarm algorithm, and repeatedly iterating for multiple times to obtain an optimal deployment scheme of actual gateway nodes.
1. And establishing a geographical position distribution map of the routing nodes according to the Mesh network scene and the actual deployment position data of the sensor nodes, calculating connection parameters of the routing nodes, the gateway and the sensor according to the communication range of the routing nodes, further constructing a topological connection map of the routing nodes, and calculating to obtain the size S of the Mesh network scale.
2. Referring to FIG. 2, 50 node maps in the graph are initialized, each node having a particle coordinate X i ＝(x i1 ,x i2 ) Speed representationComprises the following steps: v i ＝(v i1 ,v i2 ) Meanwhile, the difference threshold of the iteration number of 240 times and the iteration result is set to 0.0005.
3. And taking the communication distance of each router as a radius, taking the candidate deployment position of the router as each central point, obtaining the wireless link connection parameters of the candidate deployment position, and combining the communication range of the router and the sensing node according to the candidate deployment position and the position of the sensing node. Kth gateway w of the whole network k Coordinate w of k ＝(a k ,b k ) And a gateway w k The set of nodes whose distance is less than the communication radius is called gateway adjacency set GAS k (Gateway adjacency set), then the hop count size from any node in the network to the Gateway is written as:
Figure BDA0003246771610000051
calculating to obtain a fitness function:
Figure BDA0003246771610000052
4. after the fitness function is calculated, the optimal solution of the node is updated according to the result of the fitness function f (X), namely the historical optimal position P of the node in the deployment process i ＝(p i1 ,p i2 ) Then, the global optimal solution, namely the historical optimal position P of the whole gateway node in the flight process is updated g ＝(p g1 ,p g2 )。
5. Updating iteration times, and calculating the inertia weight of the iteration formula by adopting an improved sigmoid function:
Figure BDA0003246771610000053
6. and substituting the inertia weight omega into an iterative formula, wherein the velocity and position updating formulas of the ith node particle are respectively as follows:
Figure BDA0003246771610000054
Figure BDA0003246771610000055
in the formula:
ω is an inertia factor, whose value is non-negative. When omega is larger, the global searching capability is strong, and the local searching capability is weak, and when omega is smaller, the global searching capability is weak, and the local searching capability is strong.
C 1 Is an individual learning factor for the particle, whose value is an acceleration constant.
C 2 Is the social learning factor of the particle, and its value is also an acceleration constant.
Xi and eta are random numbers in the range of 0 to 1, so that premature convergence of particles can be avoided, and the wide-area searching capability of the particle swarm is increased.
And q is the relative proportion of the global social factor and the local social factor, wherein 0< q <1, when the q value is larger, the global social factor has larger influence and the searching speed is higher, and when the q value is smaller, the local social factor has larger influence and the searching speed is lower, so that premature convergence is avoided.
7. Judging whether the iteration times and the threshold value setting are met, if the global optimal solution is not reached, adding 1 to the iteration times, repeating the steps 5, 6 and 7, and obtaining the optimal deployment scheme by repeating iterative update calculation, as shown in fig. 3.

Claims (2)

1. A Mesh gateway deployment optimization method based on a self-adaptive hybrid particle swarm algorithm is characterized by comprising the following steps:
step 1: initializing information of node particles, deploying m gateway nodes, wherein each node particle has n dimensions, and the coordinate of the ith gateway node particle is expressed as: x i ＝(x i1 ,x i2 ,x i3 ,…x in ) The velocity of the ith gateway node particle is expressed as: v i ＝(v i1 ,v i2 ,v i3 ,…v in ) Setting a maximum iteration number num and a convergence threshold epsilon;
step 2: definition and gateway w k The set formed by the nodes with the distance less than the communication radius is a gateway adjacency set GAS k (ii) a Any node in the network to the gateway w k The hop count of (a) is expressed as:
Figure FDA0003246771600000011
wherein v is i 、v j Respectively representing the ith node and the jth node;
the fitness function f (x) is then expressed as:
Figure FDA0003246771600000012
wherein S represents the scale of the Mesh network;
and step 3: updating individual optimal solution, namely historical optimal position P of node particles in the deployment process by using fitness function f (X) i ＝(p i1 ,p i2 ,p i3 ,…p in ) Then, the global optimal solution, namely the historical optimal position P of the whole particle swarm in the flight process is updated g ＝(p g1 ,p g2 ,p g3 ,…p gn ) Then, the optimal value of the neighborhood of the particle is updated
Figure FDA0003246771600000013
Figure FDA0003246771600000014
And 4, step 4: updating iteration times N, and determining an inertia weight omega by adopting an improved sigmoid function, wherein the inertia weight omega is expressed as follows:
Figure FDA0003246771600000015
in the formula: e is a natural constant, K is the maximum value of the sigmoid curve, and K e The curvature of the sigmoid curve, namely the change rate of the curve;
and 5: iterative equations (4) and (5) are substituted with the inertial weight ω into the velocity and position updates for the ith node particle:
Figure FDA0003246771600000016
Figure FDA0003246771600000017
wherein, V i t+1 Velocity, V, of the node particle at time t +1 i t Is the velocity of the node particle at time t,
Figure FDA0003246771600000018
the position of the node particle at time t +1,
Figure FDA0003246771600000019
is the position of the node particle at time t; c 1 The individual learning factor is node particles, and the value of the individual learning factor is an acceleration constant; c 2 The social learning factor is a node particle, and the value of the social learning factor is an acceleration constant; ξ and η are random numbers in the range of 0 to 1; q is the relative proportion of the global social factor and the local social factor, 0<q<1；
And 6: and (4) judging whether the maximum iteration number num is reached or the difference value between two continuous calculation results is smaller than a convergence threshold epsilon, finishing the iteration when any condition is met, otherwise, repeating the step 4 and the step 5, and obtaining the optimal solution after repeated iteration updating.
2. The Mesh gateway deployment optimization method based on the adaptive hybrid particle swarm algorithm according to claim 1, wherein the maximum iteration number num ranges from 240 to 260, and the convergence threshold epsilon ranges from 0.0003 to 0.001.
CN202111034979.0A 2021-09-04 2021-09-04 Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm Active CN113905386B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111034979.0A CN113905386B (en) 2021-09-04 2021-09-04 Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111034979.0A CN113905386B (en) 2021-09-04 2021-09-04 Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm

Publications (2)

Publication Number Publication Date
CN113905386A CN113905386A (en) 2022-01-07
CN113905386B true CN113905386B (en) 2022-09-06

Family

ID=79188624

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111034979.0A Active CN113905386B (en) 2021-09-04 2021-09-04 Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm

Country Status (1)

Country Link
CN (1) CN113905386B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114528096A (en) * 2022-01-25 2022-05-24 河南大学 Self-adaptive gateway deployment method and system based on multi-objective optimization
CN114665971B (en) * 2022-03-21 2023-10-13 北京理工大学 Method for generating multi-mode superimposed beam for improving communication capacity

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104994515A (en) * 2015-05-26 2015-10-21 哈尔滨工业大学 Gateway deploying method in cyber physical system
CN107277830A (en) * 2017-08-03 2017-10-20 扬州大学 A kind of wireless sensor network node dispositions method based on particle group optimizing and mutation operator
CN108399451A (en) * 2018-02-05 2018-08-14 西北工业大学 A kind of Hybrid Particle Swarm Optimization of combination genetic algorithm

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103945395B (en) * 2014-02-27 2016-06-01 北京理工大学 The rapid Optimum dispositions method of a kind of wireless network sensor based on population
CN105357681B (en) * 2015-10-29 2018-09-07 哈尔滨工业大学 Things-internet gateway dispositions method based on multiple-objection optimization
CN109447359B (en) * 2018-11-06 2021-04-16 成都信息工程大学 Data acquisition point deployment method and system
CN110610245A (en) * 2019-07-31 2019-12-24 东北石油大学 AFPSO-K-means-based long oil pipeline leakage detection method and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104994515A (en) * 2015-05-26 2015-10-21 哈尔滨工业大学 Gateway deploying method in cyber physical system
CN107277830A (en) * 2017-08-03 2017-10-20 扬州大学 A kind of wireless sensor network node dispositions method based on particle group optimizing and mutation operator
CN108399451A (en) * 2018-02-05 2018-08-14 西北工业大学 A kind of Hybrid Particle Swarm Optimization of combination genetic algorithm

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"加速度粒子群算法在多旅行商问题中的应用";强宁;《陕西师范大学学报(自然科学版)》;20151110;全文 *
"基于最佳粒子共享的并行粒子群优化算法及其在分类中的应用";刘剑波等;《机械》;20090215;第36卷(第02期);摘要，引言、第1节、第2节 *

Also Published As

Publication number Publication date
CN113905386A (en) 2022-01-07

Similar Documents

Publication Publication Date Title
CN113905386B (en) Mesh gateway deployment optimization method based on self-adaptive hybrid particle swarm algorithm
CN109063938B (en) Air quality prediction method based on PSODE-BP neural network
CN107396374B (en) Covering method based on virtual force and Thiessen polygon
CN112902969B (en) Path planning method of unmanned aerial vehicle in data collection process
CN112462803B (en) Unmanned aerial vehicle path planning method based on improved NSGA-II
CN110807230B (en) Method for autonomously learning and optimizing topological structure robustness of Internet of things
CN107277889A (en) A kind of network clustering method of wireless sensor based on k means
CN108320293A (en) A kind of combination improves the quick point cloud boundary extractive technique of particle cluster algorithm
CN108416392A (en) Building clustering method based on SOM neural networks
CN113573333B (en) Particle swarm heterogeneous WSNs coverage optimization algorithm based on virtual force
CN109753680A (en) A kind of swarm of particles intelligent method based on chaos masking mechanism
CN114460941B (en) Robot path planning method and system based on improved sparrow search algorithm
CN112911705A (en) Bayesian iteration improved particle swarm optimization algorithm-based indoor positioning method
CN112770256B (en) Node track prediction method in unmanned aerial vehicle self-organizing network
CN115866621A (en) Wireless sensor network coverage method based on whale algorithm
CN117350175B (en) Artificial intelligent ecological factor air environment quality monitoring method and system
CN114995390A (en) Mobile robot path planning method based on dynamic adaptive parameter adjustment dayflies algorithm
CN107229998A (en) A kind of autonomous pathfinding strategy process of unmanned plane
CN105357681B (en) Things-internet gateway dispositions method based on multiple-objection optimization
CN112528556B (en) Micro-electro-mechanical system design optimization method based on integrated model assisted social learning particle swarm algorithm
CN112462613B (en) Bayesian probability-based reinforcement learning intelligent agent control optimization method
Shahbazi et al. Density-based clustering and performance enhancement of aeronautical ad hoc networks
CN117241215A (en) Wireless sensor network distributed node cooperative positioning method based on graph neural network
CN106950833B (en) Based on the attitude of satellite dynamic programming method for improving PIO algorithm
CN114442670A (en) Unmanned aerial vehicle cluster self-organizing flight method and system and unmanned aerial vehicle

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