CN117812614A - Multi-target dynamic optimization decision method of wireless sensor network - Google Patents
Multi-target dynamic optimization decision method of wireless sensor network Download PDFInfo
- Publication number
- CN117812614A CN117812614A CN202311868248.5A CN202311868248A CN117812614A CN 117812614 A CN117812614 A CN 117812614A CN 202311868248 A CN202311868248 A CN 202311868248A CN 117812614 A CN117812614 A CN 117812614A
- Authority
- CN
- China
- Prior art keywords
- cluster
- sensor network
- objective function
- nodes
- energy consumption
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000005457 optimization Methods 0.000 title claims abstract description 34
- 241000854291 Dianthus carthusianorum Species 0.000 claims abstract description 42
- 238000005265 energy consumption Methods 0.000 claims abstract description 38
- 239000002245 particle Substances 0.000 claims abstract description 36
- 230000005540 biological transmission Effects 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 33
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims description 2
- 238000007499 fusion processing Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
Classifications
-
- 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
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The invention discloses a multi-objective dynamic optimization decision method of a wireless sensor network. According to the method, aiming at a detection area with the radius L of N sensor nodes, the sensor is divided into K clusters, the sensor is divided into fixed nodes and movable nodes according to the distance between the sensor in the cluster and other cluster heads, the fixed nodes can be connected with only one cluster head in a sensing range, the movable nodes can be simultaneously connected with a plurality of cluster heads in the sensing range, and one cluster head can be flexibly selected for connection according to the data transmission requirement. Aiming at the cluster head selection problem of the movable node, a multi-objective function is established by considering the coverage rate target, the energy consumption target and the uniformity target of the wireless sensor network under the fixed node and the movable node, and the cluster head selection scheme of the movable node is output by solving by utilizing a particle swarm optimization algorithm. The overall energy consumption of the sensor network is optimized, the coverage rate and uniformity are guaranteed, and the service life and the overall performance of the sensor network are improved.
Description
Technical Field
The invention belongs to the field of wireless sensor networks, and particularly relates to a multi-objective dynamic optimization decision method of a wireless sensor network.
Background
The wireless sensor network has the characteristics of huge number of sensor nodes and severe application environment, and in order to realize long-time operation under the conditions of the coverage area of the wireless sensor network as large as possible and difficult energy supply, a plurality of key targets such as the data transmission energy consumption, the coverage area, the non-uniformity and the like of the wireless sensor network need to be considered in design. The existing sensor network dynamic optimization decision method is mainly focused on a single target of energy consumption balancing, comprehensive optimization of energy consumption, coverage rate and uniformity is not achieved, and in addition, the node and cluster heads are generally assumed to correspond one by one, and the energy consumption balancing is achieved by searching a communication support set of an energy consumption optimal solution in the redundant sensor nodes or dynamically transforming the optimal position of the node according to a certain optimization strategy. Although the energy consumption balance effect of the wireless sensor network is improved, the comprehensive optimization of multiple targets of the wireless sensor network is lacking; in addition, the method for arranging the redundant sensor nodes greatly increases the input cost of the sensor network, and the method for dynamically transforming the optimal positions of the nodes additionally increases the energy consumption.
Disclosure of Invention
Aiming at the defects of the existing method, the invention provides a multi-objective dynamic optimization decision method of a wireless sensor network. Sensor movable nodes capable of being connected with a plurality of cluster heads are introduced, a multi-objective collaborative optimization model of the sensor network for comprehensively transmitting energy consumption, coverage rate and uniformity is constructed, an optimization multi-objective function is established through a self-adaptive weighted sum method, an optimization decision solution is obtained through solving by adopting a heuristic learning algorithm, collaborative optimization of the transmission energy consumption, the coverage rate and the uniformity of the line sensor network is realized under the condition that redundant sensor nodes or node optimal positions are not additionally distributed and dynamically transformed, and the coverage rate and the uniformity of the sensor network are ensured while the transmission energy consumption is optimized.
For N distributed sensor nodes S= { S 1 ,S 2 ,...,S N The method comprises the steps of designing a multi-target dynamic optimization decision method of the wireless sensor network, wherein the multi-target dynamic optimization decision method comprises the following steps of:
step 1, a multi-objective optimization decision model of a wireless sensor network
The method comprises the steps of dividing N sensors in a detection area into K clusters, dividing the sensors into fixed nodes and movable nodes according to the distances between the sensors in the clusters and other cluster heads, wherein the fixed nodes can be connected with only one cluster head in a sensing range, and the movable nodes can be simultaneously connected with a plurality of cluster heads in the sensing range and are preferentially selected according to data transmission requirements. The following objective function is established:
(1) Coverage rate objective function of wireless sensor network
Uniformly taking M points in the circular detection area, wherein the network coverage rate objective function C is as follows:
wherein P (P j ) Is the point P in the region j Probability of being covered by the sensor:
p(S i ，P j ) Representing sensor S i Can perceive the point P j Probability of (2):
wherein R is S Is the perceived radius of the sensor, d (S i ，P j ) Representing a sensor node S i To point P j Is a euclidean distance of (2):
wherein, (x) i ，y i ) Is a sensor S i Plane coordinates of (a) j ，b j ) Is point P j Is a plane coordinate of (c).
(2) Wireless sensor network energy consumption objective function
Sensor S i Toward cluster head Z j Energy consumption E required for transmitting k-bit data Tx (k, d) is:
wherein d (S) i ，Z j ) Is a sensor S i And Z is j The euclidean distance between j=1,..k. E (E) elec The energy consumption required by the data transmission circuit for unit bit; epsilon fs And epsilon mp The energy consumption coefficient of the power amplifier; d, d c Threshold value representing transmission distance:
sensor S i The data is received without considering the distance, the required energy E Rx (k) The method comprises the following steps:
E Rx (k)＝kE elec (7)
defining a behavior Boolean variable alpha (i, j) of a selected cluster head to describe the selection of different cluster heads by an active node:
and limiting an active node to select only one from K cluster heads at the same time for data uploading:
the energy consumption required by the cluster head is as follows:
wherein E is DA Represents the energy consumption, d, required by the cluster head fusion processing of unit bit data toSink N is the distance between the cluster head and the management node Rx 、N DA The number of source nodes for receiving data and the number of data groups to be processed are respectively:
N DA ＝N Rx +1 (12)
wherein μ is the number of fixed nodes in the cluster, and γ is the number of active nodes in the cluster.
Energy consumption E required by fixed nodes in a cluster Member (k) The method comprises the following steps:
energy consumption E of all nodes in the cluster Cluster (k) The method comprises the following steps:
E Cluster (k)＝E Head (k)+N Rx E Member (k) (14)
therefore, the energy consumption sum objective function E of the sensor network is as follows:
(3) Uniformity objective function of wireless sensor network
The uniformity of the sensor is defined as the mean value of the sum of standard deviations of all the distances between the sensors, and the uniformity objective function U is as follows:
wherein L is a sensor S i The number of adjacent sensors, d (S i ，S j ) Is a sensor S i 、S j Euclidean distance between M i Is a sensor S i The mean value of euclidean distance between all adjacent sensors.
(4) Wireless sensor network configuration multi-objective function
The adaptive weighted sum algorithm is adopted to construct a multi-objective function of the wireless sensor as follows:
wherein C is max 、E max U and U max The theoretical maximum value of the coverage rate, the energy consumption and the node uniformity of the wireless sensor network are respectively obtained. Lambda (lambda) C 、λ E 、λ u For the corresponding weight, satisfy lambda C 、λ E 、λ u > 0. In the constraint condition, mu is less than or equal to N Rx The number of nodes for transmitting information to the cluster head is limited to be larger than the number of fixed nodes and not to exceed the total number of the fixed nodes and the movable nodes,limiting the relation between the number of fixed nodes and movable nodes in the cluster and the total number of nodes, d c ≤R S Limiting the threshold value of the transmission distance between the sensor and the cluster head not to exceedThe perceived radius of the sensor is exceeded.
Step 2, designing an optimal solver based on particle swarm optimization algorithm
The particle swarm algorithm is optimized by simulating the foraging behavior of birds, and the mathematical model is expressed as follows: in an N-dimensional target space, there is a particle number N P Each particle corresponds to an n-dimensional vector, wherein the position of the χ -th particle isThe flying speed is v χ ，χ＝1，2，...，N P . f (χ) is an objective function to be optimized, P bestχ Is the best position of the χ particle obtained during the search process, G best And (3) updating the position, the speed and the maximum fitness value of the particle according to the following formula after each iteration for the global optimal position obtained by information sharing and comprehensive comparison of the whole population:
wherein q represents the number of iterations; omega is the inertial weight; c 1 Is a self-learning factor, c 2 Is a group learning factor; r is (r) 1 、r 2 Is subject to [0,1 ]]A uniform random number on the same. After a plurality of iterations, N P The particles will converge to the same position, i.e. the position of the optimal solution, where the fitness value corresponding to this position is the optimal fitness.
Adopting a particle swarm algorithm to obtain an optimal solution of the wireless sensor network configuration multi-objective function in the step 1, and realizing the selection of the cluster head by the active node, wherein the specific method comprises the following steps:
s2.1 initializing particle swarm
Initializing all particles, assigning particle positions and particle speeds by using Latin hypercube sampling method, and limiting maximum particle speed to be 10% O.ltoreq.v max ≤20％O。
s2.2, parameter adjustment
Selecting particle swarm size N P ∈[20，1000]The smaller particle swarm size is easy to fall into local optimum, the larger particle swarm size can improve convergence, and the global optimum solution can be found out more quickly, but the calculated amount can be increased; when the particle swarm size is increased to a certain level, the further increase will no longer have a significant effect.
Setting iteration times q E [50, 100 ]]When the iteration times are too small, the solution is unstable, and when the iteration times are too large, the solution is very time-consuming; setting learning factor c 1 ，c 2 ∈[0，4]Too low a value may cause the particles to wander outside the target area, while too high a value may cause the particles to cross the target area, both values being adjusted, typically by trial and error over an interval.
The selection of the inertia weight omega has great influence on the calculation process, and in the initial stage, the large inertia weight can lead the algorithm not to be easy to fall into local optimum, and in the later stage of the algorithm, the small inertia factor can lead the convergence speed to be accelerated and lead the convergence to be more stable. The following adaptive adjustment strategy is thus set for the inertia weight ω:
wherein omega max Is the maximum inertial weight; omega min Is the minimum inertial weight; the item is the current iteration number; ter (iter) max Is the maximum number of iterations. As the iteration number increases, the value of the inertia weight omega is linearly reduced, so that the particle swarm algorithm has stronger global convergence capacity in the initial stageHas stronger local convergence capacity in the later stage.
s2.3 termination policy
In the multi-objective dynamic optimization of the wireless sensor network, the energy and calculation power loss is brought by repeated iteration for a plurality of times, and in order to enable the multi-objective function value O to be stabilized to the maximum value as soon as possible, the cooperative optimization of the transmission energy consumption, coverage rate and uniformity of the wireless sensor network is realized, and the termination strategy is set as follows: and stopping optimizing when the absolute value of the difference between the value of the optimized objective function after the last iteration and the value of the objective function after the current iteration is smaller than 0.05.
The invention has the following beneficial effects:
in order to solve the problems of uneven cluster head energy consumption and easy consumption of node energy, active nodes are introduced, a sensor network optimization decision model is built by integrating the number, the positions and the energy consumption of the sensor network nodes, and a multi-objective function of the coverage rate, the energy consumption and the uniformity of the sensor network is integrated, an optimal solution is obtained by utilizing a particle swarm optimization algorithm to obtain an optimal cluster head selection strategy of the active nodes, the utilization rate of balanced nodes can be better realized through flexible node deployment, the multi-objective optimization decision capability of the wireless sensor network is improved, the coverage rate and the uniformity are ensured while the whole energy of the sensor network is optimized, and the service life and the whole performance of the sensor network are improved.
Drawings
FIG. 1 is a schematic diagram of a wireless sensor network in an embodiment;
fig. 2 is a flow chart of a multi-objective dynamic optimization decision method of a wireless sensor network.
Detailed Description
As shown in fig. 1, for N distributed sensor nodes s= { S 1 ，S 2 ，...，S N The method comprises the steps of dividing N sensors into K clusters in a circular detection area with the radius of L and the area of V, dividing the sensors into fixed nodes and movable nodes according to the distance between the sensors in the clusters and other cluster heads, wherein the fixed nodes can only be connected with one cluster head in a sensing range, and the movable nodes can be simultaneously connected with a plurality of cluster heads in the sensing range, so that the data transmission requirement can be met according toAnd flexibly selecting one cluster head for connection.
Aiming at the cluster head selection problem of the movable node, a multi-target dynamic optimization decision method is provided, as shown in fig. 2, a multi-target optimization decision model of the wireless sensor network is firstly established, meanwhile, the coverage rate target, the energy consumption target and the uniformity target of the wireless sensor network under the fixed node and the movable node are considered to be combined into a multi-target function, and the multi-target function is solved by utilizing a particle swarm optimization algorithm, so that a cluster head selection scheme of the movable node is output.
Claims (5)
1. A multi-target dynamic optimization decision method of a wireless sensor network is characterized in that: for N distributed sensor nodes S= { S 1 ，S 2 ，...，S N A circular detection region with radius L and area V, outputting a decision by:
step 1, dividing N sensors in a detection area into K clusters, dividing the sensors into fixed nodes and movable nodes according to the distance between the sensors in the clusters and other cluster heads, wherein the fixed nodes can only be connected with one cluster head in a sensing range, and the movable nodes can select one from a plurality of cluster heads to be connected according to data transmission requirements in the sensing range;
step 2, establishing a multi-objective function integrating network coverage rate, energy consumption and uniformity aiming at the sensor network;
and step 3, solving the maximum value of the multi-objective function by using a particle swarm optimization algorithm, and outputting a cluster head selection scheme of the movable node.
2. The multi-objective dynamic optimization decision-making method of a wireless sensor network according to claim 1, wherein: the following objective function is established for the wireless sensor network:
(1) Coverage rate objective function of wireless sensor network
Uniformly taking M points in the circular detection area, wherein the network coverage rate objective function C is as follows:
wherein P (P j ) Is the point P in the region j Probability of being covered by the sensor:
p(S i ，P j ) Representing sensor S i Can perceive the point P j Probability of (2):
wherein R is S Is the perceived radius of the sensor, d (S i ，P j ) Representing a sensor node S i To point P j Is a euclidean distance of (2):
wherein, (x) i ，y i ) Is a sensor S i Plane coordinates of (a) j ，b j ) Is point P j Is a plane coordinate of (2);
(2) Wireless sensor network energy consumption objective function
Sensor S i Toward cluster head Z j Energy consumption E required for transmitting k-bit data Tx (k, d) is:
wherein d (S) i ，Z j ) Is a sensor S i And Z is j The euclidean distance between j=1,., K; e (E) elec The energy consumption required by the data transmission circuit for unit bit; epsilon fs And epsilon mp The energy consumption coefficient of the power amplifier; d, d c Threshold value representing transmission distance:
sensor S i The data is received without considering the distance, the required energy E Rx (k) The method comprises the following steps:
E Rx (k)＝kE elec (7)
defining a behavior Boolean variable alpha (i, j) of a selected cluster head to describe the selection of different cluster heads by an active node:
and limiting an active node to select only one from K cluster heads at the same time for data uploading:
the energy consumption required by the cluster head is as follows:
wherein E is DA Represents the energy consumption, d, required by the cluster head fusion processing of unit bit data toSink N is the distance between the cluster head and the management node Rx 、N DA The number of source nodes for receiving data and the number of data groups to be processed are respectively:
N DA ＝N Rx +1 (12)
wherein mu is the number of fixed nodes in the cluster, and gamma is the number of movable nodes in the cluster;
energy consumption E required by fixed nodes in a cluster Member (k) The method comprises the following steps:
energy consumption E of all nodes in the cluster Cluster (k) The method comprises the following steps:
E cluster (k)＝E Head (k)+N Rx E Member (k) (14)
therefore, the energy consumption sum objective function E of the sensor network is as follows:
(3) Uniformity objective function of wireless sensor network
The uniformity of the sensor is defined as the mean value of the sum of standard deviations of all the distances between the sensors, and the uniformity objective function U is as follows:
wherein L is a sensor S i The number of adjacent sensors, d (S i ，S j ) Is a sensor S i 、S j Euclidean distance between M i Is a sensor S i The mean value of euclidean distance between all adjacent sensors.
3. The multi-objective dynamic optimization decision-making method of a wireless sensor network according to claim 2, wherein: the established multi-objective function is:
wherein C is max 、E max U and U max The theoretical maximum values of the coverage rate, the energy consumption and the node uniformity of the wireless sensor network are respectively; lambda (lambda) C 、λ E 、λ U For the corresponding weight, satisfy lambda C 、λ E 、λ U ＞0。
4. A multi-objective dynamic optimization decision-making method of a wireless sensor network as claimed in claim 1 or 3, characterized in that: the particle swarm optimization algorithm is used for solving the maximum value of the multi-objective function, so that the cluster head is selected by the movable node, and the method comprises the following steps of:
s3.1 number of build particles N P Each particle corresponds to an n-dimensional vector, wherein the position of the χ -th particle isThe flying speed is v χ χ = 1,2,..np; f (χ) is an objective function to be optimized, namely a multi-objective function O of the constructed wireless sensor network; p (P) bestχ Is the best position of the χ particle obtained during the search process, G best And (3) updating the position, the speed and the maximum fitness value of the particle after each iteration for the global optimal position obtained by the information sharing and comprehensive comparison of the whole population:
wherein q represents the number of iterations; omega is the inertial weight; c 1 Is a self-learning factor, c 2 Is a group learning factor; r is (r) 1 、r 2 Is subject to [0,1 ]]A uniform random number thereon;
s3.2, assigning values to particle positions and particle speeds by using Latin hypercube sampling method, and limiting the maximum particle speed to be 10% O.ltoreq.v max Initializing particle swarm size N with less than or equal to 20% O P Number of iterations q and learning factor c 1 、c 2 ；
s3.2, setting the following adaptive adjustment strategy for the inertia weight omega:
wherein omega max Is the maximum inertial weight; omega min Is the minimum inertial weight; the item is the current iteration number; ter (iter) max The maximum iteration number;
and s3.4, stopping iteration after the absolute value of the difference between the value of the optimized objective function after the last iteration and the value of the objective function after the current iteration is smaller than 0.05, and outputting a cluster head connection decision of the movable node.
5. The multi-objective dynamic optimization decision-making method of wireless sensor network as claimed in claim 4, wherein: setting particle swarm size N p ∈[20，1000]StackingGeneration number q epsilon [50, 100 ]]Learning factor c 1 ，c 2 ∈[0，4]。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311868248.5A CN117812614A (en) | 2023-12-29 | 2023-12-29 | Multi-target dynamic optimization decision method of wireless sensor network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311868248.5A CN117812614A (en) | 2023-12-29 | 2023-12-29 | Multi-target dynamic optimization decision method of wireless sensor network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117812614A true CN117812614A (en) | 2024-04-02 |
Family
ID=90423289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311868248.5A Pending CN117812614A (en) | 2023-12-29 | 2023-12-29 | Multi-target dynamic optimization decision method of wireless sensor network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117812614A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102438298A (en) * | 2011-11-09 | 2012-05-02 | 无锡南理工科技发展有限公司 | Trusted energy-saving data convergence method for wireless sensor network |
| CN102711180A (en) * | 2012-05-25 | 2012-10-03 | 杭州电子科技大学 | Cluster head multiple selection energy balance routing method |
| CN110072265A (en) * | 2019-03-25 | 2019-07-30 | 湖州师范学院 | A kind of implementation method of energy heterogeneous wireless sensor network Clustering protocol |
| CN111065103A (en) * | 2019-12-11 | 2020-04-24 | 哈尔滨工程大学 | Multi-objective optimization wireless sensor network node deployment method |
| CN111988786A (en) * | 2020-06-08 | 2020-11-24 | 长江大学 | Sensor network covering method and system based on high-dimensional multi-target decomposition algorithm |
| CN115243273A (en) * | 2022-09-23 | 2022-10-25 | 昆明理工大学 | Wireless sensor network coverage optimization method, device, equipment and medium |
| CN115567889A (en) * | 2022-09-23 | 2023-01-03 | 柳州职业技术学院 | Method for selecting static anchor node position of sensor network based on butterfly optimization algorithm |
-
2023
- 2023-12-29 CN CN202311868248.5A patent/CN117812614A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102438298A (en) * | 2011-11-09 | 2012-05-02 | 无锡南理工科技发展有限公司 | Trusted energy-saving data convergence method for wireless sensor network |
| CN102711180A (en) * | 2012-05-25 | 2012-10-03 | 杭州电子科技大学 | Cluster head multiple selection energy balance routing method |
| CN110072265A (en) * | 2019-03-25 | 2019-07-30 | 湖州师范学院 | A kind of implementation method of energy heterogeneous wireless sensor network Clustering protocol |
| CN111065103A (en) * | 2019-12-11 | 2020-04-24 | 哈尔滨工程大学 | Multi-objective optimization wireless sensor network node deployment method |
| CN111988786A (en) * | 2020-06-08 | 2020-11-24 | 长江大学 | Sensor network covering method and system based on high-dimensional multi-target decomposition algorithm |
| CN115243273A (en) * | 2022-09-23 | 2022-10-25 | 昆明理工大学 | Wireless sensor network coverage optimization method, device, equipment and medium |
| CN115567889A (en) * | 2022-09-23 | 2023-01-03 | 柳州职业技术学院 | Method for selecting static anchor node position of sensor network based on butterfly optimization algorithm |
Non-Patent Citations (3)
| Title |
|---|
| 刁鹏飞等: "基于节点休眠的水下无线传感器网络覆盖保持分簇算法", 电子与信息学报, 31 May 2018 (2018-05-31) * |
| 孙环: "无线传感器网络中数据采集的节点重部署算法研究", 中国优秀硕士学位论文全文数据库信息科技辑, 15 February 2022 (2022-02-15) * |
| 李洪兵等: "基于改进粒子群聚类的无线传感器网络能量均衡分簇策略", 计算机应用研究, 15 February 2011 (2011-02-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wen et al. | Federated dropout—a simple approach for enabling federated learning on resource constrained devices | |
| CN112118287B (en) | Network resource optimization scheduling decision method based on alternative direction multiplier algorithm and mobile edge calculation | |
| Gamal et al. | Enhancing the lifetime of wireless sensor networks using fuzzy logic LEACH technique-based particle swarm optimization | |
| CN105429185B (en) | A kind of economic load dispatching method with the harmonious property of robust | |
| CN108075975B (en) | Method and system for determining route transmission path in Internet of things environment | |
| CN108416421B (en) | Dynamic fire power distribution method based on DDE improved bat algorithm | |
| CN110225569B (en) | WSNs clustering multi-hop routing protocol method based on improved particle swarm optimization | |
| Ma et al. | An improved dynamic self-adaption cuckoo search algorithm based on collaboration between subpopulations | |
| CN110687926B (en) | Rapid formation method for unmanned aerial vehicle group | |
| CN110120892B (en) | SDN multi-controller deployment method and system based on improved firefly algorithm | |
| Hwang et al. | Deep reinforcement learning approach for uav-assisted mobile edge computing networks | |
| KR101565694B1 (en) | Artificial bee colony clustering design method and system in wireless sensor network | |
| CN111488208B (en) | Bian Yun collaborative computing node scheduling optimization method based on variable-step-size bat algorithm | |
| CN117812614A (en) | Multi-target dynamic optimization decision method of wireless sensor network | |
| CN116560828A (en) | Task processing method, device, computer equipment, storage medium and program product | |
| CN113011097B (en) | Multi-group self-adaptive collaborative optimization method | |
| Xu et al. | Cognitive radio decision engine using hybrid binary particle swarm optimization | |
| CN115438722A (en) | Big data product index clustering method based on distributed clustering | |
| CN111160513B (en) | Energy optimization method for electric power distribution network | |
| Feng et al. | Spectrum Allocation for Cognitive Radio Networks Using the Fireworks Algorithm. | |
| Liu | Optimization analysis of WSN location process based on hybrid PSO algorithm | |
| Kou et al. | Intelligent selection: A neural network-based mac protocol-selection mechanism for wireless ad hoc networks | |
| Wang et al. | Resource allocation algorithm for MEC based on Deep Reinforcement Learning | |
| Tseng et al. | Coverage hole repairment for mobile wireless sensor networks with simultaneous multiple node deaths | |
| Jeong et al. | Optimal Partitioning of Distributed Neural Networks for Various Communication Environments |
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 |