CN107734637A - A kind of method for three-dimensionally positioning network node of wireless sensor based on SCE PSO algorithms - Google Patents
A kind of method for three-dimensionally positioning network node of wireless sensor based on SCE PSO algorithms Download PDFInfo
- Publication number
- CN107734637A CN107734637A CN201710989499.7A CN201710989499A CN107734637A CN 107734637 A CN107734637 A CN 107734637A CN 201710989499 A CN201710989499 A CN 201710989499A CN 107734637 A CN107734637 A CN 107734637A
- Authority
- CN
- China
- Prior art keywords
- sce
- algorithm
- particle
- pso
- wireless sensor
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The present invention devises a kind of method for three-dimensionally positioning network node of wireless sensor based on SCE PSO algorithms.The advantages of by comprehensive SCE two kinds of optimized algorithms of UA and PSO, replace simplex algorithm to remove each complex of evolving using PSO algorithms in SCE UA algorithms, so as to propose a kind of new algorithm SCE PSO algorithms.By introducing the faster PSO algorithms of convergence rate, the shortcomings that SCE PSO algorithms improve SCE UA algorithms and had a great influence by problem dimension, and convergence rate is slower, it is suitable for wireless sensor network node three-dimensional localization.Simultaneously using the strategy of shuffling in SCE UA algorithms, the diversity of particle is added, improves the shortcomings that PSO algorithms mid-early maturity is restrained.The present invention carries out the positioning of wireless sensor network three-dimensional nodes using SCE PSO algorithms, improves node locating precision.
Description
Technical Field
The invention belongs to the field of node positioning in a wireless sensor network.
Background
Three-dimensional positioning of Wireless Sensor Network (WSN) nodes is one of the current research hotspots. The node positioning method of the wireless sensor network can be divided into two methods based on ranging and non-ranging according to whether the distance between the nodes needs to be measured. The method based on the distance measurement is widely adopted in the positioning of the wireless sensor network node due to high positioning precision. The positioning method based on ranging measures the distance or Angle between nodes first, and commonly used measuring methods include Received Signal Strength Indicator (RSSI), time of Arrival (TOA), time Difference of Arrival (TDOA), and Angle of Arrival (AOA).
After the distance or angle information between the nodes is obtained, some positioning methods can be adopted to position the unknown nodes by a distance measurement-based method, wherein in one method, the obtained distance or angle information is taken as a constraint condition and is converted into an objective function, and then the minimum value of the objective function is searched by various optimization algorithms, so that the unknown nodes are positioned. The optimization method can be divided into a traditional optimization method and a biological heuristic optimization method.
The traditional optimization method is based on a determined search strategy, and under the condition of meeting certain limiting conditions, mathematical properties such as derivatives and gradients of an optimization problem are utilized to carry out solving. The method has the disadvantages that the operation complexity is higher, the complexity is multiplied exponentially along with the increase of the dimension of the problem, the biological heuristic optimization method can effectively avoid the problem, the calculation is more effective, no assumption is made on the function form corresponding to the optimization problem, the continuity or the instructive assumption of the target function is not required, the algorithm is simple, and the realization is easy.
Common bio-heuristic optimization algorithms include: simulated Annealing (SA), ant Colony Optimization (ACO), genetic Optimization (GA), artificial Bee Colony Optimization (ABC), bacterial Foraging (BFA), particle Swarm Optimization (PSO). Compared with other biological heuristic optimization algorithms, the particle swarm optimization algorithm has the advantages of easy execution and high convergence speed. Especially, the more the number of dimensions of the problem to be solved, the more obvious the advantages are. Therefore, the particle swarm algorithm is very suitable for three-dimensional positioning of the wireless sensor network nodes. However, during the operation process, the particle swarm optimization may fall into local optimization, and premature convergence occurs.
Disclosure of Invention
Aiming at the problem that when the particle swarm algorithm is adopted for three-dimensional positioning of a wireless sensor network node, particles can be trapped into local optimization in the searching process, premature convergence occurs, and therefore the node positioning accuracy is low, the invention provides an improved particle swarm algorithm SCE-PSO, and the algorithm is combined with an SCE-UA (robust computing-University of Arizona) algorithm, so that the diversity of the particles in the searching process is increased, the probability that the particles are trapped into the local optimization is reduced, and the understanding quality is improved. Therefore, compared with the original particle swarm method, the method can improve the positioning accuracy and is more suitable for three-dimensional positioning of the wireless sensor network nodes.
The specific implementation process is as follows:
1. particle swarm algorithm
The basic idea of the particle swarm optimization algorithm is as follows: each solution of the optimization problem is regarded as a particle, each particle flies at a certain speed in a multidimensional search space, the advantages and disadvantages of the particles are measured through the fitness value of an objective function, and each particle can dynamically adjust the flying speed through the flying experience of the particle and the flying experience of other particles, so that the particle flies to the best particle position in a group, and the optimal solution of the optimization problem is finally searched. Assuming that the solved problem is n-dimensional, the solving steps of the particle swarm algorithm are as follows:
(1) Initializing parameters, including acceleration constant c 1 And c 2 Maximum number of iterations T max Velocity range of particles [ v ] min ,v max ]Number of particles s and range of inertial weights [ omega ] min ,ω max ]。
(2) Setting the number of iterations to t =1, randomly generating the position of the initial particleAnd initial velocity of the particlesi =1,2, \ 8230;, s. Wherein the content of the first and second substances, d＝1,2,…,n。
(3) Will be provided withAs the optimum position p for each particle id And calculating the best fitness value h of each particle i H is to be i Is used as a global optimum fitness value g, and the position g of the particle with g is recorded d 。
(4) Evaluating each particle, and calculating fitness value of each particleTo pairParticles of (2) to And will haveThe position of the particle of (a) is taken as p id The position of (a). Then find outMinimum value g of t If g is t &let g = g t And will have g t The position of the particle of (a) is taken as g d The position of (a).
(5) The inertial weight, the velocity of the particle and the position of the particle are updated according to formula (1), formula (2) and formula (3), respectively.
In the formula (2), r 1 And r 2 Is uniformly distributed in [0,1 ]]Random number of intervals. In the updating process, ifSet it as v min If, ifSet it as v max 。
(6) Let the number of iterations T = T +1, and then check if T is less than T max If the condition is satisfied, the step (4) is carried out, otherwise, the algorithm is stopped, and g is carried out at the moment d Is the solution to the problem.
SCE-UA Algorithm
The SCE-UA algorithm basic idea is to combine a deterministic complex shape search technology with a natural biological competition evolution principle to solve a minimization problem, and to integrate the deterministic method, the stochastic method, the competitive evolution, the complex shape mixing and other concepts, thereby ensuring the flexibility, the global property, the consistency, the effectiveness and the like of the SCE-UA algorithm search. Assuming that the solved problem is n-dimensional, the main steps of the SCE-UA algorithm are as follows:
(1) And (6) initializing. Selecting the number p (p is more than or equal to 1) of the complex shapes participating in the evolution and the number m (m is more than or equal to n + 1) of the vertexes contained in each complex shape, and calculating the number s = p × m of the sample points.
(2) Sample points are generated. Randomly generating s sample points x in the feasible region 1 ，x 2 ，…，x s Calculating each point x separately i Function value f of i ＝f(x i )，i＝1，2，…，s。
(3) And (4) sorting sample points. The s sample points (x) i ，f i ) Arranged according to ascending order of function values, and still marked as (x) after being sorted i ，f i ) I =1,2, \ 8230;, s, i.e. f 1 ≤f 2 ≤…≤f s Let D = { (x) i ，f i )，i＝1，2，…， s}。
(4) And (5) dividing the compound population. Divide D into p complexes A 1 ，A 2 ，…，A p Each complex shape having m points, whereinj＝1， 2，…，m}，k＝1，2，…，p。
(5) And (5) complex evolution. And respectively evolving each complex shape according to a downhill simplex shape algorithm.
(6) And (4) compounding and mixing. All the vertexes of each compound form after evolution are combined into a new point set, and the function value f is carried out again i The D is arranged according to the ascending order of the target function, and the D is marked as D after the sorting.
(7) And (5) judging the convergence. And (5) stopping iteration if a convergence condition is met, wherein the position of the particle with the minimum function value is the solution of the problem, and returning to the step (4) if not.
3. Improved particle swarm algorithm SCE-PSO
According to the speed updating formula (2) in the particle swarm optimization algorithm, in the running process, if a certain particle finds a current optimal position, other particles approach the current optimal position quickly, if the optimal position is only a local optimal point, the particle swarm may not jump out of the local optimal point in the searching process, so that the particle swarm falls into local optimization, and the premature convergence phenomenon occurs. One of the measures for avoiding the premature convergence phenomenon of the particle swarm optimization is to increase the diversity of particles. By taking the reference of the SCE-UA algorithm, an improved particle swarm algorithm SCE-PSO is provided.
In the traditional SCE-UA algorithm, the downhill simplex algorithm is used to evolve each complex. But the downhill simplex algorithm is a method that uses polyhedrons to approximate the optimal value of the problem step by step. If the dimension of the problem to be optimized is large, the evolution process is complex, the quality of the solution is not high, and the convergence speed is slow. Due to the fact that the three-dimensional positioning dimension of the wireless sensor network node is large, the wireless sensor network node cannot be positioned by the method. The particle swarm algorithm has no operations such as selection, intersection, variation and the like, has high convergence rate, and has small influence of the dimension of the optimization problem on the convergence rate, so that the particle swarm algorithm is more suitable for three-dimensional positioning of the wireless sensor network node.
In view of the above thought, in our proposed improved algorithm, a particle swarm algorithm is used to replace the downhill simplex algorithm to evolve each complex shape in the SCE-UA algorithm. Therefore, the defects of the traditional SCE-UA algorithm can be overcome, the convergence rate is improved, and the quality of the solution for solving the high-dimensional problem is improved; meanwhile, the shuffling strategy (after composite mixing and re-dividing) in the SCE-UA algorithm can be utilized to keep the diversity of the particles, so that the defects of the particle swarm algorithm are overcome, and the probability of premature convergence is reduced.
4. Objective function
Solving the problem using a bio-heuristic optimization algorithm requires an objective function to evaluate the quality of each candidate solution. For three-dimensional positioning of nodes of the wireless sensor network, coordinates of unknown nodes in the wireless sensor network are (x, y, z) and coordinates of anchor nodes are (x, y, z) respectively in a three-dimensional space 1 ，y 1 ，z 1 )，(x 2 ， y 2 ，z 2 )，…，(x n ，y n ，z n ) The distances from the unknown node to the anchor node are respectively d 1 ，d 2 ，…，d n . From this, we can derive the following formula (4).
Therefore, the objective function of three-dimensional positioning of the wireless sensor network node can be defined as:
5. implementation steps of wireless sensor network node three-dimensional positioning method based on SCE-PSO algorithm
(1) Finding locatable unknown nodes
In the initial stage of the network, an ID number is distributed to each sensor node, an anchor node and an unknown node are marked, then the anchor node sends a message to the unknown node within one-hop range of the anchor node, and the content of the message comprises the ID number and three-dimensional coordinate values of the anchor node and the unknown node. And the unknown node records the received message information, judges the number of the neighbor anchor nodes per se, and performs positioning estimation if the number of the anchor nodes is not less than 4.
(2) And estimating the distance between the unknown node and the anchor node through a wireless channel model.
(3) And converting the node positioning estimation problem into an unconstrained optimization problem.
(4) And solving the minimum value of the objective function through the proposed SCE-PSO algorithm to obtain the estimated value of the unknown node coordinate.
The invention has the beneficial effects that:
1. positioning accuracy
The positioning accuracy is the most important performance evaluation parameter of the positioning algorithm, and the node average positioning error is generally expressed by the following formula
In the formula (6), e represents the average positioning error, N represents the number of simulated networks, and (x) i ,y i ,z i ) Andrespectively representing the true and estimated coordinates, V, of node i n Represents a set of nodes that can be located in the nth network, | V n I represents the set V n The number of middle nodes, R represents generalThe radius is believed.
Fig. 1, fig. 2, and fig. 3 are curves of positioning accuracy of three different positioning methods, namely SCE-PSO, SCE-UA, and PSO, varying with the number of anchor nodes, the communication radius of the nodes, and the standard deviation of ranging noise, respectively. As can be seen from the figure, the positioning accuracy of the SCE-PSO algorithm is better than that of the SCE-UA algorithm and the PSO algorithm no matter the number of anchor nodes is different, the communication radius of the nodes is different or the standard deviation of the ranging noise is different.
In summary, the invention provides a three-dimensional positioning method for a wireless sensor network node based on an SCE-PSO algorithm. The method integrates the advantages of two optimization methods of PSO and SCE-UA, reduces the phenomenon of premature convergence of particles in the PSO method, and simultaneously improves the defect that the SCE method is greatly influenced by problem dimension. The method is more suitable for three-dimensional positioning of the wireless sensor network nodes.
Drawings
FIG. 1 is a comparison graph of positioning accuracy of SCE-PSO algorithm, SCE-UA algorithm and PSO algorithm under different anchor node numbers;
FIG. 2 is a comparison graph of the positioning accuracy of the SCE-PSO algorithm, the SCE-UA algorithm and the PSO algorithm under different node communication radiuses;
FIG. 3 is a comparison graph of the positioning accuracy of the SCE-PSO algorithm, the SCE-UA algorithm and the PSO algorithm under different standard deviations of the ranging noise;
Detailed Description
The invention is described in further detail below with reference to the figures and the examples.
The invention discloses a wireless sensor network node three-dimensional positioning method based on an SCE-PSO algorithm.
The three-dimensional positioner sequentially comprises the following steps:
step (1) searching for locatable unknown nodes
In the initial stage of the network, an ID number is distributed to each sensor node, an anchor node and an unknown node are marked, then the anchor node sends a message to the unknown node within one-hop range of the anchor node, and the content of the message comprises the ID number and three-dimensional coordinate values of the anchor node and the unknown node. And the unknown node records the received message information, judges the number of the neighbor anchor nodes per se, and performs positioning estimation if the number of the anchor nodes is not less than 4.
(2) And estimating the distance between the unknown node and the anchor node through a wireless channel model.
(3) And converting the node positioning estimation problem into an unconstrained optimization problem. I.e. minimum of the objective function equation (5).
(4) And (5) solving by using an SCE-PSO algorithm.
1) Selecting the number p (p is more than or equal to 1) of the complex shapes participating in the evolution and the number m (m is more than or equal to n + 1) of the vertexes contained in each complex shape, and calculating the number s = p × m of the sample points.
2) Sample points are generated. Randomly generating s sample points x in the feasible region 1 ，x 2 ，…，x s Calculating each point x separately i Function value f of i ＝f(x i )，i＝1，2，…，s。
3) And (4) sorting sample points. S sample points (x) i ，f i ) Arranging according to ascending order of function values, and marking as (x) after sequencing i ，f i ) I =1,2, \ 8230;, s, i.e. f 1 ≤f 2 ≤…≤f s Let D = { (x) i ，f i )，i＝1，2，…， s}。
4) And dividing the complex population. Divide D into p complexes A 1 ，A 2 ，…，A p Each complex shape having m points, whereinj＝1， 2，…，m}，k＝1，2，…，p。
5) And (5) complex evolution. And respectively evolving each complex shape by adopting a particle swarm algorithm.
6) And (4) mixing in a complex shape. All the vertexes of each compound form after evolution are combined into a new point set, and the function value f is carried out again i And D is arranged in an ascending order, the D is still marked as D after the sorting, and the D is arranged according to the ascending order of the objective function.
7) And (5) judging the convergence. Stopping the iteration if the convergence condition is satisfied, wherein the position of the particle with the minimum function value is the solution of the problem, and returning to the step 4) if the convergence condition is not satisfied.
Wherein, in the step 5), the step of the particle swarm algorithm to evolve the complex shape is as follows:
a) Considering each vertex of the complex as a particle, initializing parameters including an acceleration constant c 1 And c 2 Maximum number of iterations T max Velocity range of particles [ v ] min ,v max ]Range of inertial weight [ omega ] min ,ω max ]。
b) Setting the number of iterations to t =1, randomly generating an initial velocity of initial particlesi =1,2, \8230;, m. Wherein the content of the first and second substances,d＝1,2,3。
c) Will be provided withAs the optimum position p for each particle id Calculating the optimum fitness value h of each particle by using the formula (5) i H is to be i The minimum value of (a) is taken as the global optimum fitness value g, and the position g of the particle with g is recorded d 。
d) Evaluating each particle, and calculating the fitness value of each particle by formula (5)To pairParticles of (1), toAnd will haveThe position of the particle of (a) is taken as p id The position of (a). Then find outMinimum value g of t If g is t &let g = g t And will have g t The position of the particle of (a) is taken as g d The position of (a).
e) The inertial weight, the velocity of the particle, and the position of the particle are updated according to formula (1), formula (2), and formula (3), respectively.
f) Let the number of iterations T = T +1, then check if T is less than T max And c), if the condition is met, turning to the step d), otherwise, stopping the algorithm.
It should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, the scope of the present invention is not limited thereto, and any modifications or equivalent substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention disclosed herein are all included within the scope of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (1)
1. A wireless sensor network node three-dimensional positioning method based on SCE-PSO algorithm is characterized in that: a PSO algorithm is used for replacing a downhill simplex algorithm in the SCE-UA algorithm to evolve each complex shape, and a new algorithm SCE-PSO algorithm is provided; the algorithm integrates the advantages of two optimization algorithms of SCE-UA and PSO, and simultaneously improves the defects of the two algorithms; converting the three-dimensional positioning problem of the wireless sensor network node into an unconstrained optimization problem by defining an objective function of the three-dimensional positioning of the wireless sensor network node, and solving the unconstrained optimization problem by using the proposed SCE-PSO algorithm, wherein the solved solution is an estimated value of the three-dimensional coordinate of the wireless sensor network node;
the method comprises the following steps:
step 1: searching a locatable unknown node;
and 2, step: estimating the distance between the unknown node and the anchor node through a wireless channel model;
and step 3: writing a target function of three-dimensional positioning of the wireless sensor network node, and converting the node positioning estimation problem into an unconstrained optimization problem;
and 4, step 4: solving the unconstrained optimization problem by using an SCE-PSO algorithm, and solving an estimated value of a three-dimensional coordinate of a wireless sensor network node;
the specific solving steps of the SCE-PSO algorithm are as follows:
step 1, selecting the number p (p is more than or equal to 1) of complex shapes participating in evolution and the number m (m is more than or equal to n + 1) of vertexes contained in each complex shape, and calculating the number s = p × m of sample points;
step 2, randomly generating s sample points x in feasible region 1 ，x 2 ，…，x s Separately calculating each point x i Function value f of i ＝f(x i )，i＝1，2，…，s；
Step 3. The s sample points (x) i ，f i ) Arranged according to ascending order of function values, and still marked as (x) after being sorted i ，f i ) I =1,2, \8230;, s, i.e. f 1 ≤f 2 ≤…≤f s Let D = { (x) i ，f i )，i＝1，2，…，s}；
Step 4, dividing D into p composite shapes A 1 ，A 2 ，…，A p Each complex shape having m points, wherein
Step 5, respectively evolving each composite shape by adopting a particle swarm algorithm;
step 6, all the vertexes of each compound shape after the evolution are combined into a new point set, and the function value f is carried out again i The D is arranged according to the ascending order of the target function, the D is still marked as D after the sequencing;
step 7, judging whether a convergence condition is met, if so, stopping iteration, and if not, returning to the step 4, wherein the position of the particle with the minimum function value is the solution of the problem;
wherein, the step of the particle swarm algorithm in the step 5 for evolving the complex shape is as follows:
step 1, regarding each vertex of the complex shape as a particle, initializing parameters including an acceleration constant c 1 And c 2 Maximum number of iterations T max Velocity range of particles [ v ] min ,v max ]Range of inertial weight [ omega ] min ,ω max ]；
Step 2, setting the iteration times as t =1, and randomly generating the initial speed of the initial particlesWherein, the first and the second end of the pipe are connected with each other,
step 3 willAs the optimum position p for each particle id Calculating an optimum fitness value h for each particle using the objective function i H is to be i Is used as a global optimum fitness value g, and the position g of the particle with g is recorded d ；
Step 4, evaluating each particle, and calculating the fitness value of each particle by using the objective functionTo pairParticles of (1), toAnd will haveThe position of the particle of (a) is taken as p id The position of (a); then find outMinimum value g of t If g is t &let g = g t And will have g t The position of the particle of (a) is taken as g d The position of (a);
step 5, updating the inertia weight, the speed of the particles and the positions of the particles according to the formula (1), the formula (2) and the formula (3) respectively;
step 6 let the iteration number T = T +1, then check if T is less than T max And if the condition is met, turning to the step 4, otherwise, stopping the algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710989499.7A CN107734637A (en) | 2017-10-21 | 2017-10-21 | A kind of method for three-dimensionally positioning network node of wireless sensor based on SCE PSO algorithms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710989499.7A CN107734637A (en) | 2017-10-21 | 2017-10-21 | A kind of method for three-dimensionally positioning network node of wireless sensor based on SCE PSO algorithms |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107734637A true CN107734637A (en) | 2018-02-23 |
Family
ID=61213272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710989499.7A Pending CN107734637A (en) | 2017-10-21 | 2017-10-21 | A kind of method for three-dimensionally positioning network node of wireless sensor based on SCE PSO algorithms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107734637A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325370A (en) * | 2011-06-28 | 2012-01-18 | 山东大学威海分校 | High-precision three-dimensional positioner for wireless sensor network node |
| CN103517338A (en) * | 2013-10-17 | 2014-01-15 | 山东省计算中心 | Positioning method using mobile anchor nodes and facing three-dimensional wireless sensing network |
| CN103517413A (en) * | 2013-10-09 | 2014-01-15 | 江西理工大学 | WSN node locating method based on heterogeneous double-population particle swarm optimization |
| CN105430706A (en) * | 2015-11-03 | 2016-03-23 | 国网江西省电力科学研究院 | WSN (Wireless Sensor Networks) routing optimization method based on improved PSO (particle swarm optimization) |
-
2017
- 2017-10-21 CN CN201710989499.7A patent/CN107734637A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325370A (en) * | 2011-06-28 | 2012-01-18 | 山东大学威海分校 | High-precision three-dimensional positioner for wireless sensor network node |
| CN103517413A (en) * | 2013-10-09 | 2014-01-15 | 江西理工大学 | WSN node locating method based on heterogeneous double-population particle swarm optimization |
| CN103517338A (en) * | 2013-10-17 | 2014-01-15 | 山东省计算中心 | Positioning method using mobile anchor nodes and facing three-dimensional wireless sensing network |
| CN105430706A (en) * | 2015-11-03 | 2016-03-23 | 国网江西省电力科学研究院 | WSN (Wireless Sensor Networks) routing optimization method based on improved PSO (particle swarm optimization) |
Non-Patent Citations (3)
| Title |
|---|
| JIANG YAN: "A Modified Particle Swarm Optimization Algorithm", 《IEEE》 * |
| 刘羿彤: "一种改进的PSO算法", 《PROCEEDINGS OF THE 26TH CHINESE CONTROL CONFERENCE》 * |
| 马海波等: "SCE-UA 算法在TOPMODEL 参数优化中的应用", 《河海大学学报( 自然科学版)》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107613561B (en) | Wireless sensor network node three-dimensional positioning method based on alternating current SCE-PSO algorithm | |
| CN104023394A (en) | WSN positioning method based on self-adaptation inertia weight | |
| CN108924755B (en) | DV-HOP indoor positioning method based on immune particle swarm optimization | |
| CN113329490B (en) | Wireless sensor network node positioning method based on quantum tiger shark mechanism | |
| CN110062327A (en) | The wireless sensor network node locating method of microhabitat grey wolf optimization DV-Hop algorithm | |
| CN110996388B (en) | DV-Hop positioning method based on anchor node selection and random sampling particle swarm | |
| CN105554873A (en) | Wireless sensor network positioning algorithm based on PSO-GA-RBF-HOP | |
| CN110049433A (en) | A kind of positioning performance optimization method based on EDW-DPSO algorithm | |
| Chen et al. | 3D DV–hop localisation scheme based on particle swarm optimisation in wireless sensor networks | |
| CN112954594A (en) | Wireless sensor network node positioning algorithm based on artificial bee colony | |
| CN102325370A (en) | High-precision three-dimensional positioner for wireless sensor network node | |
| Yang et al. | An improved DV-Hop localization algorithm based on bat algorithm | |
| Rabhi et al. | An improved method for distributed localization in WSNs based on fruit fly optimization algorithm | |
| Rauniyar et al. | A new distributed localization algorithm using social learning based particle swarm optimization for Internet of Things | |
| CN111031502A (en) | Wireless sensor network node positioning method based on goblet sea squirt group algorithm | |
| CN109190787B (en) | Dual particle swarm multi-monitoring point access path planning method for underwater vehicle | |
| Singh et al. | An optimum localization approach using hybrid TSNMRA in 2D WSNs | |
| Pandian | Novel distance estimation based localization scheme for wireless sensor networks using modified swarm intelligence algorithm | |
| Cheng et al. | A fingerprint localization method based on weighted KNN algorithm | |
| CN107734637A (en) | A kind of method for three-dimensionally positioning network node of wireless sensor based on SCE PSO algorithms | |
| CN117241215A (en) | Wireless sensor network distributed node cooperative positioning method based on graph neural network | |
| CN103929810B (en) | DV Hop wireless sensor network node positioning methods based on wavelet neural | |
| Gupta et al. | Centroid based localization utilizing artificial bee colony algorithm | |
| Pang et al. | DV-hop localization algorithm based on RSSI hop number correction and improved artificial immune algorithm optimization | |
| Barshandeh et al. | A learning-based metaheuristic administered positioning model for 3D IoT networks |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180223 |