CN110996287B - Network node selection method, system and storage medium based on whale optimization algorithm - Google Patents
Network node selection method, system and storage medium based on whale optimization algorithm Download PDFInfo
- Publication number
- CN110996287B CN110996287B CN201911211845.4A CN201911211845A CN110996287B CN 110996287 B CN110996287 B CN 110996287B CN 201911211845 A CN201911211845 A CN 201911211845A CN 110996287 B CN110996287 B CN 110996287B
- Authority
- CN
- China
- Prior art keywords
- whale
- population
- optimal
- iteration
- individual
- 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
- H04W40/04—Communication route or path selection, e.g. power-based or shortest path routing based on wireless node resources
Abstract
The invention discloses a network node selection method, a system and a storage medium based on a whale optimization algorithm, wherein the method comprises the following steps: setting a population matrix of binary codes, setting maximum iteration times and initial iteration times, and randomly initializing the population matrix; calculating a target function according to a node selection scheme corresponding to each whale individual in the population to obtain the optimal individual position and the optimal fitness function value in the population; calculating a current dynamic convergence factor and a current dynamic weight according to the current iteration times; determining a scheme for calculating the individual position of the whale according to the current dynamic convergence factor and the generated random number, and updating the current individual position of the whale and the iteration times; if the iteration times reach the maximum iteration times, returning to the optimal whale individual position, and determining the sensor nodes participating in tracking according to the optimal whale individual position; otherwise, returning to the calculation. The invention is beneficial to improving the tracking precision and the real-time performance in the target tracking process in the wireless sensor network.
Description
Technical Field
The invention relates to the technical field of target tracking, in particular to a whale optimization algorithm-based network node selection method, system and storage medium.
Background
With the development of the technology in the field of microelectronics, the wireless sensor network is gradually and widely applied to the fields of military affairs, environmental monitoring and the like, and target tracking is also one of the important application scenes of the wireless sensor network. In the practical application process, all the sensor nodes are used for participating in target tracking, so that good tracking accuracy can be obtained, but due to the limitation of the energy of the sensors, the service life of the network can be greatly shortened by using all the sensor nodes for participating in tracking. How to reduce the service life of the sensor network as far as possible under the condition of ensuring the target tracking precision is a problem which is urgently needed to be solved in the field of target tracking at present. The node selection can well solve the problem that in each sampling time period, a part of sensor nodes are selected to participate in target tracking in a self-adaptive mode, and therefore energy waste is effectively avoided. Therefore, for the wireless sensor network, the node selection has strong theoretical and practical significance, and the design of an effective node selection algorithm is crucial.
At present, algorithms for node selection problems include a genetic algorithm, a particle swarm optimization algorithm, a convex optimization algorithm and the like, but the methods generally have the characteristics of low tracking precision, low convergence speed and easiness in falling into local optimization.
Disclosure of Invention
The invention provides a whale optimization algorithm-based network node selection method, a system and a storage medium, which are used for overcoming the technical problems in the prior art and improving the tracking precision and the real-time performance in the target tracking process in a wireless sensor network.
The invention provides a network node selection method based on whale optimization algorithm, which comprises the following steps:
The invention also provides a whale optimization algorithm-based network node selection system, which comprises the following components:
the system comprises a setting module, a calculating module and a judging module, wherein the setting module is used for setting a binary coded population matrix, each row of the population matrix represents one whale individual in a population, the column number represents the number of nodes in a wireless sensor network, the maximum iteration number and the initial iteration number are set, and the population matrix is initialized randomly so that the number of nodes in each row of the population matrix is 1;
the first calculation module is used for calculating the objective function according to the node selection scheme corresponding to each whale individual in the population, acquiring the fitness function value corresponding to each whale individual, and acquiring the optimal individual position and the optimal fitness function value in the population;
the second calculation module is used for calculating a current dynamic convergence factor and a current dynamic weight according to the current iteration frequency, wherein the dynamic convergence factor and the dynamic weight are functions taking the iteration frequency as a variable;
the third calculation module is used for determining a scheme for calculating the individual position of the whale according to the current dynamic convergence factor and the generated random number, updating the individual position of the current whale and adding 1 to the iteration number;
the judging module is used for outputting the optimal fitness function value and the optimal whale individual position if the iteration times reach the maximum iteration times, and returning to the first calculating module to continue iterative calculation if the iteration times do not reach the maximum iteration times;
and the node determining module is used for determining the sensor nodes participating in tracking according to the node selection scheme corresponding to the optimal whale individual position output by the judging module.
The invention also provides a storage medium having stored thereon a computer program readable by a computer, the computer program being executable to perform the method as described above.
By adopting the nonlinear adaptive dynamic convergence factor, the algorithm is in an exploration stage in the early stage of iteration, the descending speed of the nonlinear adaptive dynamic convergence factor is low, and the method is favorable for enhancing the global search capability of the algorithm. In the later stage of iteration, the algorithm is in a development stage, the reduction speed of the nonlinear self-adaptive convergence factor is increased, and the search speed of the algorithm and the accuracy of local search are ensured, so that the balance between an exploration stage and the development stage is facilitated; furthermore, by adopting controllable dynamic weight, the algorithm can be encouraged to carry out global search in the early iteration stage, and the exploration capability of the algorithm is enhanced and improved; in the later stage of iteration, the dynamic weight encourages the algorithm to perform local search, so that the development capability of the algorithm is enhanced and improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a network node selection method based on a whale optimization algorithm according to an embodiment of the present invention;
FIG. 2 shows example a of the present invention max2 and aminWhen the weight is 0, a nonlinear convergence factor and a dynamic disturbance weight graph are obtained;
FIG. 3 is a detailed flow chart of a whale optimization algorithm employed in an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a network node selection system based on a whale optimization algorithm according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the technical solution of the present invention clearer, embodiments of the present invention are described in detail below with reference to the accompanying drawings.
FIG. 1 is a flowchart of a network node selection method based on whale optimization algorithm according to an embodiment of the present invention, and FIG. 2 is a flowchart of a network node selection method according to an embodiment of the present invention max2 and aminFig. 3 is a specific flowchart of a whale optimization algorithm adopted in the embodiment of the present invention, as shown in fig. 1 to 3, where the method in the embodiment includes:
A target to be tracked and a plurality of sensor nodes exist in an observation area at the same time, and an optimal node set needs to be selected at different moments to participate in target tracking. The embodiment of the invention adopts a binary coded whale population to represent the sensor nodes, and the population pop is N _ pop × NaWherein N _ pop is the number of population individuals, NaIs the total number of sensor nodes in the observation area, NsThe number of sensor nodes to be selected. Namely, it is
i∈{1,2,...,N_pop}，j∈{1,2,...,Na}
Wherein L isk+1＝L(xk+1|z1:k)，
And
the specific calculation of node selection by using the objective function corresponding to the x and y components in the target motion state at the time k +1 is described in detail in the paper published by the inventor, and is not described herein again.
At the beginning of algorithm iteration, initial parameters of the algorithm are firstly set, such as the maximum iteration number, the initial iteration number and population matrix initialization of the algorithm, and N is required to be selected for each sampling time periodsEach sensor node participates in target tracking, so that N is ensured in each row during population matrix initializationsEach node is 1, the rest are 0, and 1 in the matrix indicates that the corresponding sensor node is to be activated.
And step 12, calculating the objective function according to the node selection scheme corresponding to each whale individual in the population, acquiring the fitness function value corresponding to each whale individual, and acquiring the optimal individual position and the optimal fitness function value in the population.
And selecting an objective function according to the calculation requirement, substituting each row in the population matrix into the objective function to calculate, comparing the objective function value corresponding to each whale individual, namely the fitness function value, and acquiring the optimal fitness function value and the corresponding optimal whale individual.
And step 13, calculating a current dynamic convergence factor and a current dynamic weight according to the current iteration frequency, wherein the dynamic convergence factor and the dynamic weight are functions taking the iteration frequency as a variable.
A general group intelligence algorithm can be divided into two stages of exploration and development, and how to balance the two stages of the algorithm is the key for improving the algorithm. The following are the parameter calculations for the traditional whale algorithm:
A＝2a*r-a
C＝2*r
wherein Maxlter is the maximum iteration number of the algorithm, t is the iteration number, and r is a random number of [0,1 ]. And (4) selecting the current iteration times and calculating and updating the parameters in each calculation.
In the whale algorithm, the parameter A influences the trend of the whole algorithm, when the parameter A is greater than 1, the search range of an individual is wide and random, global search can be performed at the moment, and the algorithm is in an exploration stage at the moment. When | A | ≦ 1, the individual approaches the optimal solution gradually, local search is realized, and the algorithm is in the development stage at this time. The weight C also influences the searching process of the algorithm, and the exploration and development capacity of the algorithm can be changed by changing the value of C.
As known from the parameter calculation, the traditional whale algorithm adopts linear convergence factors and randomly generated weights, and is not ideal when the problem of node selection is processed, local optimization is easy to happen in target tracking, and the convergence speed is low, so that the requirement of target tracking instantaneity cannot be met.
In order to solve the above problems, the present invention proposes to control the dynamic convergence factor and the dynamic weight by the number of iterations, rather than the conventional randomly generated dynamic weight, i.e., the dynamic convergence factor and the dynamic weight are both functions with the number of iterations as variables. In practical application, corresponding dynamic convergence factors and dynamic weight functions can be selected according to the characteristics of specific target tracking or the field of whale optimization algorithm application. Specifically, the linear convergence factor a and the controllable dynamic weight C can be used to control the algorithm exploration phase and the algorithm development phase, and the nonlinear convergence factor a and the controllable dynamic weight C can also be used to control the algorithm exploration phase and the algorithm development phase, so that the convergence factor a and the dynamic weight C can be adjusted and controlled by selecting a proper function to meet the requirements of the algorithm on rapid convergence and tracking accuracy.
In order to achieve better algorithm convergence speed and tracking accuracy, the following parameter calculation formula is adopted in the embodiment of the invention:
A＝2a*r-a
a＝amax-(amax-amin)*(t/Maxlter)2
C＝2*exp[-(2*t/Maxlter)2]
wherein Maxlter is the maximum iteration number of the algorithm, t is the iteration number, and r is a random number of [0,1 ]. And substituting t into the current iteration times during each iteration calculation.
According to different algorithm requirements, a can be selected to be suitablemaxAnd aminTo perform algorithm optimization. The embodiment of the invention is applied to whale optimization algorithm, and a can be selectedmax＝2，amin＝0。
The convergence factor a and the dynamic weight C in the above formula can be adopted at the same time, or the dynamic weight C can be only adopted and then combined with other nonlinear self-adaptive dynamic convergence factor formulas to calculate the a.
Compared with the linear convergence factor, the nonlinear adaptive dynamic convergence factor provided by the invention has the advantages that the algorithm is in an exploration phase in the early stage of iteration, the descending speed of the nonlinear adaptive dynamic convergence factor is slower, and the global search capability of the algorithm is enhanced. In contrast, in the later stage of iteration, the algorithm is in a development stage, and the descending speed of the improved convergence factor is increased, so that the searching speed of the algorithm and the accuracy of local searching are ensured. The nonlinear dynamic adaptive convergence factor is suitable for practical problems in daily life and is more beneficial to the balance between an exploration phase and a development phase.
In the iteration process of the whale algorithm, the dynamic convergence factor a and the dynamic weight C jointly influence how the current individual moves in the next iteration, and therefore the value of the dynamic weight C also influences the exploration and utilization capacity of the algorithm. When C is larger than 1, the algorithm is encouraged to explore, and the global searching capability of the algorithm can be further enhanced. When C is smaller than 1, the development capability of the algorithm is enhanced, the algorithm is prevented from falling into local optimization, but r in the existing whale algorithm is randomly generated, and the control on the C value is not facilitated. The embodiment of the invention provides the dynamic disturbance weight based on the exponential function, so that the exploration and development stages of the algorithm can be better balanced through the mutual cooperation of A and C in the whole algorithm iteration process, and a better result is obtained.
In the whale algorithm, the value of A influences the searching process of the whole algorithm, when | A | >1, the algorithm carries out global searching, and at the moment, the algorithm carries out random searching in the whole searching space. When | A | is less than or equal to 1, the algorithm carries out local search and searches around the optimal position to further obtain the optimal solution. The traditional convergence factor is linear, and the global search and the local search respectively occupy half of the search time, which is unrealistic for practical problems, as shown in fig. 2, the convergence factor provided by the invention enables the time ratio of the global search and the local search of the algorithm to be about 6:4, which is beneficial for the global search, and meanwhile, the factor is nonlinear self-adaptive and is more suitable for solving practical problems. The value of the weight C also influences the searching capability of the algorithm, when C is greater than 1, the algorithm can be encouraged to carry out global search, so that the exploration capability of the algorithm is improved, and when C is less than 1, the algorithm is encouraged to carry out local search, so that the development capability of the algorithm is improved. As can be seen from fig. 2, in the earlier stage of algorithm iteration, | a | >1, the algorithm is in the exploration stage, and at this time, the dynamic disturbance weight C >1 can further encourage the algorithm to perform global search on the basis of | a | >1, thereby enhancing the exploration capability of the algorithm. Similarly, in the later stage of algorithm iteration, when the | A | ≦ 1 algorithm is in the development stage, the dynamic disturbance weight C <1 encourages the algorithm to perform local search on the basis of | A | ≦ 1, and the development capability of the algorithm is enhanced.
The nonlinear self-adaptive dynamic convergence factor and the dynamic weight provided by the embodiment of the invention are combined with each other, so that the exploration and development capabilities of the algorithm can be well balanced.
And step 14, determining a scheme for calculating the individual position of the whale according to the current dynamic convergence factor and the generated random number, updating the current individual position of the whale, and adding 1 to the iteration number.
The current dynamic convergence factor a is calculated through the step 13, so that a parameter A in the whale algorithm can be calculated, and the mode of updating and calculating the individual positions of the whales can be determined through the generated random number p. Specifically, if p is less than 0.5 and the absolute value of a is less than 1, then the current whale individual is updated by the following formula:
D＝|C·Xbest-X(t)|
X(t+1)＝Xbest(t)-A·D
wherein, XbestAs the best individual position, X (t) is the current individual position, and X (t +1) is the updated current individual position.
If p is less than 0.5 and the absolute value of A is greater than or equal to 1, randomly selecting an individual X from the populationrand(t) and updating the individual positions of the whales by adopting the following formula:
D＝|C·Xrand-X(t)|
X(t+1)＝Xrand(t)-A·D
if the value of p is greater than or equal to 0.5, updating the individual position by adopting the following formula:
X(t+1)＝D'·ebl·cos(2πl)+Xbest(t)
wherein D' ═ Xbest(t) -X (t) l represents the distance between the current individual and the best individual, l is [ -1,1]Random number in betweenAnd b is a spiral shape parameter.
When the iteration times reach the preset maximum iteration times, the algorithm terminates searching and iteration, the whale individual output by the last iteration is the optimal individual to be searched, and therefore the sensor node participating in tracking can be selected according to the corresponding node selection scheme. The whale algorithm in the embodiment of the invention has the effect of constantly changing the whale population in the node selection process to obtain higher randomness and accuracy, so that the optimal sensor node subset is more likely to be obtained.
According to the embodiment of the invention, the nonlinear adaptive dynamic convergence factor is adopted, the algorithm is in an exploration stage in the early stage of iteration, the descending speed of the nonlinear adaptive dynamic convergence factor is low, and the method is favorable for enhancing the global search capability of the algorithm. In the later stage of iteration, the algorithm is in a development stage, the reduction speed of the nonlinear self-adaptive convergence factor is increased, and the search speed of the algorithm and the accuracy of local search are ensured, so that the balance between an exploration stage and the development stage is facilitated; furthermore, by adopting controllable dynamic weight, the algorithm can be encouraged to carry out global search in the early iteration stage, and the exploration capability of the algorithm is enhanced and improved; in the later stage of iteration, the dynamic weight encourages the algorithm to perform local search, so that the development capability of the algorithm is enhanced and improved.
When solving the node selection problem in the actual target tracking process, it is usually necessary to convert the continuous space into the discrete space through an appropriate transformation. The range of the transformation function should be within the interval 0,1 and should provide a higher probability to change the current position for greater randomness. Compared with an S-shaped function and a V-shaped function, the hyperbolic tangent V-shaped conversion function has a faster convergence speed and a higher transformation probability, and the embodiment of the invention adopts the following hyperbolic tangent function based on position updating to map the position information of each whale individual into a binary system.
Wherein q is a random number between [0,1 ].
In the above embodiment, for target tracking of a sensor network node, the target function selected by the present invention is a sensor node selection algorithm based on a Conditional Posterior clavier cramer-Rao Lower bound (CPCRLB for short), and the algorithm has good performance in tracking accuracy, energy consumption, and computational complexity.
Fig. 4 is a schematic structural diagram of a network node selection system based on a whale optimization algorithm according to an embodiment of the present invention, and as shown in fig. 4, the system according to the embodiment of the present invention includes: the node determination system comprises a setting module 100, a first calculation module 201, a first calculation module 202, a first calculation module 203, a judgment module 300 and a node determination module 400. The setting module 100 is configured to set a binary-coded population matrix, where each row of the population matrix represents one whale individual in a population, the number of columns represents the number of nodes in a wireless sensor network, the maximum iteration number and the initial iteration number are set, and the population matrix is initialized randomly, so that each row of the population matrix has a preset number of nodes of 1; the first calculating module 201 is configured to calculate a target function according to a node selection scheme corresponding to each individual whale in the population, obtain a fitness function value corresponding to each individual whale, and obtain an optimal individual position and an optimal fitness function value in the population; a second calculating module 202, configured to calculate a current dynamic convergence factor and a current dynamic weight according to the current iteration number, where the dynamic convergence factor and the dynamic weight are both functions using the iteration number as a variable; a third calculating module 303, configured to determine a scheme for calculating an individual position of the whale according to the current dynamic convergence factor and the generated random number, update the individual position of the current whale, and add 1 to the iteration number; the judging module 300 is used for outputting an optimal fitness function value and an optimal whale individual position if the iteration times reach the maximum iteration times, and returning to the first calculating module to continue iterative calculation if the iteration times do not reach the maximum iteration times; and a node determining module 400, configured to determine a sensor node participating in tracking according to a node selection scheme corresponding to the optimal whale individual position output by the determining module.
The network node selection system provided in the embodiment of the present invention further includes: and the binarization module is used for binarizing the position information of each whale individual by adopting a hyperbolic tangent function.
The technical working principle and the achieved working effect corresponding to the network node selection system provided by the embodiment of the invention are similar to those of the method embodiment, and are not described again.
The present invention also provides a computer-readable storage medium, such as: ROM/RAM, magnetic disks, optical disks, etc., which store a computer program readable by a computer, which can be executed by a hardware device such as a terminal device, a computer or a server to perform the above-mentioned node selection method based on the whale optimization algorithm.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A network node selection method based on whale optimization algorithm is characterized by comprising the following steps:
step 11, setting a population matrix of binary codes, wherein each row of the population matrix represents one whale individual in a population, the number of columns represents the number of nodes in a wireless sensor network, the maximum iteration times and the initial iteration times are set, and the population matrix is initialized randomly so that the number of nodes in each row of the population matrix is 1;
step 12, calculating an objective function according to a node selection scheme corresponding to each whale individual in the population, acquiring a fitness function value corresponding to each whale individual, and acquiring an optimal individual position and an optimal fitness function value in the population;
step 13, calculating a current dynamic convergence factor and a current dynamic weight according to the current iteration frequency, wherein the dynamic convergence factor and the dynamic weight are functions taking the iteration frequency as a variable;
step 14, determining a scheme for calculating the individual position of the whale according to the current dynamic convergence factor and the generated random number, updating the current individual position of the whale, and adding 1 to the iteration number;
step 15, if the iteration times reach the maximum iteration times, outputting an optimal fitness function value and an optimal whale individual position, and determining a sensor node participating in tracking according to a node selection scheme corresponding to the optimal whale individual position; otherwise, executing step 12;
wherein, the dynamic weight adopts a dynamic disturbance weight C based on an exponential function,
C＝2*exp[-(2*t/Maxlter)2]
t is the iteration number, and Maxlter is the set maximum iteration number.
2. The method of claim 1, further comprising: and binarizing the position information of each whale individual by adopting a hyperbolic tangent function.
3. The method of claim 1, wherein the dynamic convergence factor varies nonlinearly adaptively with the number of iterations, and is obtained by the following formula:
a＝amax-(amax-amin)*(t/Maxlter)2
wherein a is a dynamic convergence factor, amaxAnd aminRespectively, the maximum and minimum values of a.
4. The method according to any one of claims 1 to 3, wherein the objective function is a node selection algorithm based on the lower bound of the conditional A posteriori Cramer-Rou.
5. A whale optimization algorithm-based network node selection system is characterized by comprising:
the system comprises a setting module, a calculating module and a judging module, wherein the setting module is used for setting a binary coded population matrix, each row of the population matrix represents one whale individual in a population, the column number represents the number of nodes in a wireless sensor network, the maximum iteration number and the initial iteration number are set, and the population matrix is initialized randomly so that the number of nodes in each row of the population matrix is 1;
the first calculation module is used for calculating the objective function according to the node selection scheme corresponding to each whale individual in the population, acquiring the fitness function value corresponding to each whale individual, and acquiring the optimal individual position and the optimal fitness function value in the population;
the second calculation module is used for calculating a current dynamic convergence factor and a current dynamic weight according to the current iteration frequency, wherein the dynamic convergence factor and the dynamic weight are functions taking the iteration frequency as a variable;
the third calculation module is used for determining a scheme for calculating the individual position of the whale according to the current dynamic convergence factor and the generated random number, updating the individual position of the current whale and adding 1 to the iteration number;
the judging module is used for outputting the optimal fitness function value and the optimal whale individual position if the iteration times reach the maximum iteration times, and returning to the first calculating module to continue iterative calculation if the iteration times do not reach the maximum iteration times;
the node determining module is used for determining sensor nodes participating in tracking according to the node selection scheme corresponding to the optimal whale individual position output by the judging module;
wherein, the dynamic weight adopts a dynamic disturbance weight C based on an exponential function,
C＝2*exp[-(2*t/Maxlter)2]
wherein t is the iteration number, and MaxFilter is the set maximum iteration number.
6. The system of claim 5, further comprising: and the binarization module is used for binarizing the position information of each whale individual by adopting a hyperbolic tangent function.
7. The system of claim 5, wherein the dynamic convergence factor varies nonlinearly adaptively with the number of iterations, and is obtained by the following formula:
a＝amax-(amax-amin)*(t/Maxlter)2
wherein a is a dynamic convergence factor, amaxAnd aminRespectively, the maximum and minimum values of a.
8. A storage medium, characterized in that the storage medium stores a computer program readable by a computer, the computer program being executable by the computer to perform the method according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911211845.4A CN110996287B (en) | 2019-12-04 | 2019-12-04 | Network node selection method, system and storage medium based on whale optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911211845.4A CN110996287B (en) | 2019-12-04 | 2019-12-04 | Network node selection method, system and storage medium based on whale optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110996287A CN110996287A (en) | 2020-04-10 |
| CN110996287B true CN110996287B (en) | 2022-02-01 |
Family
ID=70089064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911211845.4A Active CN110996287B (en) | 2019-12-04 | 2019-12-04 | Network node selection method, system and storage medium based on whale optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110996287B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001309A (en) * | 2020-08-21 | 2020-11-27 | 上海特金无线技术有限公司 | Target searching method, device and equipment based on unmanned aerial vehicle cluster and storage medium |
| CN112947531A (en) * | 2021-03-26 | 2021-06-11 | 上海工程技术大学 | Control method, device and equipment of unmanned aerial vehicle and storage medium |
| CN113780787B (en) * | 2021-09-01 | 2023-05-02 | 成都信息工程大学 | Collaborative task allocation method for multi-mobile-platform system under complex water environment |
| CN114048668B (en) * | 2021-09-23 | 2023-04-28 | 石河子大学 | Comprehensive energy-oriented wireless sensor wheel value method and system |
| CN114172769B (en) * | 2021-11-26 | 2023-10-03 | 哈尔滨工程大学 | Modulation signal identification method for evolutionary long-short-term memory network |
| CN114390672A (en) * | 2021-12-15 | 2022-04-22 | 广州杰赛科技股份有限公司 | Intelligent vehicle positioning method, device, equipment and medium |
| CN115080402B (en) * | 2022-06-22 | 2023-04-18 | 河南工业大学 | Whale optimization algorithm-based software defect positioning method and processing device |
| CN115866621B (en) * | 2022-11-08 | 2023-12-01 | 重庆邮电大学 | Wireless sensor network coverage method based on whale algorithm |
| CN116709240B (en) * | 2023-06-26 | 2024-03-12 | 南京理工大学 | Hierarchical sensor deployment method based on whale optimization algorithm |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108183500A (en) * | 2017-11-24 | 2018-06-19 | 国网甘肃省电力公司电力科学研究院 | A kind of rural area provided multiple forms of energy to complement each other is micro- can net capacity configuration optimizing method and device |
| CN109635492A (en) * | 2018-12-27 | 2019-04-16 | 湖南科技大学 | Based on the adaptive BBMC main circuit parameter preferred method of electric current quota |
| CN109768573A (en) * | 2019-01-29 | 2019-05-17 | 三峡大学 | Var Optimization Method in Network Distribution based on multiple target difference grey wolf algorithm |
| CN109886589A (en) * | 2019-02-28 | 2019-06-14 | 长安大学 | A method of low-carbon Job-Shop is solved based on whale optimization algorithm is improved |
| CN109902873A (en) * | 2019-02-28 | 2019-06-18 | 长安大学 | A method of the cloud manufacturing resource allocation based on modified whale algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180284758A1 (en) * | 2016-05-09 | 2018-10-04 | StrongForce IoT Portfolio 2016, LLC | Methods and systems for industrial internet of things data collection for equipment analysis in an upstream oil and gas environment |
-
2019
- 2019-12-04 CN CN201911211845.4A patent/CN110996287B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108183500A (en) * | 2017-11-24 | 2018-06-19 | 国网甘肃省电力公司电力科学研究院 | A kind of rural area provided multiple forms of energy to complement each other is micro- can net capacity configuration optimizing method and device |
| CN109635492A (en) * | 2018-12-27 | 2019-04-16 | 湖南科技大学 | Based on the adaptive BBMC main circuit parameter preferred method of electric current quota |
| CN109768573A (en) * | 2019-01-29 | 2019-05-17 | 三峡大学 | Var Optimization Method in Network Distribution based on multiple target difference grey wolf algorithm |
| CN109886589A (en) * | 2019-02-28 | 2019-06-14 | 长安大学 | A method of low-carbon Job-Shop is solved based on whale optimization algorithm is improved |
| CN109902873A (en) * | 2019-02-28 | 2019-06-18 | 长安大学 | A method of the cloud manufacturing resource allocation based on modified whale algorithm |
Non-Patent Citations (3)
| Title |
|---|
| CPCRLB based local node selection for passive acoustic target tracking in a distributed sensor network;JIANG Xiao-xiao等;《声学技术》;20181031;全文 * |
| Whale Optimization Approach for Optimization Problem In Distributed Wireless Sensor Network;Lotfi Baidar等;《Proceedings of the 9th International Conference on Information Systems and Technologies》;20190331;全文 * |
| 基于灰狼算法优化PID的机器人路径跟踪控制;朱敬旭辉等;《电子技术与软件工程》;20191130;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110996287A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110996287B (en) | Network node selection method, system and storage medium based on whale optimization algorithm | |
| CN109948029B (en) | Neural network self-adaptive depth Hash image searching method | |
| CN112329934A (en) | RBF neural network optimization algorithm based on improved sparrow search algorithm | |
| Zhang et al. | Deterministic and probabilistic interval prediction for short-term wind power generation based on variational mode decomposition and machine learning methods | |
| CN110619082A (en) | Project recommendation method based on repeated search mechanism | |
| CN111709511A (en) | Harris eagle optimization algorithm based on random unscented Sigma point variation | |
| Mitschke et al. | Gradient based evolution to optimize the structure of convolutional neural networks | |
| CN114091650A (en) | Searching method and application of deep convolutional neural network architecture | |
| Zhao et al. | What and where: Learn to plug adapters via nas for multidomain learning | |
| Sahman et al. | Binary tree-seed algorithms with S-shaped and V-shaped transfer functions | |
| CN110222816B (en) | Deep learning model establishing method, image processing method and device | |
| Aghajari et al. | A novel chaotic hetero-associative memory | |
| Zheng et al. | Edge-labeling based modified gated graph network for few-shot learning | |
| Yu et al. | Analysis and Application of the Spatio-Temporal Feature in Wind Power Prediction. | |
| CN111539989B (en) | Computer vision single target tracking method based on optimized variance reduction | |
| Zhao et al. | Artifcial Bee Colony Based on Special Central and Adapt Number of Dimensions Learning. | |
| CN108415783B (en) | Heterogeneous multi-core task allocation method based on improved bee colony algorithm | |
| Lu et al. | Laplacian deep echo state network optimized by genetic algorithm | |
| CN111488991A (en) | Communication community detection method of cuckoo algorithm combined with genetic and discrete difference | |
| Zenasni et al. | A Fuzzy Logic based Offloading System for Distributed Deep Learning in Wireless Sensor Networks | |
| CN112381226B (en) | Deep convolutional neural network architecture searching method based on particle swarm optimization | |
| Zhao et al. | An improved Whale Swarm Algorithm with nonlinear weighting and convergence factor | |
| Binas et al. | Low-memory convolutional neural networks through incremental depth-first processing | |
| CN117573915B (en) | Binary code image retrieval method and system based on contrast learning | |
| Teng et al. | A New Frog Leaping Algorithm Based on Simulated Annealing and Immunization Algorithm for Low-power Mapping in Network-on-chip. |
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 |