A Deployment Method and System for Sensor Nodes in a Wireless Sensor Network

Abstract

The present invention discloses a method and system for deploying sensor nodes in a wireless sensor network, defining the coverage optimization problem as a sensor node deployment problem that maximizes the network coverage rate within the monitoring area; then initializing the multi-strategy artificial bee colony algorithm, and then using the multi-strategy artificial bee colony algorithm to iteratively update the feasible solutions of the population individuals until an approximate optimal solution is obtained. Among them, in the employed bee stage, each employed bee randomly selects a search strategy from the multi-strategy pool, then uses the search strategy to update the corresponding feasible solution, and then accumulates the improvement amount corresponding to each search strategy when the feasible solution is successfully updated. In the onlooker bee stage, the current feasible solution is updated with the search strategy with the largest improvement amount in the employed bee stage. Finally, the sensor nodes are deployed with reference to the approximate optimal solution. The technical solution of the present invention effectively improves the network coverage rate through a strategy complementary mechanism, and obtains a more reliable sensor node deployment scheme.

Description

Technical Field

[0001] The present invention belongs to the technical field of wireless sensor networks, and particularly relates to a method and system for deploying sensor nodes in a wireless sensor network. Background Art

[0002] A wireless sensor network (WSN) is an emerging computing and networking paradigm, which can be defined as a network consisting of tiny, small, expensive, and highly intelligent devices called sensor nodes. A wireless sensor network is a network structure formed by organizing several sensor nodes through wireless communication technology, and its main applications are in the detection and monitoring of target areas, and it has been widely used in the industrial field, such as urban monitoring, environmental detection, military monitoring, mobile target tracking, and smart home and other application fields. However, there are some limitations in the sensor nodes themselves, such as high network costs and weak sensing ranges. When deploying sensor nodes, the redundancy of sensor nodes should be minimized as much as possible to improve the coverage rate of the wireless sensor network WSN.

[0003] Sensor node coverage optimization is an important issue in wireless sensor networks, and the degree of coverage has a very large impact on the network quality. The purpose of sensor node coverage optimization is to maximize the monitorable area within the network with a limited number of sensors, while minimizing the detection blind spots as much as possible. Usually, sensor nodes are randomly deployed in the target area to be detected. However, this random deployment scheme will lead to high node density and large redundancy, resulting in low overall coverage rate and further affecting the monitoring quality of the wireless sensor network. Therefore, a reasonable sensor node deployment scheme needs to be designed to not only improve the service quality and energy utilization rate of the wireless sensor network, but also achieve load balancing in the transmission within the wireless sensor network.

[0004] Affected by network resources and coverage characteristics, sensor node coverage optimization is essentially a typical NP-hard problem, and many classic mathematical optimization methods are difficult to solve, such as the gradient descent method. In recent years, many scholars have studied the problem of wireless sensor network node coverage. Among them, the most popular ones are to use genetic algorithms (GA), particle swarm optimization algorithms (PSO), artificial bee colony algorithms (ABC), and simulated annealing algorithms (SA) to solve this problem. Such optimization algorithms have almost no requirements on the mathematical properties of the problem and have strong adaptability.

[0005] Although some of the above heuristics have achieved success in optimizing the coverage of wireless sensor networks, in fact, they all obtain an approximate optimal solution rather than the optimal feasible solution to this problem. In addition, the search strategies of these algorithms are too greedy. When the iteration reaches the middle and late stages, it is extremely easy to fall into the local optimal solution of this problem and it is difficult to obtain a solution of higher quality. Summary of the Invention

[0006] The object of the present invention is to solve the problem that the solution accuracy of the deployment optimization method of sensor nodes in the existing wireless sensor network needs to be improved, and to provide a method and system for deploying sensor nodes in a wireless sensor network. Specifically, the deployment method provided by the technical solution of the present invention introduces an artificial bee colony algorithm to optimize the deployment of sensor nodes in a wireless sensor network, and optimizes the artificial bee colony algorithm. On the one hand, a multi-strategy pool is set up to provide a variety of search strategies, giving full play to the complementary advantages of different strategies. On the other hand, by accumulating the improvement amount corresponding to each search strategy when successfully updating the feasible solution during the employed bee stage, and then greedily selecting the search strategy with the largest improvement amount Δ i as the search strategy of this stage to update the feasible solution. Through the principle of complementary advantages between strategies, the optimization performance of the algorithm is strengthened, combining the characteristics of the coverage optimization problem with the working principle of the optimization algorithm, further improving the accuracy of the feasible solution, and maximizing the coverage rate under the wireless sensor network.

[0007] On the one hand, a method for deploying sensor nodes in a wireless sensor network provided by the present invention includes the following steps:

[0008] Step 1: Solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area by using a multi-strategy artificial bee colony algorithm to obtain an approximate optimal solution;

[0009] Step 2: Then deploy sensor nodes in the monitoring area with the approximate optimal solution;

[0010] The coverage optimization problem is: the sensor node deployment problem that maximizes the network coverage rate in the monitoring area; wherein, the monitoring area is discretized into M×N monitoring points, and the number of sensor nodes to be deployed is D, and D is a positive integer;

[0011] During the process of solving the coverage optimization problem by using the multi-strategy artificial bee colony algorithm, the feasible solution corresponding to each population individual is the sensor node deployment result of the coverage optimization problem; wherein, first randomly generate an initial population to obtain an initial feasible solution, and then iteratively update the feasible solution corresponding to the population individual, and regard the optimal feasible solution after meeting the iteration termination condition as the approximate optimal solution;

[0012] Each round of iterative update sequentially performs the update of feasible solutions in the employed bee, onlooker bee, and scout bee stages; and in the employed bee stage, each employed bee randomly selects a search strategy from the multi-strategy pool, then uses the search strategy to update the corresponding feasible solution, and then accumulates the improvement amount corresponding to each search strategy when the feasible solution is successfully updated; wherein, the multi-strategy pool includes two or more search strategies. When the fitness of the new feasible solution is better than that of the current feasible solution, it is considered that the corresponding search strategy has successfully updated the feasible solution and the new feasible solution replaces the current feasible solution.

[0013] In the onlooker bee stage, the current feasible solution is updated with the search strategy having the largest improvement amount in the employed bee stage.

[0014] Specifically, the process of step 1 is as follows:

[0015] Step 1-1: Initialize the multi-strategy artificial bee colony algorithm, including at least setting the population size, the maximum number of evaluations, the initial value of the improvement amount, and randomly generating initial feasible solutions for the population individuals within the solution search space.

[0016] Step 1-2: Based on the multi-strategy artificial bee colony algorithm, iteratively update the feasible solutions of the population individuals until the iteration termination condition is met to obtain an approximate optimal solution. Among them, each round of iteration sequentially performs the update of feasible solutions in the employed bee, onlooker bee, and scout bee stages.

[0017] In the employed bee stage, each employed bee randomly selects a search strategy from the multi-strategy pool, then uses the search strategy to update the corresponding feasible solution, and then accumulates the improvement amount corresponding to each search strategy when the feasible solution is successfully updated. Wherein, the multi-strategy pool includes two or more search strategies. When the fitness of the new feasible solution is better than that of the current feasible solution, it is considered that the corresponding search strategy has successfully updated the feasible solution and the new feasible solution replaces the current feasible solution.

[0018] In the onlooker bee stage, the current feasible solution is updated with the search strategy having the largest improvement amount in the employed bee stage.

[0019] Further optionally, the search strategies in the multi-strategy pool are represented as follows:

[0020]

[0021] In the formula, X i is the parent individual, corresponding to the feasible solution before update; V i is the offspring individual, corresponding to the feasible solution after update; X k and X t are both the feasible solutions corresponding to a random individual in the population, and X i ≠X k ≠X t; The parameter K is a variable coefficient that changes with iterations, and is a random number uniformly distributed in [-1.5, 1.5]. FEs is the current number of evaluations, that is, each time a feasible solution is updated, the current number of evaluations is incremented by one. MaxFEs is the maximum number of evaluations. gaussian(v 1 ,|δ 2 |) is the Gaussian distribution function, δ 1 is the central region of the Gaussian distribution, δ 2 is the perturbation range, and X best is the current optimal feasible solution in the population.

[0022] The technical solution of the present invention creatively proposes to construct multiple strategy pools and further selects 4 search strategies with different characteristics, including three search strategies with strong local search capabilities and one search strategy with strong global search capabilities, thereby strengthening the local search and global search capabilities. Through the complementary advantages of the strategies, the optimization performance of the algorithm is enhanced. The set K value is a dynamic search step size, which helps the algorithm jump out of the local optimum and obtain a better deployment plan.

[0023] Further preferably, during each iteration update, when the fitness of the new feasible solution is better than that of the current feasible solution, the new feasible solution replaces the current feasible solution. Among them, the fitness function is the coverage rate of the monitoring area, and the corresponding formula is as follows:

[0024]

[0025] Among them, CR A represents the coverage rate of the monitoring area A, and P{i} is the set of sensing probabilities of the points covered by the sensor node i, represents the set of points that can be monitored by D sensor nodes in the monitoring area.

[0026] Further preferably, the coverage optimization problem adopts a probability sensing model, and the formula for the corresponding sensing probability is as follows:

[0027]

[0028] Among them, P S,Q is the sensing probability between the sensor node and the monitoring point, S represents the central position of the sensor node, Q represents the monitoring point in the monitoring area, and λ 1 =r e -r + d(S, Q), λ 2 =r e +r - d(S, Q), and λ 1 , λ 2 are both defined intermediate parameters, and r eis the radius fluctuation value of the uncertain detection ability of the sensor node, r is the sensing radius of the sensor node, d(S,Q) is the Euclidean distance calculated between S and Q, and α 1 and α 2 and β 1 and β 2 are the attenuation coefficients of the sensing probability, and their values are generally empirical values. In the following embodiments of the present invention, this set of parameters are respectively set to 1, 0, 1, and 1.5, but the present invention is not limited thereto; e is the natural base.

[0029] When constructing the mathematical model of the coverage optimization problem, environmental factors and the attributes of sensor nodes should be considered, otherwise it will seriously affect the accuracy of the simulation experiment results. In the past, in the coverage optimization problem, the commonly used mathematical model was the binary sensing model, which too simply and ideally used the sensing radius of the sensor node to divide whether the monitoring area could be sensed. The technical solution of the present invention adopts a probability sensing model that is more in line with the actual situation. By introducing the radius fluctuation value, this model believes that the sensing range of the sensor node will fluctuate with environmental factors, and its sensing probability will decay in a negative exponential trend as the Euclidean distance between the monitoring point and the sensor node increases. As a result, the data model constructed by the technical solution of the present invention for the coverage optimization problem is more matched with environmental factors and the attributes of sensor nodes, ultimately improving the overall accuracy of the feasible solution.

[0030] In the probability sensing model, 1 represents 100%, regarded as the monitoring point can be sensed by the sensor, that is, it means that within the range less than or equal to r - re is the range that will definitely be monitored by the sensor; while for the range greater than r + re, the corresponding sensing probability is 0, indicating that the sensor node cannot sense the range greater than r + re; therefore, whether the detection points within the range less than or equal to r - re and greater than r + re can be monitored by the sensor node is determined; however, for other ranges except this, it means that a certain point has a probability of being monitored. For example, there is a 60% probability of being monitored. Generally, a random number is taken within (0 - 100%), if the random number <= 60%, it is considered that this point is monitored; if the random number > 60%, then it is not monitored by this sensor. Since the above content is all about the probability sensing model, no more detailed explanation is given here. It should be understood that based on the sensing probability between the sensor node and the monitoring point, the coverage rate of the monitoring area can be accurately calculated.

[0031] Further preferably, if a certain feasible solution has not been successfully updated for limit times, in the scouting bee stage, a global neighborhood search mechanism is used to update the feasible solution, where limit is a dynamic threshold;

[0032] The formula for the dynamic threshold limit is as follows:

[0033] limit = 200·(FEs / MaxFEs)

[0034] Wherein, FEs is the current number of evaluations. That is, each time a feasible solution is updated, the current number of evaluations is incremented by one. MaxFEs is the maximum number of evaluations, which is set in the initialization process of the multi-strategy artificial bee colony algorithm.

[0035] The setting method of the fixed threshold limit is difficult to meet the requirements in different optimization states to a certain extent. In the early stage of iteration, the algorithm should have strong global search ability. Setting limit smaller can increase the triggering frequency of this mechanism. In the middle and late stages of iteration, it should be biased towards the local search ability of the problem, and the threshold limit needs to be set larger to reduce the triggering frequency of this mechanism. Therefore, the technical solution of the present invention dynamically adjusts the parameter limit to make it increase continuously with iteration. It is worth noting that the minimum value of limit is preferably not less than 20 to avoid destroying the balance between the exploration and exploitation capabilities of the algorithm and ensure that the algorithm has good search performance.

[0036] Further preferably, the global neighborhood search mechanism is expressed as follows:

[0037] TX i = r 1 ·X i + r 2 ·X best + r 3 ·(X j - X k )

[0038] Wherein, r 1 , r 2 and r 3 are random numbers in the interval [0, 1], and satisfy r 1 + r 2 + r 3 = 1. X j and X k are two random individuals in the population, X i ≠ X j ≠ X k , and X best is the current optimal feasible solution in the population.

[0039] Further preferably, in both the employed bee stage and the observing bee stage, a new feasible solution that is worse than the current feasible solution is accepted with probability p m . Wherein, the probability p m is set as:

[0040] p m = 0.1*(FEs / MaxFEs)

[0041] Among them, FEs is the current number of evaluations. That is, every time a feasible solution is updated, the current number of evaluations is incremented by one. MaxFEs is the maximum number of evaluations, which is set in the initialization process of the multi-strategy artificial bee colony algorithm.

[0042] The technical solution of the present invention combines the idea of simulated annealing and accepts a slightly worse feasible solution with a certain probability, which helps the algorithm to jump out of the local optimum.

[0043] In a second aspect, the present invention provides a system based on the deployment method, which includes: an approximate optimal solution solving module and a deployment module;

[0044] The approximate optimal solution solving module is used to solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area by using the multi-strategy artificial bee colony algorithm to obtain an approximate optimal solution;

[0045] The deployment module is used to deploy sensor nodes in the monitoring area with the approximate optimal solution;

[0046] The coverage optimization problem is: the sensor node deployment problem that maximizes the network coverage rate in the monitoring area. Among them, the monitoring area is discretized into M×N monitoring points, and the number of sensor nodes to be deployed is D, where D is a positive integer, and each solution corresponds to a sensor node deployment result;

[0047] In the process of solving the coverage optimization problem by using the multi-strategy artificial bee colony algorithm, the feasible solution corresponding to each population individual is the sensor node deployment result of the coverage optimization problem; among them, an initial population is randomly generated first to obtain an initial feasible solution, and then the feasible solution corresponding to the population individual is iteratively updated, and the optimal feasible solution after meeting the iteration termination condition is regarded as the approximate optimal solution;

[0048] Each round of iterative update is to sequentially execute the feasible solution update in the employed bee, onlooker bee, and scout bee stages; and in the employed bee stage, each employed bee randomly selects a search strategy from the multi-strategy pool, and then uses the search strategy to update the corresponding feasible solution, and then accumulates the improvement amount corresponding to each search strategy when the feasible solution is successfully updated, so that in the onlooker bee stage, the feasible solution in the onlooker bee stage is updated with the search strategy with the largest improvement amount in the employed bee stage; the multi-strategy pool includes two or more search strategies.

[0049] In a third aspect, the present invention provides an electronic terminal, which at least includes:

[0050] One or more processors;

[0051] A memory storing one or more computer programs;

[0052] Among them, the processor calls the computer program to implement:

[0053] Steps of a method for deploying sensor nodes in a wireless sensor network.

[0054] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which is called by a processor to implement:

[0055] Steps of a method for deploying sensor nodes in a wireless sensor network.

[0056] Beneficial effects

[0057] 1. The deployment method provided by the technical solution of the present invention introduces the artificial bee colony algorithm to optimize the deployment of sensor nodes in a wireless sensor network, and optimizes the artificial bee colony algorithm. It creatively proposes to construct a multi-strategy pool, provides a variety of search strategies, gives full play to the complementary advantages of different strategies, and strengthens the optimization performance of the algorithm through the complementary advantages between strategies, further improving the accuracy of feasible solutions and maximizing the coverage rate under the wireless sensor network. In addition, during the employed bee phase, the improvement amount corresponding to each search strategy when successfully updating the feasible solution is accumulated, and then in the onlooker bee phase, the search strategy with the largest improvement amount Δ i is greedily selected as the search strategy in this phase to update the feasible solution, enabling the onlooker bee phase to find better feasible solutions, thereby improving the algorithm accuracy.

[0058] 2. In order to improve / solve the problem that the existing algorithm falls into local optimum, the technical solution of the present invention is further improved from multiple perspectives, including constructing a multi-strategy pool, and preferably selecting 4 search strategies with different characteristics, including three search strategies with strong local search capabilities and one search strategy with strong global search capabilities, thereby strengthening the local search and global search capabilities; also, by dynamically adjusting the parameter limit to make it increase continuously with iteration, and in the employed bee phase and the onlooker bee phase, accepting new feasible solutions that are worse than the current feasible solution with probability p m both contribute to the algorithm jumping out of local optimum and improving the algorithm accuracy.

[0059] 3. The technical solution of the present invention further adopts a probability perception model that is more in line with the actual scenario for the data model of the coverage optimization problem. By introducing a radius fluctuation value, this model believes that the sensing range of sensor nodes will fluctuate with environmental factors, and its sensing probability will decay in a negative exponential trend as the Euclidean distance between the monitoring point and the sensor node increases, so that the data model constructed by the technical solution of the present invention for the coverage optimization problem is more matched with environmental factors and the attributes of sensor nodes, ultimately improving the overall accuracy of feasible solutions. Description of the drawings

[0060] Figure 1It is a schematic flow chart of the multi-strategy artificial bee colony algorithm provided by the present invention;

[0061] Figure 2 It is a sensor distribution diagram of the test scenario provided by the example of the present invention;

[0062] Figure 3 It is the convergence curves of different algorithms for WSN coverage optimization in a 40m×40m scenario. The algorithm categories include SaMABC, PSO, ABC, GABC, GBABC, ABCVSS, ECABC, and NABC of the present invention;

[0063] Figure 4 It is the convergence curves of different algorithms for WSN coverage optimization in a 50m×50m scenario. The algorithm categories include SaMABC, PSO, ABC, GABC, GBABC, ABCVSS, ECABC, and NABC of the present invention;

[0064] Figure 5 It is the convergence curves of different algorithms for WSN coverage optimization in a 100m×100m scenario. The algorithm categories include SaMABC, PSO, ABC, GABC, GBABC, ABCVSS, ECABC, and NABC of the present invention;

[0065] Figure 6 They are the deployment results of sensor nodes of different algorithms. Among them, Figures (a) to (i) respectively correspond to the initialization, PSO optimized deployment result, ABC optimized deployment result, GABC optimized deployment result, GBABC optimized deployment result, ABCVSS optimized deployment result, ECABC optimized deployment result, NABC optimized deployment result, and the SaMABC optimized deployment result of the present invention. Detailed implementation manners

[0066] A method for deploying sensor nodes in a wireless sensor network provided by the present invention is a technical means for optimizing the coverage of sensor nodes and is used to determine the deployment of sensor nodes in a monitoring area. The present invention aims at maximizing the coverage rate, introduces the artificial bee colony algorithm, optimizes the algorithm according to the characteristics of the wireless sensor network, constructs a multi-strategy artificial bee colony algorithm, provides multiple search strategies for selection, and accumulates the improvement amounts corresponding to each search strategy when successfully updating the feasible solution, and selects the search strategy in the observation bee stage with the maximum improvement amount to update the feasible solution, effectively improving the network coverage rate, helping the algorithm to jump out of the local optimum, and obtaining a better deployment scheme. The present invention will be further described below in conjunction with embodiments.

[0067] Embodiment 1:

[0068] A deployment method for sensor nodes in a wireless sensor network provided by this embodiment includes the following steps:

[0069] Step 1: Use the multi-strategy artificial bee colony algorithm to solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area to obtain an approximate optimal solution.

[0070] In this embodiment, the length of the monitoring area A is M meters and the width is N meters, and there are M×N monitoring points inside. That is, for the two-dimensional plane supervision area A, the monitoring area A is numerically discretized into M×N monitoring points, and each monitoring point has a corresponding position coordinate.

[0071] Among them, the coverage optimization problem is: for D sensor nodes to be deployed, it is a sensor node deployment problem that maximizes the network coverage rate in the monitoring area. That is, it is essentially an NP-hard problem. First, it is converted into a solvable objective function, and then an optimization algorithm is used to solve the coverage optimization problem.

[0072] The implementation process of Step 1 includes:

[0073] Step 1-1: Perform initialization settings on the multi-strategy artificial bee colony algorithm, including at least setting the population size, the maximum number of evaluations, the initial value of the improvement amount, and randomly generating an initial feasible solution for each individual in the solution search space.

[0074] Specifically, in this embodiment, the population size SN is 50, and each individual corresponds to a feasible solution to the coverage optimization problem (in this embodiment, both the employed bees and the observing bees are SN; the scout bee is when a feasible solution fails to be improved after limit times, and the related employed bee or observing bee will turn into a scout bee, responsible for resetting the feasible solution. Therefore, the scout bee is basically 1 each time and will immediately turn back into an employed bee or an observing bee). A feasible solution represents a deployment plan of wireless sensor nodes in the monitoring area A. The dimension of the coverage optimization problem is set to D, that is, D corresponds to the number of sensor nodes to be deployed. The maximum number of evaluations MaxFEs is 300000 times; p m is set to 0.1*(FEs / MaxFEs), where FEs is the current number of evaluations; the initial values of the improvement amount values Δ i of all search strategies are all set to 0. The solution search space is preset or determined by other existing algorithms, and the present invention does not specifically limit this.

[0075] It should be noted that the present invention characterizes the coverage rate as fitness. The larger the fitness value (coverage rate), the better the quality of the feasible solution corresponding to the individual. That is, the deployment plan is evaluated by the fitness value.

[0076] To set up the fitness function, first understand the coverage rate. The present invention characterizes the data model of the coverage optimization problem with a probability perception model. By introducing a radius fluctuation value, this model assumes that the sensing range of sensor nodes fluctuates with environmental factors, and its sensing probability decays in a negative exponential trend as the Euclidean distance between the monitoring point and the sensor node increases. The sensing probability P of the probability perception model S,Q The calculation formula is as follows:

[0077]

[0078] where P S,Q is the sensing probability between the sensor node and the monitoring point, S represents the central position of the sensor node, Q represents the monitoring point in the monitoring area, and λ 1 = r e - r + d(S,Q), λ 2 = r e + r - d(S,Q), and λ 1 , λ 2 are both defined intermediate parameters. r e is the radius fluctuation value of the uncertain detection ability of the sensor node (the r e value is a predetermined fixed value, which varies according to different scenarios. In the present invention, simulation experiments are carried out in three wireless sensor network scenarios, and the configuration parameters are shown in Table 1 below), r is the sensing radius of the sensor node, d(S,Q) is the Euclidean distance calculated between S and Q, and α e 1 , α 2 , β 1 , β 2 x are the attenuation coefficients of the sensing probability, and e is the natural logarithm base.

[0079]

[0080] where S x , S y and Q x , Q y respectively represent the abscissa and ordinate of the sensor node S and the monitoring point Q in the two-dimensional plane.

[0081] Table 1 Parameter Configuration in Wireless Sensor Network Scenarios

[0082]

[0083] Then, the coverage rate of the monitoring area A is determined using the sensing probability:

[0084]

[0085] where CR AIt represents the coverage rate of the monitoring area A. P{i} is the set of sensing probabilities of the points covered by sensor node i. U represents the union in the set. It means incorporating the value of the i-th in the total D into the set. It represents the set of detectable points within the monitoring area by D sensor nodes, that is, by checking one by one for the M×N detection points whether they can be sensed by the D sensors. According to the probability sensing formula P S,Q to determine whether a certain detection point is monitored by the D sensors. The ratio of the detectable points to the area of the monitoring area is the coverage rate.

[0086] Step 1-2: Based on the multi-strategy artificial bee colony algorithm, iteratively update the feasible solutions of the population individuals until the iteration termination condition is satisfied to obtain an approximate optimal solution. Among them, each round of iteration sequentially performs the update of the feasible solutions in the employed bee, onlooker bee, and scout bee stages. The specific process is as follows:

[0087] One: First, judge whether the employed bee stage is completely finished, that is, each employed bee performs a search and update based on this step. If not, the corresponding employed bee randomly selects a search strategy from the multi-strategy pool and uses the selected search strategy to update the feasible solution X of the current individual i , if the updated feasible solution V i is better than the current feasible solution X i , replace the old solution X with the new feasible solution V i , and accumulate the value of the improvement amount Δ of the successful update using this search strategy i ; if it is worse than the current feasible solution X i , accept the solution V that is slightly worse than the current feasible solution X with a certain probability p i . If the employed bee stage is completed, execute the onlooker bee stage. m i i .

[0088] Among them, the improvement amount represents the degree of optimization. Therefore, in this embodiment, the fitness is directly used as the standard, and the corresponding calculation formula is as follows. In other feasible embodiments, other reference quantities representing fitness improvement and algorithm improvement can be set with reference to the fitness.

[0089]

[0090] The multi-strategy pool involved in this step has two or more search strategies. In this embodiment, 4 search strategies with different characteristics are set, that is, three search strategies with strong local search capabilities and one search strategy with strong global search capabilities. It is expected to strengthen the optimization performance of the algorithm through the principle of complementing advantages and disadvantages among the strategies. The search strategies in the multi-strategy pool are represented as follows:

[0091] ​​

[0092] In the formula, X i is the parent individual, corresponding to the feasible solution before update; V i is the offspring individual, corresponding to the feasible solution after update; X k and X t are the feasible solutions corresponding to a random individual in the population, and X i ≠X k ≠X t ; the parameter K is a variable coefficient that changes with iteration, and is a random number uniformly distributed in [-1.5, 1.5], FEs is the current number of evaluations, that is, each time the feasible solution is updated, the current number of evaluations is incremented by one, MaxFEs is the maximum number of evaluations, gaussian(δ 1 , |δ 2 |) is the Gaussian distribution function, δ 1 is the central region of the Gaussian distribution, δ 2 is the perturbation range, and X best is the current optimal solution in the population.

[0093] Second: In the observing bee stage, determine whether the observing bee stage is completely finished, that is, each observing bee with a size of SN conducts a search and update based on this step once. If not finished, the observing bee greedily selects the search strategy with the largest improvement amount Δ i recorded in the employed bee stage as the search strategy for this stage to update X i . If the updated feasible solution V i is better than the current feasible solution X i , replace the old solution X i with the new feasible solution V i . If it is worse than the current feasible solution X i , accept the solution V m that is slightly worse than the current feasible solution X i with a certain probability p i . If the employed bee stage has been completed, execute the scout bee stage.

[0094] Third: In the scout bee stage, determine whether the scout bee stage is completely finished, that is, scan all (SN) individuals in the entire population to check if there is a bee that has not been successfully updated for limit times. If not finished, when the feasible solution X i has not been successfully updated for limit times through the dynamic threshold, then use the global neighborhood search mechanism to update it; otherwise, execute the next step to determine whether the iteration termination condition is currently met.

[0095] Among them, a dynamic threshold limit is set to prevent the algorithm from falling into a search stagnation state. And to avoid disrupting the balance between the exploration and exploitation capabilities of the algorithm and ensure good search performance of the algorithm, the minimum value of limit shall not be lower than 20. The specific calculation is as follows:

[0096] limit = 200·(FEs / MaxFEs)

[0097] The global neighborhood search mechanism learns historical search experiences to find a better-quality feasible solution. The global neighborhood search mechanism is as follows:

[0098] TX i = r 1 ·X i + r 2 ·X best + r 3 ·(X j - X k )

[0099] Among them, r 1 , r 2 and r 3 are random numbers in the interval [0, 1], and satisfy r 1 + r 2 + r 3 = 1. X j and X k are two random individuals in the population, X i ≠ X j ≠ X k .

[0100] Four: Determine whether the iteration termination condition is satisfied. If it is satisfied, output the approximate optimal solution; if not, continue the iteration and enter the next employed bee stage. That is, the approximate optimal solution is the feasible solution with the largest current fitness value.

[0101] In this embodiment, when FEs <= MaxFEs, it is regarded as not yet satisfying the iteration termination condition, and what is satisfied is the iteration condition. FEs is the current evaluation times. Whenever any individual (feasible solution) in the population undergoes an initialization or update operation and the fitness value is recalculated, the current evaluation times FEs is incremented by one.

[0102] Step 4: Deploy sensor nodes in the monitoring area with the approximate optimal solution.

[0103] In summary, the deployment method provided by the present invention optimizes the update of feasible solutions in the employed bee and observing bee stages by constructing a multi-strategy pool and cumulative improvement amount. In addition, a dynamic threshold limit is set and a solution V i that is slightly worse than the current feasible solution X i, which helps the algorithm jump out of the local optimum and improve the reliability of the approximate optimal solution obtained by the algorithm.

[0104] Embodiment 2:

[0105] Based on the deployment method provided in Embodiment 1, this embodiment further provides a system based on the deployment method, which includes: an approximate optimal solution solving module and a deployment module.

[0106] The approximate optimal solution solving module is used to solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area by using the multi-strategy artificial bee colony algorithm to obtain an approximate optimal solution; the deployment module is used to deploy sensor nodes in the monitoring area with the approximate optimal solution.

[0107] Among them, the coverage optimization problem is: for D sensor nodes to be deployed, it is a sensor node deployment problem that maximizes the network coverage rate in the monitoring area. In the process of using the multi-strategy artificial bee colony algorithm to solve the coverage optimization problem, the feasible solution corresponding to each population individual is the sensor node deployment result of the coverage optimization problem.

[0108] Among them, the approximate optimal solution solving module includes: an initialization module and an update module. The initialization module is used to perform initialization settings on the multi-strategy artificial bee colony algorithm, at least including setting the population size, the maximum number of evaluations, the initial value of the improvement amount, and randomly generating an initial feasible solution for the population individuals in the solution search space; the update module is used to iteratively update the feasible solutions of the population individuals based on the multi-strategy artificial bee colony algorithm until the iteration termination condition is met to obtain an approximate optimal solution, where each round of iteration is to sequentially execute the feasible solution update in the employed bee, onlooker bee, and scout bee stages.

[0109] In the employed bee stage, each employed bee randomly selects a search strategy from the multi-strategy pool, then uses the search strategy to update the corresponding feasible solution, and then accumulates the improvement amount corresponding to when each search strategy successfully updates the feasible solution. Among them, the multi-strategy pool includes two or more search strategies. When the fitness of the new feasible solution is better than the current feasible solution, it is considered that the corresponding search strategy successfully updates the feasible solution and replaces the current feasible solution with the new feasible solution; in the onlooker bee stage, the current feasible solution is updated with the search strategy with the largest improvement amount in the employed bee stage.

[0110] For the specific implementation process of each module, please refer to the content of the above method and will not be elaborated here. It should be understood that the above division of functional modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. At the same time, the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0111] Example 3:

[0112] This embodiment provides an electronic terminal, which at least includes: one or more processors; and a memory storing one or more computer programs.

[0113] Wherein, the processor calls the computer program to implement: the steps of a method for deploying sensor nodes in a wireless sensor network.

[0114] Specifically, the following steps are executed:

[0115] Step 1: Use the multi-strategy artificial bee colony algorithm to solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area to obtain an approximate optimal solution;

[0116] Step 2: Then deploy sensor nodes in the monitoring area with the approximate optimal solution;

[0117] The coverage optimization problem is: the sensor node deployment problem that maximizes the network coverage rate in the monitoring area. The number of sensor nodes to be deployed is D, and D is a positive integer; in the process of using the multi-strategy artificial bee colony algorithm to solve the coverage optimization problem, the feasible solution corresponding to each population individual is the sensor node deployment result of the coverage optimization problem.

[0118] Among them, the process of Step 1 is as follows:

[0119] Step 1-1: Perform initialization settings on the multi-strategy artificial bee colony algorithm, including at least setting the population size, the maximum number of evaluations, the initial value of the improvement amount, and randomly generating an initial feasible solution for the population individuals in the solution search space;

[0120] Step 1-2: Based on the multi-strategy artificial bee colony algorithm, iteratively update the feasible solutions of the population individuals until the iteration termination condition is met to obtain an approximate optimal solution. Among them, each round of iteration is to sequentially execute the feasible solution update in the employed bee, onlooker bee, and scout bee stages.

[0121] Among them, the process of each round of iteration is as follows:

[0122] One: First, determine whether the employed bee stage is all completed, that is, each employed bee performs a search and update based on this step. If not completed, the corresponding employed bee randomly selects a search strategy from the multi-strategy pool and uses the selected search strategy to update the current individual's feasible solution X i , if the updated feasible solution V i is better than the current feasible solution X i , use the new feasible solution V i to replace the old solution X i , and accumulate the value of the improvement amount Δ of the successful update using this search strategyi ; if it is inferior to the current feasible solution X i , with a certain probability p m accept a solution V that is slightly worse than the current feasible solution X i . If the employed bee stage is completed, execute the onlooker bee stage. i

[0123] II: In the onlooker bee stage, determine whether the onlooker bee stage is completely completed, that is, each onlooker bee with a quantity of SN conducts a search and update based on this step once. If it is not completed, the onlooker bee greedily selects the search strategy with the largest improvement amount Δ according to the improvement amount Δ of the search strategy recorded in the employed bee stage i as the search strategy for this stage to update X i . If the updated feasible solution V i is superior to the current feasible solution X i , replace the old solution X with the new feasible solution V i . If it is inferior to the current feasible solution X i , with a certain probability p i accept a solution V that is slightly worse than the current feasible solution X m . If the employed bee stage is completed, execute the scout bee stage. i i

[0124] III: In the scout bee stage, determine whether the scout bee stage is completely completed, that is, scan all (SN individuals) in the entire population and check whether there is a bee that has not been successfully updated after limit times. If it is not completed, when the feasible solution X i has not been successfully updated after the dynamic threshold limit times, then use the global neighborhood search mechanism to update it; otherwise, execute the next step to determine whether the current iteration termination condition is satisfied.

[0125] IV: Determine whether the iteration termination condition is satisfied. If it is satisfied, output the approximate optimal solution; if it is not satisfied, continue the iteration and enter the next employed bee stage. That is, the approximate optimal solution is the feasible solution with the largest current fitness value.

[0126] It should be understood that the implementation process of some steps, as well as whether some steps are executed and the execution order, can refer to the implementation process of the foregoing embodiments.

[0127] Among them, the memory may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0128] ​​​If the memory and the processor are implemented independently, the memory, the processor, and the communication interface can be interconnected through a bus to complete communication with each other. The bus can be an Industry Standard Architecture bus, a Peripheral Component Interconnect bus, an Extended Industry Standard Architecture bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like.

[0129] Optionally, in a specific implementation, if the memory and the processor are integrated on a single chip, the memory and the processor can complete communication with each other through an internal interface.

[0130] It should be understood that in the embodiments of the present invention, the so-called processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0131] Embodiment 4:

[0132] This embodiment provides a computer-readable storage medium that stores a computer program, and the computer program is called by a processor to implement the steps of a method for deploying sensor nodes in a wireless sensor network.

[0133] Specifically, the following steps are executed:

[0134] Step 1: Use a multi-strategy artificial bee colony algorithm to solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area to obtain an approximate optimal solution;

[0135] Step 2: Then deploy sensor nodes in the monitoring area with the approximate optimal solution;

[0136] The coverage optimization problem is: the sensor node deployment problem that maximizes the network coverage rate in the monitoring area. The number of sensor nodes to be deployed is D, and D is a positive integer. In the process of using the multi-strategy artificial bee colony algorithm to solve the coverage optimization problem, the feasible solution corresponding to each population individual is the sensor node deployment result of the coverage optimization problem.

[0137] Among them, the process of Step 1 is as follows:

[0138] Step 1-1: Initialize the multi-strategy artificial bee colony algorithm, including at least setting the population size, the maximum number of evaluations, the initial value of the improvement amount, and randomly generating an initial feasible solution for each individual in the population within the solution search space;

[0139] Step 1-2: Iteratively update the feasible solutions of the population individuals based on the multi-strategy artificial bee colony algorithm until the iteration termination condition is met to obtain an approximate optimal solution. Among them, in each round of iteration, the feasible solution updates in the employed bee, onlooker bee, and scout bee stages are executed in sequence.

[0140] Among them, the process of each round of iteration is as follows:

[0141] One: First, judge whether the employed bee stage is completely completed, that is, each employed bee performs a search and update based on this step. If not completed, the corresponding employed bee randomly selects a search strategy from the multi-strategy pool and uses the selected search strategy to update the feasible solution X i , if the updated feasible solution V i is better than the current feasible solution X i , replace the old solution X i with the new feasible solution V i , and accumulate the value of the improvement amount Δ that has been successfully updated using this search strategy i ; if it is worse than the current feasible solution X i , accept the solution V m that is slightly worse than the current feasible solution X i with a certain probability p i . If the employed bee stage has been completed, execute the onlooker bee stage.

[0142] Two: In the onlooker bee stage, judge whether the onlooker bee stage is completely completed, that is, each onlooker bee with a size of SN performs a search and update based on this step. If not completed, the onlooker bee greedily selects the search strategy with the largest improvement amount Δ i recorded in the employed bee stage as the search strategy for this stage to update X i , if the updated feasible solution V i is better than the current feasible solution X i , replace the old solution X i with the new feasible solution V i , if it is worse than the current feasible solution X i , accept the solution V m that is slightly worse than the current feasible solution X i with a certain probability p i . If the employed bee stage has been completed, execute the scout bee stage.

[0143] III: In the scout bee stage, determine whether the scout bee stage is completely finished, that is, scan all (SN) individuals in the entire population and check whether there is a bee that has not been successfully updated after limit times. If it is not finished, when the feasible solution X i has not been successfully updated after limit times by the dynamic threshold, then use the global neighborhood search mechanism to update it; otherwise, execute the next step to determine whether the current iteration termination condition is satisfied.

[0144] IV: Determine whether the iteration termination condition is satisfied. If it is satisfied, output the approximate optimal solution; if it is not satisfied, continue the iteration and enter the next employed bee stage. That is, the approximate optimal solution is the feasible solution with the largest current fitness value.

[0145] It should be understood that the implementation process of some steps, as well as whether some steps are executed and the execution order, can refer to the implementation process of the foregoing embodiments.

[0146] The readable storage medium is a computer-readable storage medium, which may be the internal storage unit of the controller described in any of the foregoing embodiments, such as the hard disk or memory of the controller. For example, the terrain element model constructed in the present invention exists in the hard disk, and then the computer program for executing the fusion step is stored in the memory, so that the fusion process is realized relying on the memory. The readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk equipped on the controller, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the readable storage medium may also include both the internal storage unit of the controller and the external storage device. The readable storage medium is used to store the computer program and other programs and data required by the controller. The readable storage medium may also be used to temporarily store the data that has been output or will be output.

[0147] Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the foregoing readable storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs and other various media that can store program codes.

[0148] Example:

[0149] The present invention is implemented using a Java program in the Eclipse platform and performance tests are conducted.

[0150] The experimental settings are as follows: The proposed SaMABC algorithm of the present invention is simulated and analyzed under three different WSN coverage scenarios, and the WSN coverage optimization problems under scenarios of 40m×40m, 50m×50m, and 100m×100m are solved. Figure 2 It is the sensor distribution diagram of the test scenario. Under the three WSN coverage optimization scenarios, the monitoring areas are square areas of 40m×40m, 50m×50m, and 100m×100m respectively, the number of sensors are 30, 40, and 50 respectively, and the sensing radii r of the sensors are set to 4m, 5m, and 10m respectively. The present invention is respectively compared and tested with 7 existing optimization algorithms (PSO, ABC, GABC, GBABC, ABCVSS, ECABC, NABC), and the deployed diagrams of sensor nodes after optimization by each algorithm are given.

[0151] Figure 3 It is the convergence curves of different algorithms for WSN coverage optimization under the 40m×40m scenario to further examine the performance differences of various algorithms. The present invention is named SaMABC. It can be seen from the results in the figure that SaMABC has achieved a very high coverage rate in the early stage, and its convergence speed is also the fastest among all algorithms, and the final coverage result reaches 85.38%. Compared with GBABC, as time goes by, the coverage range of SaMABC has been significantly improved, showing the strong ability of the algorithm to deviate from the local optimum. At the same time, ABCVSS is also an adaptive multi-strategy improvement algorithm, and SaMABC effectively proves the effectiveness of the improvement points proposed by the present invention, and its optimization effect is far better than it.

[0152] Figure 4 It is the convergence curves of different algorithms for WSN coverage optimization under the 50m×50m scenario. It can be seen from the results in the figure that the SaMABC algorithm has achieved a high coverage rate in the early stage, and its convergence speed is also the fastest among all algorithms, and the final coverage result reaches 95.48%. Similar improvements in the coverage rate are also shown in the middle and late stages of SaMABC, further proving the strong ability of the algorithm to break through local optimization.

[0153] Figure 5 It is the convergence curves of different algorithms for WSN coverage optimization under the 100m×100m scenario. It can be seen from the results in the figure that the coverage rate optimization of the SaMABC algorithm reaches 99% in 50,000 evaluations, with the highest solution accuracy and the fastest convergence speed, and the final coverage result reaches 99.05%. In addition, Figure 6The deployment locations of the original sensor nodes are also shown, as well as the final deployment diagrams after various algorithm optimizations. From Figure 6 it can be seen from the deployment diagrams in Figure 6 that the SaMABC in Figure (i) of

[0154] has a more uniform node deployment and a larger detection coverage area than other comparison algorithms. Although there is a very small uncovered area in SaMABC, in fact, the nearby sensor nodes can sense this area, showing the best coverage deployment scheme. In summary, the results of the three scenarios show that the SaMABC of the present invention has good competitiveness in WSN coverage and has good performance.

[0155] It should be emphasized that the examples described in the present invention are illustrative rather than restrictive. Therefore, the present invention is not limited to the examples described in the specific embodiments. Any other embodiments obtained by those skilled in the art according to the technical solutions of the present invention, whether modified or replaced, as long as they do not depart from the spirit and scope of the present invention, also belong to the protection scope of the present invention.

Claims

1. A deployment method for sensor nodes in a wireless sensor network, characterized in that: It includes the following steps: Step 1: Use the multi-strategy artificial bee colony algorithm to solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area to obtain an approximate optimal solution; Step 2: Then deploy sensor nodes in the monitoring area with the approximate optimal solution; The coverage optimization problem is: the sensor node deployment problem that maximizes the network coverage rate in the monitoring area; wherein, the monitoring area is discretized into M×N monitoring points, and the number of sensor nodes to be deployed is D, and D is a positive integer; In the process of using the multi-strategy artificial bee colony algorithm to solve the coverage optimization problem, the feasible solution corresponding to each population individual is the sensor node deployment result of the coverage optimization problem; wherein, first randomly generate an initial population to obtain an initial feasible solution, and then iteratively update the feasible solution corresponding to the population individual, and regard the optimal feasible solution after meeting the iteration termination condition as the approximate optimal solution; Each round of iterative update sequentially performs the update of the feasible solution in the employed bee, onlooker bee, and scout bee stages; and in the employed bee stage, each employed bee randomly selects a search strategy from the multi-strategy pool, and then uses the search strategy to update the corresponding feasible solution, and then accumulates the improvement amount corresponding to when each search strategy successfully updates the feasible solution, so that in the onlooker bee stage, the feasible solution in the onlooker bee stage is updated with the search strategy with the largest improvement amount in the employed bee stage; the multi-strategy pool includes two or more search strategies; Among them, the multi-strategy pool includes three local search strategies and one global search strategy, which are expressed as: Where X i is the parent individual, corresponding to the feasible solution before update; V i is the offspring individual, corresponding to the feasible solution after update; X k and X t are both the feasible solutions corresponding to a random individual in the population, and X i ≠X k ≠X t ; the parameter K is a variable coefficient that changes with iteration, and is a random number uniformly distributed in [-1.5, 1.5], FEs is the current number of evaluations, that is, each time the feasible solution is updated, the current number of evaluations is incremented by one, MaxFEs is the maximum number of evaluations, gaussian(δ 1 , |δ 2 |) is the Gaussian distribution function, δ 1 is the central region of the Gaussian distribution, δ 2 is the perturbation range, and X best is the current optimal feasible solution in the population; The fitness function of the multi-strategy artificial bee colony algorithm is the coverage rate of the monitoring area based on the sensing probability. The coverage optimization problem uses a probability sensing model, and the formula for the corresponding sensing probability is as follows: Among them, P S,Q is the perception probability between the sensor node and the monitoring point, S represents the central position of the sensor node, Q represents the monitoring point in the monitoring area, λ 1 = r e - r + d(S, Q), λ 2 = r e + r - d(S, Q), λ 1 and λ 2 are both defined intermediate parameters, r e is the radius fluctuation value of the uncertain detection ability of the sensor node, r is the perception radius of the sensor node, d(S, Q) is the Euclidean distance calculated between S and Q, α 1 and α 2 , β 1 and β 2 are the attenuation coefficients of the perception probability, and e is the natural base.

2. The deployment method according to claim 1, characterized in that: In the process of each iterative update, when the fitness of the new feasible solution is better than the current feasible solution, the new feasible solution replaces the current feasible solution, wherein the formula of the fitness function is as follows: Among them, CR A represents the coverage rate of the monitoring area A, and P{i} is the set of sensing probabilities of the points covered by the sensor node i. represents the set of points that can be monitored by D sensor nodes within the monitoring area.

3. The deployment method according to claim 1, characterized in that: If a certain feasible solution has not been successfully updated for limit times, in the scout bee stage, a global neighborhood search mechanism is used to update the feasible solution, and limit is a dynamic threshold; The formula for the dynamic threshold limit is as follows: limit = 200·(FEs / MaxFEs) wherein, FEs is the current evaluation times, that is, each time the feasible solution is updated, the current evaluation times is incremented by one; MaxFEs is the maximum evaluation times, which is set by the initialization process of the multi-strategy artificial bee colony algorithm.

4. The deployment method according to claim 3, characterized in that: The global neighborhood search mechanism is expressed as follows: TX i = r 1 · X i + r 2 · X best + r 3 · (X j - X k ) Among them, TX i is the feasible solution updated based on the global domain search mechanism, r 1 , r 2 and r 3 are random numbers in the interval [0, 1], and satisfy r 1 + r 2 + r 3 = 1, X j and X k are the feasible solutions of two random individuals in the population, X i ≠ X j ≠ X k , X best is the current optimal feasible solution in the population.

5. The deployment method according to claim 1, characterized in that: In both the employed bee stage and the observing bee stage, a new feasible solution that is worse than the current feasible solution is accepted with probability p m where the probability p m is set to: p m = 0.1 * (FEs / MaxFEs) wherein, FEs is the current evaluation times, that is, each time the feasible solution is updated, the current evaluation times is incremented by one, and MaxFEs is the maximum evaluation times, which is set by the initialization process of the multi-strategy artificial bee colony algorithm.

6. A system based on the deployment method according to any one of claims 1-5, characterized in that: comprising: an approximately optimal solution solving module and a deployment module; the approximately optimal solution solving module is used to solve the coverage optimization problem of the wireless sensor network corresponding to the monitoring area by using a multi-strategy artificial bee colony algorithm to obtain an approximately optimal solution; the deployment module is used to deploy sensor nodes in the monitoring area with the approximately optimal solution; the coverage optimization problem is: the sensor node deployment problem that maximizes the network coverage rate in the monitoring area, where the monitoring area is discretized into M×N monitoring points, the number of sensor nodes to be deployed is D, D is a positive integer, and each solution corresponds to a sensor node deployment result; in the process of solving the coverage optimization problem by using the multi-strategy artificial bee colony algorithm, the feasible solution corresponding to each population individual is the sensor node deployment result of the coverage optimization problem; among them, an initial population is randomly generated to obtain an initial feasible solution, and then the feasible solution corresponding to the population individual is iteratively updated, and the optimal feasible solution after meeting the iteration termination condition is regarded as the approximately optimal solution; each round of iterative update sequentially performs the update of the feasible solution in the employed bee, onlooker bee, and scout bee stages; and in the employed bee stage, each employed bee randomly selects a search strategy from the multi-strategy pool, and then uses the search strategy to update the corresponding feasible solution, and then accumulates the improvement amount corresponding to when each search strategy successfully updates the feasible solution, so that in the onlooker bee stage, the feasible solution in the onlooker bee stage is updated with the search strategy with the largest improvement amount in the employed bee stage; the multi-strategy pool includes two or more search strategies.

7. An electronic terminal, characterized in that: at least comprising: one or more processors; a memory storing one or more computer programs; wherein, the processor calls the computer program to implement: the steps of the deployment method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: stores a computer program, and the computer program is called by a processor to implement: the steps of the deployment method according to any one of claims 1-5.

Images