WSN coverage optimization method, device, equipment and medium based on improved dung beetle algorithm

Abstract

The present application discloses a WSN coverage optimization method, apparatus, device and medium based on an improved dung beetle algorithm, which relates to the field of wireless communication technology. The method comprises: initializing algorithm parameters and setting a maximum number of iterations, initializing a population using a sinusoidal chaotic mapping strategy, calculating individual fitness values, determining preset individual positions, updating individual positions using a vertical and horizontal crossover and random inertia weight strategy, and finally outputting an optimization result and generating a WSN coverage plan, thereby improving global search capability and optimization accuracy, effectively avoiding local optimality, and improving network coverage and node energy efficiency.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a WSN coverage optimization method, device, equipment and medium based on an improved dung beetle algorithm. Background Art

[0002] With the development of the Internet of Things (IoT), wireless sensor networks (WSNs) have gained widespread application in a variety of fields, including environmental monitoring, smart cities, and industrial automation. WSNs consist of a large number of low-cost, low-power sensor nodes that collaborate via wireless communication to sense, collect, and process information from their deployment area and transmit the data to users or data centers. However, how to effectively deploy these sensor nodes to cover the entire target industrial area and ensure long-term stable network operation has become a critical research topic. This challenge is particularly complex in heterogeneous WSNs, where different sensor types have varying characteristics (such as sensing range and communication capabilities).

[0003] Current technologies have made considerable progress. Traditional optimization methods include those based on mathematical programming, genetic algorithms, and particle swarm optimization. In recent years, metaheuristic algorithms inspired by biological behavior in nature, such as the ant colony algorithm and the bee colony algorithm, have also been widely used to solve WSN coverage optimization problems. These algorithms attempt to mimic the collective intelligence of nature to find optimal or near-optimal solutions, thereby improving network coverage, reducing energy consumption, and extending network lifespan. Among them, the dung beetle optimization algorithm (DBO) has attracted attention for its excellent solution accuracy and convergence speed. However, when dealing with complex optimization problems, traditional DBO algorithms are prone to getting stuck in local optimal solutions and lack global search capabilities. Furthermore, many algorithms lack effective mechanisms to balance exploration and exploitation, resulting in low search efficiency. Furthermore, some existing methods fail to fully account for the heterogeneous nature of WSNs, namely the differences between different sensor types, which can lead to suboptimal deployment solutions. Finally, existing algorithms often lack sufficient adaptability and flexibility to dynamically changing environmental conditions, such as node failures and moving obstacles, making it difficult to adjust optimization strategies in real time. Therefore, there is an urgent need for optimization methods to improve the coverage and performance of WSNs. Summary of the Invention

[0004] The main purpose of this application is to provide a WSN coverage optimization method, device, equipment and medium based on the improved dung beetle algorithm, aiming to solve the technical problem of how to achieve more efficient and energy-saving WSN coverage optimization.

[0005] To achieve the above objectives, this application proposes a WSN coverage optimization method based on an improved dung beetle algorithm, the method comprising:

[0006] Obtain initial data on WSN coverage in industrial areas;

[0007] Optimizing the initial data according to a preset WSN coverage optimization model to obtain an optimization result, wherein the preset WSN coverage optimization model is constructed based on an improved dung beetle algorithm;

[0008] Obtaining a target WSN coverage solution based on the optimization result;

[0009] Before the step of optimizing the initial data according to the preset WSN coverage optimization model to obtain the optimization result, the method includes:

[0010] Initializing algorithm parameters and setting the maximum number of iterations, wherein the algorithm parameters include coverage target and node average moving distance target;

[0011] The Sinusoidal chaotic mapping strategy is used to initialize the dung beetle population;

[0012] Calculating the dung beetle population to obtain fitness values ​​of multiple individuals;

[0013] Obtaining a first preset individual position and a second preset individual position based on a comparison of the plurality of fitness values;

[0014] Adopt the vertical and horizontal cross strategy and random inertia weight strategy to update the individual positions in the population and obtain the updated individual positions;

[0015] Calculating according to the updated individual position based on the first preset individual position and the second preset individual position to obtain a target individual fitness value and a corresponding target position;

[0016] If the maximum number of iterations is reached, the target individual fitness value and the corresponding target position are output as the optimization result.

[0017] In one embodiment, the step of initializing the dung beetle population using the Sinusoidal chaotic mapping strategy includes:

[0018] Set the chaos map parameters and define the initial values;

[0019] According to the chaotic mapping formula, the chaotic sequence is generated by iteration according to the number of chaotic iterations. The specific formula is:

[0020] ;

[0021] in, represents the chaos parameter, , the number of chaotic iterations is the same as the maximum number of iterations;

[0022] The chaotic sequence is linearly mapped to the target industrial area to generate an initial dung beetle population.

[0023] In one embodiment, the step of adopting the vertical and horizontal cross strategy and the random inertia weight strategy to update the individual positions in the population to obtain the updated fitness value and the corresponding individual position includes:

[0024] Performing a crossover operation according to a horizontal crossover strategy to update the positions of the ball-pushing dung beetles and the breeding dung beetles in the population, generating first-generation offspring individuals that meet preset retention requirements, and obtaining the individual positions of the ball-pushing dung beetles and the breeding dung beetles;

[0025] Performing mutation operations in different dimensions according to a vertical crossover strategy, updating the positions of the small dung beetles in the population, generating second-generation individuals that meet preset retention requirements, and obtaining the individual positions of the small dung beetles;

[0026] The positions of the thieving dung beetles in the population are updated according to a random inertia weight strategy, a third generation of individuals that meet preset retention requirements are generated, and the individual positions of the thieving dung beetles are obtained.

[0027] In one embodiment, the step of performing a crossover operation according to a horizontal crossover strategy, updating the positions of the ball-pushing dung beetles and the breeding dung beetles in the population, generating first-generation offspring individuals that meet preset retention requirements, and obtaining the individual positions of the ball-pushing dung beetles and the breeding dung beetles includes:

[0028] selecting two ball-pushing dung beetles or two breeding dung beetles as parent individuals based on the population;

[0029] Perform a horizontal crossover operation on the parent individual to obtain the first individual and the second individual. The specific formula is:

[0030] ;

[0031] in, There are two parent individuals, Indicates the The first and second bodies of the dimension, is a random number in [0, 1], is a random number within [-1, 1];

[0032] Calculating and comparing the fitness values ​​of the first individual and the second individual with the fitness value of the parent individual, and retaining the individual with the larger fitness value;

[0033] When the position updates of all the dung beetles and breeding dung beetles in the population are completed, the individuals with larger fitness values ​​at this time are output as the first offspring individuals and the corresponding individual positions of the dung beetles and breeding dung beetles.

[0034] In one embodiment, the step of performing mutation operations in different dimensions according to the vertical crossover strategy, updating the positions of the small dung beetles in the population, generating second-generation individuals that meet preset retention requirements, and obtaining the individual positions of the small dung beetles includes:

[0035] selecting two initial dung beetle individuals of different dimensions based on the population;

[0036] A vertical crossover operation is performed on the small dung beetle individual to obtain a third individual. The specific formula is:

[0037] ;

[0038] in, are the initial dung beetle individuals in two different dimensions. is a random number in [0, 1];

[0039] Calculating the fitness value of the third individual and comparing it with the fitness value of the initial small dung beetle individual;

[0040] When the fitness value of the third individual is larger, the position of the initial small dung beetle individual is replaced, otherwise the position of the initial small dung beetle individual is maintained;

[0041] The individual with the larger fitness value at this time is output as the second offspring individual and the individual position of the corresponding small dung beetle, until the position update of all small dung beetles in the population is completed.

[0042] In one embodiment, the step of updating the positions of the thieving dung beetles in the population according to the random inertia weight strategy, generating third-generation individuals that meet preset retention requirements, and obtaining the individual positions of the thieving dung beetles includes:

[0043] Get the current number of iterations and the maximum number of iterations, and get the iteration progress ratio;

[0044] The random inertia weight is calculated based on the iterative progress ratio, and the formula is:

[0045] ;

[0046] in, are the upper and lower limits of the inertia weight, is the iteration progress ratio, is a random number in [0, 1];

[0047] The position of the stealing dung beetle is updated according to the random inertia weight to obtain the fourth individual. The specific formula is:

[0048] ;

[0049] in, is the current local optimal position, is the global optimal position, is a constant, is a random vector that follows a normal distribution;

[0050] When the fitness value of the fourth individual is larger, the position of the stealing dung beetle individual is replaced, otherwise the position of the stealing dung beetle individual is maintained;

[0051] The individual with the larger fitness value at this time is output as the third offspring individual and the individual position of the corresponding thieving dung beetle, until the position update of all thieving dung beetles in the population is completed.

[0052] In one embodiment, the step of obtaining a target WSN coverage solution according to the optimization result includes:

[0053] generating a deployment plan for sensor nodes according to the optimization results;

[0054] Applying the deployment scheme to the target industrial area to achieve optimized deployment of sensor nodes;

[0055] Calculating the network coverage rate and the average moving distance of the nodes after the optimized deployment to obtain an optimization result;

[0056] Perform verification according to the optimization result to obtain a verification result;

[0057] When the verification result shows that the optimization result meets the preset optimization requirement, the optimization process is completed and the deployment plan is output as the target WSN coverage plan.

[0058] In addition, the present application also proposes a WSN coverage optimization device based on an improved dung beetle algorithm, the device comprising:

[0059] An acquisition module is used to obtain initial data of WSN coverage in an industrial area, wherein the initial data includes the industrial area boundary, the number of sensor nodes, the node sensing radius, and the communication radius;

[0060] An optimization module, configured to optimize the initial data according to a preset WSN coverage optimization model to obtain an optimization result, wherein the preset WSN coverage optimization model is constructed based on an improved dung beetle algorithm;

[0061] A result module, configured to obtain a target WSN coverage solution based on the optimization result;

[0062] A construction module is provided for initializing algorithm parameters and setting a maximum number of iterations, wherein the algorithm parameters include a coverage rate target and a node average moving distance target; a dung beetle population is initialized using a sinusoidal chaotic mapping strategy; the dung beetle population is calculated to obtain fitness values ​​of a plurality of individuals; a first preset individual position and a second preset individual position are obtained by comparing the plurality of fitness values; individual positions in the population are updated using a vertical and horizontal cross strategy and a random inertia weight strategy to obtain updated individual positions; a target individual fitness value and a corresponding target position are calculated based on the first and second preset individual positions according to the updated individual positions; if the maximum number of iterations is reached, the target individual fitness value and the corresponding target position are output as an optimization result.

[0063] In addition, to achieve the above objectives, the present application also proposes a medium, which is a computer-readable medium and stores a computer program. When the computer program is executed by a processor, the steps of the WSN coverage optimization method based on the improved dung beetle algorithm as described above are implemented.

[0064] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the WSN coverage optimization method based on the improved dung beetle algorithm as described above.

[0065] This application initializes the algorithm parameters and sets the maximum number of iterations, uses the Sinusoidal chaotic mapping strategy to initialize the population, calculates the individual fitness value, determines the preset individual position, and uses the vertical and horizontal cross and random inertia weight strategies to update the individual position. Finally, it outputs the optimization results and generates a WSN coverage plan, which improves the global search capability and optimization accuracy, effectively avoids local optimality, and improves network coverage and node energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0067] Figure 1 This is a flow chart of the first embodiment of the WSN coverage optimization method based on the improved dung beetle algorithm of this application;

[0068] Figure 2 This is a graph showing the relationship between network coverage and the number of nodes in the first embodiment of the WSN coverage optimization method based on the improved dung beetle algorithm of this application;

[0069] Figure 3 This is a graph showing the relationship between the average node movement distance and the number of nodes in the first embodiment of the WSN coverage optimization method based on the improved dung beetle algorithm of this application;

[0070] Figure 4 This is a flow chart of the second embodiment of the WSN coverage optimization method based on the improved dung beetle algorithm of this application;

[0071] Figure 5 This is a flow chart of the third embodiment of the WSN coverage optimization method based on the improved dung beetle algorithm of this application;

[0072] Figure 6 This is a schematic diagram of the module structure of a WSN coverage optimization device based on an improved dung beetle algorithm according to the first embodiment of the WSN coverage optimization method based on the improved dung beetle algorithm of the present application;

[0073] Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the WSN coverage optimization method based on the improved dung beetle algorithm in the embodiment of the present application.

[0074] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0075] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0076] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0077] In today's era of rapid information and intelligent development, wireless sensor networks (WSNs), as a key component of the Internet of Things (IoT), are being widely used in a variety of fields, including environmental monitoring, smart cities, industrial automation, and agricultural monitoring. WSNs utilize a large number of distributed, low-cost, low-power sensor nodes to monitor and collect data on physical or environmental conditions (such as temperature, humidity, and pressure) within a specific area in real time, transmitting this information to users or data centers for analysis and decision-making. However, the key challenge is how to efficiently deploy these sensor nodes to ensure comprehensive coverage of the entire target industrial area while ensuring long-term stable network operation.

[0078] Therefore, this application proposes a method for achieving higher coverage and lower energy consumption in heterogeneous WSNs. The main solution of the embodiment of this application is to obtain initial data on WSN coverage in an industrial area; optimize the initial data according to a preset WSN coverage optimization model to obtain an optimization result, where the preset WSN coverage optimization model is constructed based on the improved dung beetle algorithm; and obtain a target WSN coverage solution based on the optimization result.

[0079] Based on the above, the embodiment of the present application also provides a WSN coverage optimization method based on the improved dung beetle algorithm, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the WSN coverage optimization method based on the improved dung beetle algorithm of this application.

[0080] In this embodiment, the WSN coverage optimization method based on the improved dung beetle algorithm includes steps S10 to S30:

[0081] Step S10: Acquire initial data of WSN coverage in the industrial area.

[0082] It's important to note that initial data acquisition requires comprehensive and detailed information. This information includes the boundaries of the industrial area, the number of sensor nodes, and the node sensing and communication radius to ensure the accuracy and effectiveness of the subsequent optimization algorithm. First, a comprehensive survey of the industrial area is required, documenting its size, shape, boundaries, and the distribution of internal obstacles (such as large equipment, pipelines, and walls). This information can be obtained through Geographic Information System (GIS) technology or on-site mapping, providing the basic geographic information for sensor node deployment. Second, detailed documentation is required of sensor node performance parameters, including communication radius, energy consumption characteristics, sensing capabilities (such as temperature, humidity, and gas concentration), as well as the node's initial location and sensing radius. These parameters directly determine the node's coverage and communication efficiency within the industrial area. Furthermore, the monitoring requirements of the industrial area must be clearly defined, such as the environmental parameters to be monitored, the required monitoring accuracy, and the monitoring frequency. These requirements will directly influence the configuration and deployment strategy of the sensor nodes. Furthermore, understanding the network topology, including the communication links and data transmission paths between sensor nodes, will help optimize data transmission efficiency and reduce communication energy consumption. Finally, considering the dynamic changes in industrial areas, such as changes in production activities, the movement or addition of equipment, and other factors, this dynamic information may affect the coverage of sensor nodes, so it needs to be updated and adjusted in real time during the optimization process. By comprehensively and accurately obtaining this initial data, we can provide reliable input for the optimization algorithm.

[0083] Step S20: Optimize the initial data according to the preset WSN coverage optimization model to obtain an optimization result.

[0084] It should be noted that the preset WSN coverage optimization model usually takes into account multiple objectives, such as maximizing network coverage, minimizing node energy consumption, and optimizing the average movement distance of nodes. By inputting the initial data into the preset WSN coverage optimization model, the preset WSN coverage optimization model is constructed based on the improved dung beetle algorithm to adjust and optimize the initial positions of sensor nodes.

[0085] Specifically, step S20 also includes initializing algorithm parameters and setting a maximum number of iterations. The algorithm parameters include a coverage target and an average node travel distance target. The number of sensor nodes determines the network density and coverage capability, while the size of the target industrial area limits the spatial scope of the optimization problem. The coverage target defines the minimum coverage ratio to achieve, ensuring that there are no blind spots within the entire target industrial area. The average node travel distance target aims to reduce unnecessary movement by optimizing node positions, thereby reducing energy consumption and extending network life. For example, within a 100m×100m target industrial area, if 30 sensor nodes are initially randomly deployed, with a 90% coverage target and an average node travel distance target of no more than 5 meters, the algorithm must find the optimal deployment solution while meeting these two conditions. Secondly, setting a maximum number of iterations is to control the algorithm's runtime and prevent premature convergence or falling into a local optimum. The maximum number of iterations should be selected based on the specific application requirements and computing resource constraints. Generally, a larger number of iterations provides more opportunities for exploration, but also implies higher computational cost. Therefore, properly setting the maximum number of iterations is crucial for balancing search depth and computational efficiency. For example, setting the maximum number of iterations to 500 can avoid unnecessary lengthy calculations while ensuring sufficient search space. Then, the Sinusoidal chaotic mapping strategy is used to initialize the dung beetle population. Sinusoidal chaotic mapping is a special chaotic mapping method that is widely used in the population initialization stage of optimization algorithms due to its unique mathematical properties. Specifically, the chaotic mapping parameters are set and the initial values ​​are defined. , according to the chaotic mapping formula, the chaotic sequence is generated by iteration according to the number of chaotic iterations. The specific formula is:

[0086] ;

[0087] in, represents the chaos parameter, , the number of chaotic iterations is the same as the maximum number of iterations. Through this mapping method, a series of numerical sequences with high randomness and ergodicity can be generated in the interval [0, 1]. These sequences can be used to initialize the position of the dung beetle population, thereby ensuring a more uniform and diversified population distribution.

[0088] Then, the chaotic sequence is linearly mapped to the target industrial area to generate the initial dung beetle population. Specifically, when applying the Sinusoidal chaotic mapping strategy to initialize the dung beetle population, each dung beetle individual is first assigned an initial position. Assuming the population size is , the dimension of the target industrial area is , you need to generate a size of The initial position matrix is ​​constructed using a sinusoidal chaotic map. For each dimension of each individual, a set of random numbers is generated using a sinusoidal chaotic map and mapped to the actual target industrial area. For example, if the target industrial area is a 100m×100m square, the generated random numbers in the range [0, 1] can be converted to coordinates within the target industrial area through a linear transformation. The fitness values ​​of the dung beetle population are then calculated to obtain the fitness values ​​of the individuals. This value reflects the quality of the individual solution and is a key metric for measuring the performance of the optimization algorithm. Specifically, in the context of wireless sensor network (WSN) coverage optimization, the fitness function is typically defined based on two main objectives: coverage and average node movement distance. First, coverage is the proportion of the target industrial area that can be covered by deployed sensor nodes. Ideally, full coverage is desired, but in practice, it is necessary to balance coverage with other factors such as energy consumption. Assuming the target industrial area is 100m×100m, the coverage under the current population configuration can be calculated by analyzing the effective sensing range and location of each sensor node. For the position vector of each dung beetle individual (representing the layout of the sensor node), the coverage area is determined using geometric methods or grid methods, and the coverage rate is calculated accordingly. In addition, the average node movement distance is used to adjust from the initial random distribution to the optimal layout, and each sensor node may need to move a certain distance. Reducing unnecessary movement helps reduce energy consumption and extend the life of the network. Therefore, the fitness function also considers the sum of the distances moved by the nodes and minimizes it as much as possible. Finally, the fitness function combines the coverage rate and the average node movement distance according to the weight coefficient. The weight coefficient balances the relationship between the coverage rate and the movement distance to obtain the fitness values ​​of multiple individuals. The specific fitness function is expressed as:

[0089] ;

[0090] in, is a weight coefficient that balances the relationship between coverage and moving distance, Indicates coverage, Indicates the average moving distance of the node.

[0091] Next, a comparison is made based on multiple fitness values ​​to obtain a first preset individual position and a second preset individual position. The individual with the highest fitness value is selected as the first preset individual position, which is the optimal position in the current population. This position represents the layout solution that is closest to the global optimal solution in the current iteration, with the highest coverage and lowest energy consumption. On the other hand, the individual with the lowest fitness value is selected as the second preset individual position, which is the worst position in the current population. Although this position is generally considered a poor solution, it provides important information that can help the algorithm identify inefficient areas in the search space and guide the population away from these bad areas, thereby improving overall search efficiency. Comparison of fitness values ​​is usually done by directly comparing the fitness value scores of each individual. Assuming that the fitness function is designed to maximize coverage while minimizing the average node movement distance, then the higher the fitness value, the closer the individual's layout solution is to the optimal solution.

[0092] Next, a crossover strategy and a random inertia weight strategy are used to update the positions of individuals in the population, yielding updated individual positions. The crossover strategy is implemented through both horizontal and vertical crossover. The horizontal crossover operation crosses different individuals within the same dimension, randomly matching individuals within the population and exchanging features to generate new offspring individuals. This operation effectively improves the ability and speed of individuals to explore the optimal position, enhancing global search capabilities. The vertical crossover operation mutates the same individual along different dimensions, similar to the mutation operation in genetic algorithms. This helps individuals escape local optima, further improving the algorithm's convergence speed and optimization accuracy. The random inertia weight strategy optimizes the position updates of thieving dung beetles. By introducing a random inertia weight, the thieving dung beetle's previous position is used to guide its subsequent position. The larger the weight, the greater the influence on the subsequent position. This strategy effectively prevents premature convergence, reduces the risk of falling into a local optimum, and enhances the algorithm's flexibility and adaptability during the local search phase. Calculations are then performed based on the updated individual positions, using the first and second preset individual positions, to obtain the target individual fitness value and the corresponding target position. First, for each updated individual position, the corresponding coverage and average node movement distance are calculated. For example, assuming the target industrial area is a 100m×100m square, the coverage of the current layout can be determined by analyzing the effective sensing range of each sensor node and its new position. Simultaneously, the sum of the required movement distances from the initial position to the new position is calculated, and the average movement distance is derived from this. This calculation yields the fitness value of each individual at the updated position. Next, the updated individual fitness value is compared with the fitness value at the first preset individual position. If the updated individual fitness value is better, the first preset individual position is replaced with it, and the corresponding fitness value is updated. Conversely, if the updated individual fitness value is worse than the first preset individual position but better than the second preset individual position, the individual position is retained to maintain population diversity. Furthermore, the algorithm adjusts the population's search direction based on the second preset individual position. By analyzing the characteristics of the worst-case location, the algorithm can dynamically adjust its search strategy to avoid over-concentration of the population in the local optimal area, thereby improving global search capabilities. For example, when it finds that the fitness values ​​of multiple individuals are close to the worst-case location, the algorithm increases the probability of mutation operations to introduce new solutions and break the local optimal deadlock.

[0093] If the maximum number of iterations is reached, the target individual's fitness value and corresponding target position are output as the optimization result. When the preset maximum number of iterations is reached, the algorithm outputs the target individual's fitness value and corresponding target position as the final optimization result. This process indicates that the optimization algorithm has completed its exploration of the sensor node layout and found the optimal or near-optimal solution under the current conditions. First, at the end of each iteration, the algorithm evaluates the fitness value of each individual in the population and identifies the best-performing individual (i.e., the first preset individual position with the highest fitness value). As the number of iterations increases, the individual positions are continuously updated using a cross-pollination strategy and a random inertia weight strategy, gradually approaching the global optimal solution. When the maximum number of iterations is reached, it indicates that the algorithm has fully explored and developed the solution, and further improvement is unlikely. At this point, the algorithm outputs the target individual's fitness value and corresponding target position. The target individual fitness value reflects the quality of the layout solution, taking into account key metrics such as coverage and average node movement distance. The target position specifies the optimal deployment location for each sensor node, ensuring the highest coverage and lowest energy consumption.

[0094] Furthermore, a multi-objective test function was selected to test and evaluate the optimization algorithm of this embodiment. The ZDT (Zitzler-Deb-Thiele) multi-objective function test set is the most widely used multi-objective algorithm test function for evaluating algorithm performance. The ZDT series of test functions possesses an optimal Pareto front, which is generally non-convex or multi-peaked. By calculating different Pareto fronts, the accuracy, diversity, and convergence of the algorithm can be evaluated. This embodiment uses the ZDT series of test functions from the ZDT standard test function table shown in Table 1 to test the algorithm performance. Three multi-objective algorithms, namely the Multi-Objective Grey Wolf Optimization (MOGWO), the Multi-Objective Particle Swarm Optimization (MOPSO), and the Multi-Objective Dung Beetle Optimization (MODBO), are compared and analyzed with the Multi-Objective Dung Beetle Optimization (MOSCRDBO) algorithm proposed in this embodiment.

[0095] Table 1 ZDT standard test function table

[0096]

[0097] Algorithms are evaluated using convergence and diversity metrics. Multi-objective optimization algorithms seek the solution set closest to the Pareto front, finding more non-dominated solutions. As the algorithm iterates, it gradually approaches and ultimately converges to the true Pareto front. Convergence metrics evaluate the convergence speed and stability of multi-objective optimization algorithms. Common convergence evaluation metrics include: GD (Generational Distance): This calculates the sum of the distances between all solutions in the algorithm's non-dominated solution set and the true curve, and takes the average. IGD (Inverted Generational Distance): This is the opposite of the iteration distance, with the true value being the inverse of the iteration distance. Table 2 shows the iteration distance values ​​for the four algorithms, and Table 3 shows the inverse iteration distance values ​​for the four algorithms.

[0098] Table 2 Iterative distance values ​​of four algorithms

[0099]

[0100] Table 3. Inverse iterative distance values ​​of four algorithms

[0101]

[0102] When evaluating convergence indices, smaller GD and IGD values ​​indicate better algorithm performance. Calculations show that the MOSCRDBO algorithm proposed in this embodiment achieves the smallest values ​​for both GD and IGD convergence indices on each test function, demonstrating the best convergence and a curve closer to the true value.

[0103] In addition to the aforementioned convergence metrics, multi-objective optimization algorithms also use diversity metrics to evaluate the diversity and uniformity of solutions. Common convergence metrics include SP (non-inferiority spacing metric), which calculates the sum of the distances between non-dominated solutions obtained by all algorithms and takes the average. Table 4 shows the non-inferiority spacing metric values ​​for four algorithms.

[0104] Table 4 Non-inferiority interval metric values ​​of four algorithms

[0105]

[0106] The SP value indicates the diversity and uniformity of the algorithm's solution set. A smaller SP value indicates a more uniform distribution of the algorithm's solutions on the true Pareto front. Calculations show that the MOSCRDBO algorithm proposed in this example achieves the minimum SP value for each test function, indicating that the algorithm's non-dominated solutions are more evenly distributed on the true Pareto front, resulting in better performance.

[0107] As iterations progress, the model continuously approaches the optimal solution, ultimately yielding optimized results. These results include key information such as optimal sensor node locations, network coverage, node energy consumption distribution, and average travel distance. These results not only demonstrate the effectiveness of the optimized network coverage but also provide a specific solution for node deployment. By applying these optimized results to real-world industrial areas, WSN coverage quality can be significantly improved.

[0108] Step S30: obtaining a target WSN coverage solution based on the optimization result.

[0109] It should be noted that the targeted wireless sensor network (WSN) coverage scheme derived from the optimization results provides a scientific basis for efficient and reliable monitoring. Based on the target individual fitness values ​​and corresponding target locations derived through multiple rounds of iterative optimization, this scheme ensures maximum coverage of the target industrial area while minimizing energy consumption.

[0110] First, the target locations determine the optimal deployment locations for each sensor node. These locations, precisely calculated, not only ensure effective coverage of the entire monitoring area but also reduce unnecessary node overlap, improving resource utilization. For example, within a 100m x 100m area, the optimized layout might indicate that certain key areas require a higher density of sensor nodes to enhance coverage accuracy, while other areas could utilize a sparse deployment strategy to reduce energy consumption.

[0111] Second, the target fitness value reflects the overall performance of the proposed layout. It takes into account factors such as coverage, average node travel distance, and potential energy consumption. A high fitness value indicates that the solution provides comprehensive coverage while maximizing the network's lifespan. For example, the optimization results may show that the solution can achieve over 90% coverage while keeping the average node travel distance under 5 meters and reducing energy consumption.

[0112] Specifically, in this example, a coverage experiment was conducted in a target industrial area measuring 100m x 100m, with no obstacles within the plane. Using coverage and average node movement distance as objective functions, a comparative experiment was conducted among the MOGWO, MOPSO, MODBO, and MOSCRDBO algorithms. The optimized coverage results obtained by the MOGWO, MOPSO, MODBO, and MOSCRDBO algorithms show that all four algorithms offer significant improvements in coverage optimization for heterogeneous WSNs. Among them, the MOPSO and MODBO algorithms offer relatively small improvements in coverage optimization, with significant gaps and overlap remaining. The MOGWO and MOSCRDBO algorithms significantly improve coverage. While the MOGWO algorithm exhibits relatively more gaps and overlap, the MOSCRDBO algorithm, while still exhibiting a small amount of coverage, achieves an overall coverage rate exceeding 90%, representing the most significant improvement. This demonstrates that the MOSCRDBO algorithm proposed in this example achieves the best coverage optimization results for heterogeneous WSNs. In addition to the coverage experiments of the above four algorithms, experiments were also conducted on the network coverage rate and the average moving distance of nodes under different numbers of nodes, such as Figure 2 The relationship curve between network coverage and number of nodes is shown in the figure. Figure 2 The four lines from bottom to top represent MODBO, MOPSO, MOGWO and MOSCRDBO algorithms respectively. With the increase of algorithm runs and the number of nodes, the coverage of the four optimization algorithms is constantly improving. At the same scale, MOSCRDBO algorithm has the highest coverage and the best effect among the four optimization algorithms. Figure 3 The relationship between the average moving distance of nodes and the number of nodes is shown in the graph. Figure 3 The four lines from bottom to top represent the average node movement distances of the four optimization algorithms (MOSCRDBO, MOPSO, MODBO, and MOGWO), which decrease roughly as the number of nodes increases. This decrease in average node movement distance indicates a reduction in the distance traveled during communication, reducing excess energy waste during communication, increasing sensor lifespan, and lowering costs. At the same scale, the MOSCRDBO algorithm achieves the smallest average node movement distance and energy consumption of the four optimization algorithms.

[0113] This embodiment initializes the algorithm parameters and sets the maximum number of iterations, uses the Sinusoidal chaotic mapping strategy to initialize the population, calculates the individual fitness value, determines the preset individual position, and uses the vertical and horizontal cross and random inertia weight strategies to update the individual position. Finally, it outputs the optimization results and generates a WSN coverage plan, which improves the global search capability and optimization accuracy, effectively avoids local optimality, and improves network coverage and node energy efficiency.

[0114] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 4 The WSN coverage optimization method based on the improved dung beetle algorithm, step S20, further includes steps S201 to S203:

[0115] Step S201, performing a crossover operation according to a horizontal crossover strategy, updating the positions of the ball-pushing dung beetles and the breeding dung beetles in the population, generating first-generation individuals that meet preset retention requirements, and obtaining the individual positions of the ball-pushing dung beetles and the breeding dung beetles.

[0116] It should be noted that during the WSN coverage optimization process, an evolutionary mechanism based on a horizontal crossover strategy is used to update the positions of the ball-pushing and breeding dung beetles to improve population diversity and algorithm convergence. This strategy simulates the collaboration and genetic information exchange between individuals in nature, selectively crossing over high-fitness individuals to produce better offspring.

[0117] Specifically, step S201 includes: selecting two dung beetles or two breeding dung beetles as parent individuals based on the population. In each generation of the population, first, two dung beetles or two breeding dung beetles are randomly selected as parent individuals, denoted as and The two parent individuals have higher fitness values ​​and represent the better solutions in the current iteration. Perform a horizontal crossover operation on the parent individuals to obtain the first individual and the second individual. The specific formula is:

[0118] ;

[0119] in, There are two parent individuals, Indicates the The first and second bodies of the dimension, is a random number in [0, 1], The algorithm calculates and compares the fitness values ​​of the first and second individuals with those of their parents, retaining the individual with the higher fitness value. Once the positions of all dung beetles and brooding beetles in the population have been updated, the individual with the higher fitness value is output as the first offspring and the corresponding individual position of the dung beetle and brooding beetle. Specifically, the fitness values ​​of the first and second individuals are calculated and compared with their corresponding parent individuals, and the individual with the higher fitness value is retained as part of the next generation. This process ensures the continuation of high-quality genes and prevents invalid mutations from affecting population quality. After the positions of all dung beetles and brooding beetles have been updated, the individual with the higher fitness value is output as the first offspring, and the new position of the corresponding dung beetle and brooding beetle is simultaneously recorded. This mechanism not only enhances the algorithm's global exploration capabilities but also improves local development efficiency, resulting in a more optimal WSN node layout in terms of coverage and energy balance, improving the overall performance and robustness of the network.

[0120] Step S202 , performing mutation operations in different dimensions according to the vertical crossover strategy, updating the positions of the small dung beetles in the population, generating second-generation individuals that meet the preset retention requirements, and obtaining the individual positions of the small dung beetles.

[0121] It's important to note that in WSN coverage optimization, introducing a vertical crossover strategy to update the positions of individual dung beetles is an effective improvement to further enhance population diversity and the algorithm's global optimization capabilities. This strategy enhances local search capabilities by exchanging information across different dimensions, preventing the algorithm from falling into local optimality and thus improving overall optimization performance.

[0122] Specifically, step S202 further includes: selecting two initial dung beetle individuals of different dimensions based on the population, denoted as and , respectively representing two different solutions in the current population.

[0123] Perform a vertical crossover operation on the small dung beetle individual to obtain the third individual. The specific formula is:

[0124] ;

[0125] in, are the initial dung beetle individuals in two different dimensions. is a random number in the range [0, 1], used to control the proportion of parent individuals in the new individuals. The fitness value of the third individual is calculated and compared with the fitness value of the initial dung beetle individual. If the third individual's fitness value is higher, the initial dung beetle individual's position is replaced; otherwise, the initial position is retained. Finally, the individual with the higher fitness value is output as the second-generation individual and the corresponding position of the dung beetle, and this process continues until the positions of all dung beetles in the population are updated. Specifically, after the third individual is generated, its fitness value is calculated and compared with the fitness values ​​of the original two parent individuals. If the third individual's fitness is higher than the original individual's, the original individual's position is replaced by the third individual; otherwise, the original individual's position remains unchanged. This mechanism ensures that only individuals with higher quality advance to the next generation, effectively improving the overall quality of the population. After the vertical crossover operation is completed for the entire population of dung beetles, all individuals with higher fitness values ​​are output as the second-generation individuals, and the corresponding new positions of the dung beetles are simultaneously recorded. Through this strategy, not only the algorithm's exploration ability in complex search spaces is enhanced, but also the convergence speed and stability are improved.

[0126] Step S203 , updating the position of the thieving dung beetle in the population according to the random inertia weight strategy, generating third-generation individuals that meet the preset retention requirements, and obtaining the individual position of the thieving dung beetle.

[0127] It should be noted that, in order to improve the algorithm's convergence speed and global search capabilities during WSN coverage optimization, introducing a randomized inertia weight strategy based on the iteration progress ratio to update the positions of individual thieving dung beetles is an effective improvement. This strategy dynamically adjusts the inertia weight, giving the algorithm different exploration and exploitation capabilities at different iteration stages, thereby more efficiently approaching the global optimal solution.

[0128] Specifically, step S203 includes: obtaining the current number of iterations and the maximum number of iterations, and obtaining the iteration progress ratio;

[0129] Calculate according to the iterative progress ratio to obtain the random inertia weight, the formula is:

[0130] ;

[0131] in, are the upper and lower limits of the inertia weight, is the iteration progress ratio, is a random number in [0, 1];

[0132] The position of the thieving dung beetle is updated according to the random inertia weight to obtain the fourth individual. The specific formula is:

[0133] ;

[0134] in, is the current local optimal position, is the global optimal position, is a constant, The algorithm uses a random vector that follows a normal distribution. When the fourth individual has a higher fitness value, the position of the thieving dung beetle individual is replaced; otherwise, the position remains unchanged. The individual with the higher fitness value at this point is output as the third-generation individual and the corresponding position of the thieving dung beetle, and this process continues until the positions of all thieving dung beetles in the population are updated. Specifically, the fitness value of the fourth individual is calculated and compared with that of the original individual. If the new individual has a higher fitness value, the original individual is replaced; otherwise, the original individual remains unchanged. Finally, after all thieving dung beetle individuals in the population have been updated, all individuals with higher fitness values ​​are output as the third-generation individuals, and the new positions of the corresponding thieving dung beetles are simultaneously recorded. This strategy significantly enhances the algorithm's adaptability across different iterations, resulting in a more rational WSN node layout, higher coverage, and lower energy consumption, improving overall network performance and stability.

[0135] This embodiment optimizes the positions of ball-pushing, breeding, small, and stealing dung beetles through horizontal and vertical crossover strategies, as well as random inertia weighting, to generate high-quality offspring individuals. This improves population diversity and global search capabilities, ensuring high coverage and low energy consumption in WSN coverage optimization, enhancing the system's robustness and adaptability, and making it suitable for complex dynamic environments.

[0136] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction and will not be described in detail later. Figure 5 The WSN coverage optimization method based on the improved dung beetle algorithm, step S30, further includes steps S301 to S305:

[0137] Step S301: generating a deployment plan for sensor nodes according to the optimization result.

[0138] It should be noted that the sensor node deployment scheme generated based on the optimization results provides scientific and efficient guidance for practical WSN deployment. This scheme, based on a multi-strategy improved dung beetle optimization algorithm, optimizes the positions of ball-pushing dung beetles, breeding dung beetles, small dung beetles, and thieving dung beetles through techniques such as horizontal crossover, vertical crossover, and random inertia weighting, ultimately determining the optimal location for each sensor node. The optimization results identify the optimal deployment point for each sensor node within the target industrial area. These locations not only maximize coverage but also minimize energy consumption. For example, within a 100m × 100m target industrial area, the optimized layout may indicate that certain key locations require a higher density of sensor nodes to enhance local coverage, while other areas can adopt a sparse deployment strategy to reduce energy consumption.

[0139] Step S302: Apply the deployment solution to the target industrial area to achieve optimized deployment of sensor nodes.

[0140] It should be noted that when applying the deployment plan, physical layout is required based on the specific coordinates of each sensor node in the optimization results. These locations are determined through multiple rounds of iterative optimization, aiming to maximize coverage while minimizing energy consumption. For example, within a target 100m×100m industrial area, the optimized layout may indicate that certain key areas require a higher density of sensor nodes to enhance local coverage accuracy, while other areas can adopt a sparse deployment strategy to reduce energy consumption and maintenance costs. Secondly, the deployment process must consider practical operational challenges, such as terrain obstacles and signal interference. Through a combination of simulation and field testing, the specific locations of nodes are verified and adjusted to ensure consistency between the actual deployment and the optimized plan. For example, drones or automated equipment can be used to assist in the precise deployment of nodes, especially in hard-to-reach areas, to improve deployment efficiency and accuracy.

[0141] Furthermore, to further enhance reliability and stability, redundancy can be incorporated into deployment plans. Even if some nodes fail due to malfunction or other reasons, the remaining nodes can maintain basic network functionality, ensuring the continuity and integrity of data collection. This redundancy is particularly important in dynamically changing environments, effectively addressing unexpected situations such as node damage and moving obstacles.

[0142] Step S303 , calculating the network coverage and average node movement distance after the optimized deployment to obtain the optimization result.

[0143] It's important to note that the comprehensive evaluation of two key metrics, network coverage and average node travel distance, provides a comprehensive understanding of the effectiveness of the optimized deployment. High coverage and low average node travel distance indicate that the optimized solution not only improves overall network performance but also effectively reduces energy consumption, enhancing the system's robustness and adaptability. This provides a solid foundation for subsequent data collection, transmission, and processing, enabling WSNs to operate stably and sustainably in complex and ever-changing application scenarios.

[0144] Step S304: Verify based on the optimization result to obtain a verification result.

[0145] It should be noted that the optimization results are verified by network coverage and average node movement distance.

[0146] Step S305: When the verification result shows that the optimization result meets the preset optimization requirements, the optimization process is completed and the deployment plan is output as the target WSN coverage plan.

[0147] It's important to note that achieving optimal results means that, after multiple simulations and field tests, network coverage has reached the expected standard (e.g., above 90%), while the average node movement distance has been reduced (e.g., to less than 5 meters). These indicators demonstrate that the optimized deployment not only effectively covers the target industrial area, but also significantly reduces energy consumption and extends the network's lifespan. Furthermore, the optimized solution demonstrates robustness and adaptability in a dynamically changing environment, enabling it to cope with unexpected situations such as node failures or temporary obstacles.

[0148] Next, the final deployment plan is output, including detailed node location coordinates. This plan not only specifies the specific deployment location of each sensor node but also takes into account factors such as terrain characteristics and signal interference, ensuring that the actual layout is highly consistent with the optimized design. For example, within a 100m×100m target industrial area, the optimized layout may indicate that certain key locations require a higher density of sensor nodes to enhance local coverage accuracy, while other areas can adopt a sparse deployment strategy to reduce energy consumption.

[0149] This embodiment generates an efficient sensor node deployment plan through an optimization algorithm to improve network coverage, reduce node energy consumption, extend network service life, and ensure the reliability and practicality of the plan.

[0150] Based on the first embodiment of the present application, the present application also provides a WSN coverage optimization device based on the improved dung beetle algorithm, please refer to Figure 6 , the device comprises:

[0151] The acquisition module 10 is used to acquire the initial data of the WSN coverage of the industrial area.

[0152] The optimization module 20 is used to optimize the initial data according to a preset WSN coverage optimization model to obtain an optimization result. The preset WSN coverage optimization model is constructed based on the improved dung beetle algorithm.

[0153] The result module 30 is used to obtain a target WSN coverage solution based on the optimization result.

[0154] Construction module 40 is used to initialize algorithm parameters and set the maximum number of iterations. The algorithm parameters include coverage rate target and node average moving distance target; adopt Sinusoidal chaotic mapping strategy to initialize dung beetle population; calculate the dung beetle population to obtain fitness values ​​of multiple individuals; compare the multiple fitness values ​​to obtain a first preset individual position and a second preset individual position; adopt vertical and horizontal cross strategy and random inertia weight strategy to update the individual positions in the population to obtain updated individual positions; calculate based on the first preset individual position and the second preset individual position according to the updated individual position to obtain the target individual fitness value and the corresponding target position; if the maximum number of iterations is reached, output the target individual fitness value and the corresponding target position as the optimization result.

[0155] The WSN coverage optimization device based on the improved dung beetle algorithm provided in this application, which utilizes the WSN coverage optimization method based on the improved dung beetle algorithm in the above-mentioned embodiments, can solve the technical problem of achieving more efficient and energy-efficient WSN coverage optimization. Compared with the prior art, the beneficial effects of the WSN coverage optimization device based on the improved dung beetle algorithm provided in this application are the same as those of the WSN coverage optimization method based on the improved dung beetle algorithm provided in the above-mentioned embodiments. Other technical features of the WSN coverage optimization device based on the improved dung beetle algorithm are the same as those disclosed in the above-mentioned embodiments and are not further described here.

[0156] In one embodiment, the construction module 40 is further used to set chaotic mapping parameters and define initial values; generate a chaotic sequence by iterating according to the chaotic mapping formula according to the number of chaotic iterations; and generate an initial dung beetle population by linearly mapping the chaotic sequence to the target industrial area.

[0157] In one embodiment, the construction module 40 is further used to perform a crossover operation according to a horizontal crossover strategy, update the positions of the ball-pushing dung beetles and the breeding dung beetles in the population, generate the first offspring individuals that meet the preset retention requirements, and obtain the individual positions of the ball-pushing dung beetles and the breeding dung beetles; perform a mutation operation in different dimensions according to a vertical crossover strategy, update the positions of the small dung beetles in the population, generate the second offspring individuals that meet the preset retention requirements, and obtain the individual positions of the small dung beetles; update the positions of the thieving dung beetles in the population according to a random inertia weight strategy, generate the third offspring individuals that meet the preset retention requirements, and obtain the individual positions of the thieving dung beetles.

[0158] In one embodiment, the construction module 40 is also used to select two dung beetles or two breeding dung beetles as parent individuals based on the population; perform a horizontal crossover operation on the parent individuals to obtain a first individual and a second individual; calculate and compare the fitness values ​​of the first individual and the second individual with the fitness value of the parent individual, and retain the individual with the larger fitness value; when the position update of all dung beetles and breeding dung beetles in the population is completed, output the individual with the larger fitness value at this time as the first offspring individual and the corresponding individual position of the dung beetle and breeding dung beetle.

[0159] In one embodiment, the construction module 40 is also used to select two initial small dung beetle individuals of different dimensions based on the population; perform a vertical cross operation on the small dung beetle individuals to obtain a third individual; calculate the fitness value of the third individual and compare it with the fitness value of the initial small dung beetle individual; when the fitness value of the third individual is larger, replace the position of the initial small dung beetle individual, otherwise maintain the position of the initial small dung beetle individual; output the individual with the larger fitness value at this time as the second offspring individual and the corresponding individual position of the small dung beetle, until the position update of all small dung beetles in the population is completed.

[0160] In one embodiment, the construction module 40 is further used to obtain the current number of iterations and the maximum number of iterations, and obtain the iteration progress ratio; perform calculations based on the iteration progress ratio to obtain a random inertia weight; update the position of the thieving dung beetle based on the random inertia weight to obtain a fourth individual; when the fitness value of the fourth individual is larger, replace the position of the thieving dung beetle individual, otherwise maintain the position of the thieving dung beetle individual; output the individual with the larger fitness value at this time as the third offspring individual and the corresponding individual position of the thieving dung beetle, until the position update of all thieving dung beetles in the population is completed.

[0161] In one embodiment, the construction module 40 is further used to generate a deployment plan for the sensor nodes based on the optimization results; apply the deployment plan to the target industrial area to achieve optimized deployment of the sensor nodes; calculate the network coverage and the average moving distance of the nodes after the optimized deployment to obtain the optimization results; verify according to the optimization results to obtain a verification result; when the verification result shows that the optimization result meets the preset optimization requirements, the optimization process is completed and the deployment plan is output as the target WSN coverage plan.

[0162] The present application provides a WSN coverage optimization device based on an improved dung beetle algorithm. The WSN coverage optimization device based on the improved dung beetle algorithm includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the WSN coverage optimization method based on the improved dung beetle algorithm in the above-mentioned embodiment 1.

[0163] Reference below Figure 7 , which shows a schematic diagram of the structure of a WSN coverage optimization device based on the improved dung beetle algorithm suitable for implementing the embodiments of the present application. The WSN coverage optimization device based on the improved dung beetle algorithm in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The WSN coverage optimization device based on the improved dung beetle algorithm shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0164] like Figure 7 As shown, a WSN coverage optimization device based on the improved dung beetle algorithm may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the WSN coverage optimization device based on the improved dung beetle algorithm. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the WSN coverage optimization device based on the improved dung beetle algorithm to communicate with other devices wirelessly or wired to exchange data. While the figure shows a WSN coverage optimization device based on the improved dung beetle algorithm with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0165] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0166] The WSN coverage optimization device based on the improved dung beetle algorithm provided in this application, which utilizes the WSN coverage optimization method based on the improved dung beetle algorithm described in the above-mentioned embodiments, can solve the technical problem of achieving more efficient and energy-efficient WSN coverage optimization. Compared with the prior art, the WSN coverage optimization device based on the improved dung beetle algorithm provided in this application has the same beneficial effects as the WSN coverage optimization method based on the improved dung beetle algorithm provided in the above-mentioned embodiments. Other technical features of the WSN coverage optimization device based on the improved dung beetle algorithm are the same as those disclosed in the above-mentioned embodiments and are not further described here.

[0167] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0168] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0169] The present application provides a computer-readable medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the WSN coverage optimization method based on the improved dung beetle algorithm in the above embodiment.

[0170] The computer-readable medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0171] The computer-readable medium may be included in the WSN coverage optimization device based on the improved dung beetle algorithm; or may exist independently without being assembled into the WSN coverage optimization device based on the improved dung beetle algorithm.

[0172] The computer-readable medium carries one or more programs. When executed by a WSN coverage optimization device based on the improved dung beetle algorithm, the one or more programs enable the WSN coverage optimization device based on the improved dung beetle algorithm to write computer program code for performing the operations of the present application in one or more programming languages, or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0173] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0174] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0175] The computer-readable medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned WSN coverage optimization method based on the improved dung beetle algorithm. This computer-readable medium addresses the technical problem of achieving more efficient and energy-efficient WSN coverage optimization. Compared to the prior art, the beneficial effects of the computer-readable medium provided in this application are similar to those of the WSN coverage optimization method based on the improved dung beetle algorithm provided in the aforementioned embodiments, and are not further elaborated here.

[0176] The present application also provides a computer program product, including a computer program, which implements the steps of the WSN coverage optimization method based on the improved dung beetle algorithm when executed by a processor.

[0177] The computer program product provided in this application can solve the technical problem of achieving more efficient and energy-efficient WSN coverage optimization. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the WSN coverage optimization method based on the improved dung beetle algorithm provided in the above embodiment, and will not be elaborated here.

[0178] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A WSN coverage optimization method based on an improved dung beetle algorithm, characterized in that: The method comprises: Obtain initial data on WSN coverage in industrial areas; Optimizing the initial data according to a preset WSN coverage optimization model to obtain an optimization result, wherein the preset WSN coverage optimization model is constructed based on an improved dung beetle algorithm; Obtaining a target WSN coverage solution based on the optimization result; Before the step of optimizing the initial data according to the preset WSN coverage optimization model to obtain the optimization result, the method includes: Initializing algorithm parameters and setting a maximum number of iterations, wherein the algorithm parameters include the number of sensor nodes, the size of the target industrial area, the coverage target, and the average node movement distance target; The Sinusoidal chaotic mapping strategy is used to initialize the dung beetle population; Calculating the dung beetle population to obtain fitness values ​​of multiple individuals; Obtaining a first preset individual position and a second preset individual position based on a comparison of the plurality of fitness values; Adopt the vertical and horizontal cross strategy and random inertia weight strategy to update the individual positions in the population and obtain the updated individual positions; Calculating according to the updated individual position based on the first preset individual position and the second preset individual position to obtain a target individual fitness value and a corresponding target position; If the maximum number of iterations is reached, the target individual fitness value and the corresponding target position are output as the optimization result; The step of adopting the vertical and horizontal cross strategy and the random inertia weight strategy to update the individual positions in the population to obtain the updated fitness value and the corresponding individual position includes: Performing a crossover operation according to a horizontal crossover strategy to update the positions of the ball-pushing dung beetles and the breeding dung beetles in the population, generating first-generation offspring individuals that meet preset retention requirements, and obtaining the individual positions of the ball-pushing dung beetles and the breeding dung beetles; Performing mutation operations in different dimensions according to a vertical crossover strategy, updating the positions of the small dung beetles in the population, generating second-generation individuals that meet preset retention requirements, and obtaining the individual positions of the small dung beetles; The positions of the thieving dung beetles in the population are updated according to a random inertia weight strategy, a third generation of individuals that meet preset retention requirements are generated, and the individual positions of the thieving dung beetles are obtained.

2. The method according to claim 1, wherein The step of initializing the dung beetle population using the Sinusoidal chaotic mapping strategy includes: Set the chaos map parameters and define the initial values; According to the chaotic mapping formula, the chaotic sequence is generated by iteration according to the number of chaotic iterations. The specific formula is: in, represents the chaos parameter, , the number of chaotic iterations is the same as the maximum number of iterations; The chaotic sequence is linearly mapped to the target industrial area to generate an initial dung beetle population.

3. The method according to claim 1, wherein The step of performing a crossover operation according to a horizontal crossover strategy, updating the positions of the ball-pushing dung beetles and the breeding dung beetles in the population, generating first-generation offspring individuals that meet preset retention requirements, and obtaining the individual positions of the ball-pushing dung beetles and the breeding dung beetles includes: selecting two ball-pushing dung beetles or two breeding dung beetles as parent individuals based on the population; Perform a horizontal crossover operation on the parent individual to obtain the first individual and the second individual. The specific formula is: in, There are two parent individuals, Indicates the The first and second bodies of the dimension, is a random number in [0, 1], is a random number within [-1, 1]; Calculating and comparing the fitness values ​​of the first individual and the second individual with the fitness value of the parent individual, and retaining the individual with the larger fitness value; When the position updates of all the dung beetles and breeding dung beetles in the population are completed, the individuals with larger fitness values ​​at this time are output as the first offspring individuals and the corresponding individual positions of the dung beetles and breeding dung beetles.

4. The method according to claim 1, wherein The step of performing mutation operations in different dimensions according to the vertical crossover strategy, updating the positions of the small dung beetles in the population, generating second-generation individuals that meet preset retention requirements, and obtaining the individual positions of the small dung beetles includes: selecting two initial dung beetle individuals of different dimensions based on the population; A vertical crossover operation is performed on the small dung beetle individual to obtain a third individual. The specific formula is: in, are the initial dung beetle individuals in two different dimensions. is a random number in [0, 1]; Calculating the fitness value of the third individual and comparing it with the fitness value of the initial small dung beetle individual; When the fitness value of the third individual is larger, the position of the initial small dung beetle individual is replaced, otherwise the position of the initial small dung beetle individual is maintained; The individual with the larger fitness value at this time is output as the second offspring individual and the individual position of the corresponding small dung beetle, until the position update of all small dung beetles in the population is completed.

5. The method according to claim 1, wherein The step of updating the positions of the thieving dung beetles in the population according to the random inertia weight strategy, generating third-generation individuals that meet the preset retention requirements, and obtaining the individual positions of the thieving dung beetles includes: Get the current number of iterations and the maximum number of iterations, and get the iteration progress ratio; The random inertia weight is calculated based on the iterative progress ratio. The specific formula is: in, are the upper and lower limits of the inertia weight, is the iteration progress ratio, is a random number in [0, 1]; The position of the stealing dung beetle is updated according to the random inertia weight to obtain the fourth individual. The specific formula is: in, is the current local optimal position, is the global optimal position, is a constant, is a random vector that follows a normal distribution; When the fitness value of the fourth individual is larger, the position of the stealing dung beetle individual is replaced, otherwise the position of the stealing dung beetle individual is maintained; The individual with the larger fitness value at this time is output as the third offspring individual and the individual position of the corresponding thieving dung beetle, until the position update of all thieving dung beetles in the population is completed.

6. The method according to claim 1, wherein The step of obtaining a target WSN coverage solution according to the optimization result includes: generating a deployment plan for sensor nodes according to the optimization results; Applying the deployment solution to the target industrial area to achieve optimized deployment of sensor nodes; Calculating the network coverage rate and the average moving distance of the nodes after the optimized deployment to obtain an optimization result; Perform verification according to the optimization result to obtain a verification result; When the verification result shows that the optimization result meets the preset optimization requirement, the optimization process is completed and the deployment plan is output as the target WSN coverage plan.

7. A WSN coverage optimization device based on an improved dung beetle algorithm, characterized in that: The device comprises: The acquisition module is used to obtain the initial data of WSN coverage in the industrial area; An optimization module, configured to optimize the initial data according to a preset WSN coverage optimization model to obtain an optimization result, wherein the preset WSN coverage optimization model is constructed based on an improved dung beetle algorithm; A result module, configured to obtain a target WSN coverage solution based on the optimization result; A construction module is provided for initializing algorithm parameters and setting a maximum number of iterations, wherein the algorithm parameters include the number of sensor nodes, the size of the target industrial area, the coverage target, and the average node movement distance target; a sinusoidal chaotic mapping strategy is used to initialize a dung beetle population; the dung beetle population is calculated to obtain a plurality of individual fitness values; a first preset individual position and a second preset individual position are obtained by comparing the plurality of fitness values; a vertical and horizontal cross strategy and a random inertia weight strategy are adopted to update the individual positions in the population to obtain an updated individual position; a target individual fitness value is obtained by calculating the updated individual position based on the first and second preset individual positions. value and the corresponding target position; if the maximum number of iterations is reached, the target individual fitness value and the corresponding target position are output as the optimization result; it is also used to perform a crossover operation according to a horizontal crossover strategy, update the positions of the ball-pushing dung beetles and the breeding dung beetles in the population, generate the first offspring individuals that meet the preset retention requirements, and obtain the individual positions of the ball-pushing dung beetles and the breeding dung beetles; perform mutation operations in different dimensions according to a vertical crossover strategy, update the positions of the small dung beetles in the population, generate the second offspring individuals that meet the preset retention requirements, and obtain the individual positions of the small dung beetles; update the positions of the thieving dung beetles in the population according to a random inertia weight strategy, generate the third offspring individuals that meet the preset retention requirements, and obtain the individual positions of the thieving dung beetles.

8. A WSN coverage optimization device based on an improved dung beetle algorithm, characterized in that: The device includes: a memory, a processor, and a WSN coverage optimization program based on an improved dung beetle algorithm stored in the memory and running on the processor. The WSN coverage optimization program based on the improved dung beetle algorithm is configured to implement the steps of the WSN coverage optimization method based on the improved dung beetle algorithm according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a WSN coverage optimization program based on the improved dung beetle algorithm. When the WSN coverage optimization program based on the improved dung beetle algorithm is executed by the processor, the steps of the WSN coverage optimization method based on the improved dung beetle algorithm according to any one of claims 1 to 6 are implemented.

Images