Multi-unmanned aerial vehicle based network communication task planning method, device, equipment and medium

Abstract

The application relates to a multi-unmanned aerial vehicle (UAV)-based network communication task planning method and device, equipment and medium. A set of positions of coupler nodes that maximize the connected area is found in a to-be-restored connected area, and the set of positions is used as target positions of multi-UAV task delivery. The initial positions of each UAV are used as clustering centers to cluster the multi-UAV task delivery, obtain a task delivery set corresponding to each UAV, and then, for each task delivery set, an optimized marine predator algorithm is used to plan paths of all task deliveries in the corresponding task delivery set for each UAV, and finally, the network communication task planning of each UAV is obtained. The method can effectively and quickly restore the communication of most areas in the to-be-restored connected area.

Description

Technical Field

[0001] This application relates to the field of unmanned mission planning technology, and in particular to a network communication mission planning method, apparatus, equipment and medium based on multiple unmanned aerial vehicles. Background Technology

[0002] Earthquakes or fires can cause network outages in small areas. In such situations, drones can be used to deploy a number of wireless network connectors to maximize connectivity in these small areas. Figure 1 As shown, a wireless network connector functions as a mobile base station, enabling both satellite and terrestrial communication, and allowing for rapid deployment and mobility. Drones, due to their high maneuverability and adaptability to various environments, can serve as aerial platforms carrying multiple network communication devices, playing a crucial role in urban rescue and disaster recovery.

[0003] However, there is currently no unified standard or mature deployment scheme for using drones to carry out communication tasks, and there are still many technical challenges in optimizing network coverage, scheduling equipment resources, and planning routes for multiple drones in dynamic environments. Summary of the Invention

[0004] Therefore, it is necessary to provide a network communication task planning method, apparatus, equipment, and medium based on multiple UAVs that can quickly solve the problem of network connectivity issues in small areas, in order to address the aforementioned technical problems.

[0005] A network communication task planning method based on multiple unmanned aerial vehicles (UAVs), the method comprising:

[0006] Obtain the area of ​​the region to be reconnected, the number of connector nodes, and the initial positions of multiple drones;

[0007] Find a set of connector node locations that maximize the connectivity area in the area to be restored, and use this set of locations as the target locations for multi-drone deployment missions.

[0008] With the goal of minimizing the total flight path of each drone, the initial position of each drone is used as the cluster center to cluster the multi-drone deployment tasks, thereby obtaining a deployment task set corresponding to each drone.

[0009] For each of the aforementioned delivery task sets, the optimized Ocean Predator algorithm is used to plan the paths for each UAV to complete all delivery tasks in the corresponding delivery task set, thereby obtaining the network communication task plan for each UAV.

[0010] In one embodiment, finding a set of connector node locations that maximize the connectivity area in the area to be restored includes:

[0011] The area to be restored is divided into multiple circular sub-regions of different areas. Each sub-region is represented on a two-dimensional plane by the coordinates of its center point and its radius.

[0012] The connection area of ​​each connector node is obtained based on the position coordinates and sensing radius of each connector node;

[0013] Whether a sub-region is covered by a connector node is defined based on the distance from the center of the sub-region to the center of the connector node and the sensing radius of the connector.

[0014] The regional connectivity rate of all connector nodes in the region to be restored is defined as the ratio of the area of ​​the unconnected sub-area covered by the connector node set to the total area of ​​the region to be restored.

[0015] Find a set of connector node coordinates that maximizes the connectivity of the region.

[0016] In one embodiment, a 0-1 perception model is used to obtain a set of connector node coordinates that maximize the connectivity of the region.

[0017] In one embodiment, the k-means clustering algorithm is used when clustering the delivery tasks.

[0018] In one embodiment, when using the optimized Ocean Predator algorithm for path planning for each UAV, the objective function is expressed as:

[0019]

[0020] In the above formula, the set of deployment tasks corresponding to a certain drone is represented as V={v1,v2,v3,...,v A The deployment order of the connector nodes is represented as T = {t1, t2, t3, ..., t}. A}, where t i =V(i=1,...,A), and t i+1 =t1.

[0021] In one embodiment, the optimized marine predator algorithm combines an ε-greedy strategy with the marine predator algorithm, and in different iteration stages, the strategy adopted is determined according to a preset ε value and a random number.

[0022] In one embodiment, the optimized marine predator algorithm includes:

[0023] In the initial stage of iteration, if the random number is less than the preset ε value, the first strategy is used to search within a large range; if the random number is greater than or equal to the preset ε value, the second or third strategy is randomly used to search.

[0024] During the mid-stage of the iteration, if the random number is less than the preset ε value, the second strategy is randomly adopted to search within a small range; if the random number is greater than or equal to the preset ε value, the first or third strategy is randomly adopted to search.

[0025] In the final stage of iteration, if the random number is less than the preset ε value, the third strategy is randomly adopted to search within a local range; if the random number is greater than or equal to the preset ε value, the first or second strategy is randomly adopted to search.

[0026] This application also provides a network communication task planning device based on multiple unmanned aerial vehicles, the device comprising:

[0027] The communication task information acquisition module is used to acquire the area of ​​the connection to be restored, the number of connector nodes, and the initial positions of multiple drones;

[0028] The task location acquisition module is used to find a set of connector node settings that maximizes the connectivity area in the area to be restored, and use this set of locations as the target locations for multi-UAV deployment tasks.

[0029] The drone task allocation module is used to cluster the multi-drone deployment tasks with the initial position of each drone as the cluster center, with the goal of minimizing the total flight path of each drone, to obtain a deployment task set corresponding to each drone.

[0030] The UAV mission route planning module is used to plan the path for each UAV to complete all delivery tasks in the corresponding delivery task set using the optimized ocean predator algorithm for each delivery task set, thereby obtaining the network communication task plan for each UAV.

[0031] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0032] Obtain the area of ​​the region to be reconnected, the number of connector nodes, and the initial positions of multiple drones;

[0033] Find a set of connector node locations that maximize the connectivity area in the area to be restored, and use this set of locations as the target locations for multi-drone deployment missions.

[0034] With the goal of minimizing the total flight path of each drone, the initial position of each drone is used as the cluster center to cluster the multi-drone deployment tasks, thereby obtaining a deployment task set corresponding to each drone.

[0035] For each of the aforementioned delivery task sets, the optimized Ocean Predator algorithm is used to plan the paths for each UAV to complete all delivery tasks in the corresponding delivery task set, thereby obtaining the network communication task plan for each UAV.

[0036] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0037] Obtain the area of ​​the region to be reconnected, the number of connector nodes, and the initial positions of multiple drones;

[0038] Find a set of connector node locations that maximize the connectivity area in the area to be restored, and use this set of locations as the target locations for multi-drone deployment missions.

[0039] With the goal of minimizing the total flight path of each drone, the initial position of each drone is used as the cluster center to cluster the multi-drone deployment tasks, thereby obtaining a deployment task set corresponding to each drone.

[0040] For each of the aforementioned delivery task sets, the optimized Ocean Predator algorithm is used to plan the paths for each UAV to complete all delivery tasks in the corresponding delivery task set, thereby obtaining the network communication task plan for each UAV.

[0041] The aforementioned method, apparatus, equipment, and medium for planning network communication tasks based on multiple unmanned aerial vehicles (UAVs) find a set of connector node locations in the area to be restored that maximizes the connected area, and use this set of locations as the target locations for multi-UAV deployment tasks. With the goal of minimizing the total flight path of each UAV, the initial positions of each UAV are used as cluster centers to cluster the multi-UAV deployment tasks, resulting in a deployment task set for each UAV. Then, for each deployment task set, an optimized Ocean Predator algorithm is used to plan the paths for each UAV to complete all deployment tasks in its corresponding set, thus obtaining the network communication task plan for each UAV. This method can effectively and quickly restore communication in most areas of the area to be restored. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of a local communication network connection in one embodiment;

[0043] Figure 2 This is a flowchart illustrating a network communication task planning method based on multiple UAVs in one embodiment;

[0044] Figure 3 This is a flowchart illustrating the network communication task planning steps based on multiple UAVs in one embodiment;

[0045] Figure 4 This is a schematic diagram of regional connectivity in one embodiment;

[0046] Figure 5 This is a schematic diagram showing the location distribution of unconnected sub-regions in a region to be restored during an experiment.

[0047] Figure 6 This is a schematic diagram showing the locations of sub-regions and connectors in a region to be restored during an experiment.

[0048] Figure 7 This is a schematic diagram of the clustering results for a drone-deployed connector task in an experiment.

[0049] Figure 8 This is a schematic diagram illustrating the path planning for each drone to deploy multiple wireless connectors in scenarios 1 and 2 of an experiment.

[0050] Figure 9 This is a structural block diagram of a network communication task planning device based on multiple UAVs in one embodiment;

[0051] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] In this application, as Figure 2 As shown, a network communication task planning method based on multiple UAVs is provided, which specifically includes the following steps:

[0054] Step S100: Obtain the area of ​​the connectivity region to be restored, the number of connector nodes, and the initial positions of multiple drones.

[0055] Step S110: In the area to be restored, find a set of connector node locations that maximize the connection area, and use this set of locations as the target locations for the multi-drone deployment mission.

[0056] Step S120: With the goal of minimizing the total flight path of each UAV, the initial position of each UAV is used as the cluster center to cluster the multi-UAV deployment tasks, thereby obtaining a deployment task set corresponding to each UAV.

[0057] Step S130: For each delivery task set, the optimized ocean predator algorithm is used to plan the path for each UAV to complete all delivery tasks in the corresponding delivery task set, so as to obtain the network communication task plan for each UAV.

[0058] In this application, an improved marine predator algorithm is proposed and combined with a clustering algorithm to deploy wireless network connectors using multiple UAVs. The improved algorithm is used for wireless network connector location estimation and multi-UAV motion planning.

[0059] After addressing the issue of deploying wireless network connectors using multiple drones, it is transformed into multi-drone task planning, which includes both task allocation and task path planning.

[0060] Furthermore, the communication network recovery model is constructed into three parts: wireless network connector location estimation in step S110, UAV multitasking in step S120, and UAV motion planning in step S130.

[0061] like Figure 3 The diagram illustrates the overall process of a multi-UAV network connection task. Since wireless connectors often have limited capabilities in real-world environments when faced with sudden communication failures, it's necessary to select their locations based on the location of the communication interruption area to maximize their effectiveness. Because multiple UAVs can be used for delivery, tasks can be divided through clustering, and then movement routes can be planned according to the tasks assigned to each UAV. For the wireless connector location estimation problem, the input is the location of the communication interruption area. For the multi-UAV task clustering problem, the input is the wireless connector performance parameters, and the output is the wireless connector deployment location. For the multi-UAV task clustering problem, the input is the estimated location of the wireless connector and the number of available UAVs, and the output is the wireless connector number group to be deployed by each UAV. For the multi-UAV movement planning problem, the input is the wireless connector number group to be deployed by each UAV and the UAV's starting position information, and the output is the deployment order and flight route of each UAV.

[0062] In step S100, the area of ​​the unconnected area to be restored, the number of connectors to be deployed, the coverage radius of each connector (i.e., the sensing radius), the number of drones participating in the deployment of connectors, and the initial position of each drone are first obtained.

[0063] In step S110, finding a set of connector node positions in the region to be restored that maximizes the connected area includes: first, dividing the region to be restored into multiple circular sub-regions of different areas, each sub-region represented on a two-dimensional plane by the coordinates of its center point and radius; obtaining the connected area of ​​each connector node based on its position coordinates and sensing radius; defining whether a sub-region is covered by a connector node based on the distance from the center of the sub-region to the center of the connector node and the sensing radius of the connector; defining the regional connectivity rate of all connector nodes in the region to be restored as the ratio of the area of ​​unconnected sub-regions covered by the connector node set to the total area of ​​the region to be restored; and finding a set of connector node coordinates that maximizes the regional connectivity rate.

[0064] In this embodiment, a 0-1 perception model is used to obtain a set of connector node coordinates that maximize the regional connectivity rate. In other embodiments, a grid method can also be used to deploy connectors, dividing all regions into grids of equal size and randomly or sequentially selecting grids to deploy connectors.

[0065] Specifically, area communication is achieved through area wireless connectors. When an area is within the communication range of the wireless connector, that area can be considered a communication area, such as... Figure 4 As shown.

[0066] Furthermore, in a two-dimensional plane, the connectivity range of a connector node is a circle centered at the node with radius R. n The circular area, R n This is called the connectivity radius. The connectivity radius is related to the physical characteristics of the built-in components of the node. Assume the position coordinates of the connector node n are (x... n ,y n In the 0-1 perception model, for any point p(x) on the plane... p ,y p If the probability of a node n detecting a point p within the region is expressed as:

[0067]

[0068] In formula (1), Let be the Euclidean distance between points and .

[0069] Assuming that N identical wireless communication nodes are deployed in an unconnected area, and that the location coordinates of each communication node have been initialized, and that the sensing radius of each communication node is r, then the entire set of communication nodes can be represented as:

[0070] Node{x1,...,x N}(2)

[0071] In formula (2), node i ={x i ,y i ,r}, represents the node (x i ,y i Let r be the center of a circle and r be the sensing radius. Simultaneously, assume the entire region to be restored has n circular sub-regions, meaning the entire region to be restored is divided into multiple circular sub-regions. The coordinates of the center point of each sub-region are represented as (x, y). Then, the distance between the center point of a sub-region and the center of a certain connector node is represented as:

[0072]

[0073] The event of an unconnected sub-region being connected by a connector node is defined as c. i The event occurs when the target point (x, y) is detected by the sensor node. i cover:

[0074]

[0075] Next, the connectivity rate of all connector nodes in the unconnected sub-regions is defined as the ratio of the area of ​​the unconnected sub-regions covered by the connector node set to the area of ​​the total unconnected region, i.e., the region to be restored, as shown in the formula:

[0076]

[0077] This way, we only need to find a set of connector node locations that maximize the area of ​​the connected region to be restored. These connector node locations will then be used as the deployment locations for the drones, and will also generate the tasks to be planned for subsequent drone deployments.

[0078] In step S120, when multiple drones jointly complete the network reconnection task, they start from different directions to minimize the total flight path of the drones. Since the number of drones is predetermined, clustering is used to determine the delivery tasks for each drone. The clustering attempt divides the dataset X into K clusters C = {C1, C2, ..., C...}. K}, so that it satisfies the following conditions: i,j=1,...,K i≠j. The initial position of each UAV is used as the cluster center. The deployment tasks, i.e., the deployment positions of each connector node, are clustered, and the resulting clusters are assigned to the corresponding UAVs for execution.

[0079] In this embodiment, the k-means clustering algorithm is used when clustering the delivery tasks.

[0080] Specifically, clustering divides large amounts of data into categories with different characteristics. K-means clustering is a cyclic iterative algorithm. Suppose we want to cluster N samples into K clusters. First, select K points as initial centroids. Then, assign all observations to the cluster containing each centroid. Each cluster contains several observations. Calculate the average of all sample points in the K clusters and use them as the K centroids for the second iteration. Then, repeat steps 2 and 3 until convergence (the centroids no longer change or the specified number of iterations is reached), at which point the clustering process ends.

[0081] Furthermore, given a sample set X = {x1,...,x...} n The goal of the K-means clustering algorithm is to minimize the mean square error (MSE) of the resulting clusters. The mean square error (MSE) can be expressed as...

[0082]

[0083] In formula (6), u i Cluster C represents the cluster formed by the clustering. i The mean of all points. Reducing this mean squared error loss makes the vectors within the cluster more compact, resulting in better classification performance.

[0084] In step S130, during drone path planning, certain rules are set to ensure the drone deploys the wireless connectors in sequence. This sequence is obtained using a swarm intelligence algorithm. The standard description of the Traveling Salesman Problem (TSP) is as follows: Given A wireless sensor nodes, a drone starts from one of these nodes, deploys all the wireless connectors along the way, but visits each node exactly once, and finally returns to the starting node. How should the route be planned to minimize the drone's path?

[0085] Let the set of deployment tasks for a certain drone be V = {v1, v2, v3, ..., v A The deployment order of the connector nodes is T = {t1, t2, t3, ..., t}. A}, where t i =V(i=1,...,A), and t i+1 If t1 = t1, then the objective function of the problem is as follows:

[0086]

[0087] The optimal value of the objective function is the shortest path cost for deploying all wireless communication drones.

[0088] In this embodiment, the optimized marine predator algorithm combines the marine predator algorithm with an ε-greedy strategy. At different iteration stages, the strategy adopted is determined based on a preset ε value and a random number.

[0089] Specifically, the Marine Predator Algorithm (MPA) is a metaheuristic algorithm inspired by the predation process of marine organisms. Because marine predators choose movement strategies between levy and brown, it exhibits good optimization performance. The theoretical foundation of the MPA primarily involves the behavior and ecology of marine organisms, swarm intelligence, and metaheuristic thinking. By incorporating these theoretical principles into the algorithm design, the algorithm can simulate the optimization strategies of marine predators and be applied to optimization and search to solve practical problems.

[0090] Furthermore, the MPA algorithm initializes the prey position randomly within the search space to initiate the optimization process. The MPA algorithm comprises several different iterative phases. The mathematical description is as follows:

[0091] X0 = X min +rand(X max -X min (8)

[0092] In the early stages of iteration, when the predator is faster than the prey, the mathematical description of the MPA optimization process based on the exploration strategy is as shown in formula (9), which can be regarded as strategy A1.

[0093]

[0094] In formula (9), stepsize i R is the movement step size. B Elite is a normally distributed Brownian walk random vector. i Prey is an elite matrix constructed by top predators. i To be a prey matrix with the same dimension as the elite matrix, P is the term-by-term multiplication operator, P equals 0.5, R is a uniform random vector within [0, 1], n is the population size, and iter and max_iter are the current and maximum number of iterations, respectively.

[0095] In the middle of the iteration, when the predator and prey have the same speed, the prey is responsible for development based on the Lévy walk strategy; the predator is responsible for exploration based on the Brownian walk strategy, and gradually shifts from exploration strategy to development strategy. The mathematical descriptions of development and exploration are as shown in Equations (10) and (11), which can be regarded as strategy A2.

[0096]

[0097] In formulas (10) and (11), RL Let be a random vector following a Lévy distribution; CF = (1 - iter / max_iter) (2iter / max_iter) CF controls the adaptive parameters of the predator's movement step size.

[0098] At the end of the iteration, when the predator is slower than the prey, the predator adopts an exploitation strategy based on Levy's walk. Its mathematical description is shown in formula (12), which can be regarded as strategy A3.

[0099]

[0100] In formula (12), the effect of fish aggregation devices (FADs) or eddies is considered. Fish aggregation devices (FADs) or eddies often alter the foraging behavior of marine predators. This strategy enables the MPA to overcome premature convergence and escape local extrema during the optimization process. Its mathematical description is as follows:

[0101]

[0102] In formula (13), FADs is the influence probability, which is preferably chosen as 0.2. U is a binary vector, r is a random number in [0,1], and r1 and r2 are the random indices of the prey matrix.

[0103] In other words, existing ocean predator algorithms employ a fixed strategy at different iteration stages. This leads to several problems, including: 1. Slow convergence: A fixed strategy may cause the algorithm to move slowly within the search space, failing to effectively explore potential high-quality solutions. Therefore, more iterations may be needed to find a satisfactory solution. 2. Getting trapped in local optima: Due to the unchanging strategy, the algorithm may linger near local optima, missing opportunities to find the global optimum. This is particularly evident in complex optimization problems. 3. Insufficient adaptability: Fixed strategies lack the ability to dynamically adjust to problem characteristics or the current search state. Different stages may require different search strategies to adapt to the complexity and variability of the problem. 4. Reduced diversity: During the search process, a fixed strategy may reduce the diversity of the search population, making the search process more homogeneous and reducing the breadth of the algorithm's exploration in the search space. 5. Premature convergence: If the algorithm determines its strategy too early at a certain stage, it may narrow the search range, thereby reducing the overall performance of the algorithm.

[0104] In this approach, an ε-greedy strategy was chosen to improve the Ocean Predator algorithm. The ε-greedy algorithm is a balanced approach between exploration and exploitation, and is a commonly used policy selection method in reinforcement learning. Within the theoretical framework of reinforcement learning, the ε-greedy strategy, as a behavioral strategy, provides a simple and intuitive method for agents to select actions in their environment.

[0105] Specifically, the optimized marine predator algorithm includes the following steps: In the initial iteration phase, if the random number is less than a preset ε value, the first strategy (strategy A1 above) is used to search within a large range; if the random number is greater than or equal to the preset ε value, either the second strategy (strategy A2 above) or the third strategy (strategy A3 above) is randomly used for searching. In the middle iteration phase, if the random number is less than the preset ε value, the second strategy is randomly used to search within a small range; if the random number is greater than or equal to the preset ε value, either the first strategy or the third strategy is randomly used for searching. In the final iteration phase, if the random number is less than the preset ε value, the third strategy is randomly used to search within a local range; if the random number is greater than or equal to the preset ε value, either the first strategy or the second strategy is randomly used for searching.

[0106] In this embodiment, pseudocode for implementing the optimized marine predator algorithm described above is also provided, as shown below:

[0107]

[0108]

[0109] Furthermore, in this embodiment, pseudocode for implementing steps S120 to S130 is also proposed, as follows:

[0110]

[0111]

[0112] In this paper, the effectiveness of the proposed method is also demonstrated through simulation experiments.

[0113] In the simulation experiment, the area to be connected was set to be 500km long and 500km wide. Six drones were used to transmit wireless connectors, with 50 connectors in total, and a signal radius of 15km. The maximum radius of the connected sub-area was 30km, and the minimum radius was 5km. The theoretical communication range of a GSM base station is tens of kilometers. Considering the obstruction from intermediate buildings and different types of equipment, this range was set to 15km. Due to the large area, long-range drones such as Global Eagle, Heron, and Orion were selected. The location of the sub-area to be connected was randomly generated in the spatial region, such as... Figure 5 As shown.

[0114] The motion constraints of unmanned aerial vehicle (UAV) systems mainly manifest as dynamic constraints, collision avoidance constraints, and energy constraints. Mission planning is not at the operational level, but rather at the tactical level. This paper presents a broad experimental scope, primarily considering UAV mission allocation and path planning. Since the speed and model of the UAVs are unrestricted, and weather conditions during flight are unknown, the impact of dynamic constraints such as turning radius and pitch angle on the total range is not considered. For the collision avoidance problem of UAV swarms, this paper employs a method of setting different flight altitudes to avoid collisions during movement. Regarding the UAV endurance problem, a UAV model with an endurance exceeding the experimentally calculated total range while maintaining a certain safety margin should be used.

[0115] Five swarm intelligence optimization algorithms were used for position estimation in the experiment, including Particle Swarm Optimization (PSO), Harris Eagle Optimization (HHO), Slime Mucin Algorithm (SMA), Marine Predator Algorithm (MPA), and the ε-Marine Predator Algorithm (ε-MPA), which is the optimized Marine Predator Algorithm proposed in this paper. These algorithms include both classic and recently emerging swarm intelligence algorithms. The algorithm parameter settings are shown in Table 1, where the ε-MPA and MPA algorithms have the same parameter settings, with the ε value set to 0.8.

[0116] Table 1

[0117]

[0118] First, regarding the estimation of the deployment location of the connectors, this experiment sets the population size at 30 and the maximum number of iterations at 500. Generally, in natural disasters or emergencies, communication is considered successfully restored when a certain percentage of the area is restored. This percentage can be determined based on geographical scope, population size, or the requirements of specific key locations; the actual scale threshold may vary depending on the type of disaster and the emergency situation. Regarding the communication reconnection problem in this paper, theoretically there is no limit to the number of wireless network connectors, and the communication reconnection rate can reach up to 100%. However, due to the limitations of wireless network connectors, a standard is set: a communication reconnection rate of 90% is considered a successful connection. Based on the above, under the condition of meeting the requirements, the closer the communication reconnection rate is to 100%, the better.

[0119] The results of 25 independent runs are shown in Table 2. Table 2 lists the connectivity rates obtained by different algorithms in the experiment, which can more clearly reflect the algorithm's optimization capability for the location of wireless network connectors. We use two indicators, average connectivity rate and optimal connectivity rate, to measure the algorithm results. The Best indicator represents the best connectivity rate obtained by a certain intelligent optimization algorithm in these 25 experiments, reflecting the algorithm's optimization capability. The Mean indicator represents the average connectivity rate obtained by a certain intelligent optimization algorithm in these 25 experiments, reflecting the average level of algorithm optimization. The experimental results show that among the five algorithms—PSO, HHO, SMA, MPA, and ε-MPA—the ε-MPA algorithm yields the best results, exceeding the second-ranked MPA algorithm by 0.77%. Since these five algorithms are all metaheuristic algorithms, used to obtain satisfactory solutions within an acceptable time, they are approximate solution algorithms and have a certain degree of randomness; therefore, they do not reach the global optimum in every run. It can be seen that the ε-MPA algorithm yields the best average indicator and connectivity rate, with an optimal connectivity rate of 97.89%. Therefore, the ε-MPA algorithm is used to estimate the location of the wireless connector. When the coverage reaches its optimum in the 14th run, its location is as follows: Figure 6 As shown.

[0120] Table 2: Reconnaissance Coverage Results of Five Optimization Algorithms

[0121]

[0122] Next, for task clustering, the number of drones was set in the experiment, and the K-means algorithm was used for clustering. The number of clusters was set to be the same as the number of drones, and the initial cluster centers were randomly selected. The clustering results are as follows. Figure 7 As shown in the figure. To verify the impact of different numbers of drones on the clustering results, we set the number of clusters to 1–4. For the K-means algorithm, the choice of initial cluster centers also affects the experimental results, so we chose a random method to eliminate errors. The results from different numbers of clusters show that the clustering results are good and the distribution is reasonable. The clustering results will determine the location and number of network connectors that each drone needs to transport, which is a necessary condition for drone path planning.

[0123] Finally, for UAV path planning, when obtaining the UAV mission clustering results, a swarm intelligence algorithm is used for motion planning, with a maximum of 500 iterations. The results of 25 independent runs are shown in Table 3. HHO, SMA, MPA, and ε-MPA all achieve the same optimal level. EMPA has the strongest optimization ability in most scenarios, MPA has the best average optimization effect, and ε-MPA is second. Because a greedy strategy is used to solve the exploration and utilization problem, overemphasizing exploration can cause some fluctuations.

[0124] Table 3: Total Distance Covered by the Drone Swarm

[0125]

[0126] In Scenario 1, when there are 4 drones and optimal planning is achieved, starting from different points, the paths for each drone to complete the task are 677.153, 672.089, 844.839, and 946.268, respectively. The paths for each drone are as follows: Figure 8 As shown on the left. The total path length used by the drone swarm to complete the network connectivity task is 3140.35 km. In scenario two, when there are 4 drones and the optimal planning is obtained, starting from the same starting point (250, 0), the paths for each drone to complete the task using the EMPA algorithm are 1302.005, 864.092, 929.326, and 1318.693, respectively. The paths of each drone are shown below. Figure 8 As shown on the right, the total distance traveled by the drone swarm to complete the deployment of the wireless network connector was 4414.116 kilometers.

[0127] In the aforementioned multi-UAV network communication task planning method, a multi-UAV network communication task planning model was established to address network connectivity issues in adverse environments such as earthquakes and fires. A K-means clustering algorithm combined with the ε-MPA algorithm was proposed. Through wireless network connector location estimation, multi-UAV task clustering, and motion planning, efficient network communication in certain disaster environments is achieved. Experiments compared the wireless connector location estimation and delivery path planning results of PSO, HHO, SMA, MPA, and ε-MPA, showing that ε-MPA has the best performance in most cases, maximizing network connectivity range with the shortest flight distance for UAV swarms. This method further enhances the optimization capability of MPA by balancing exploration and utilization during the optimization process using an ε-greedy strategy. The ε-MPA algorithm achieved optimal performance in solving the wireless connector location estimation problem and in multiple scenarios of multi-UAV path planning. As a metaheuristic algorithm for finding approximate solutions, ε-MPA is suitable for various problems with complex search spaces and optimization objectives, such as scheduling, organization optimization, and resource allocation. It can help find optimal or suboptimal solutions, optimize decision-making, and improve resource utilization.

[0128] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order in which these steps are executed, and they can be performed in other orders. Furthermore, Figure 1At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0129] In one embodiment, such as Figure 9 As shown, a network communication task planning device based on multiple UAVs is provided, including: a communication task information acquisition module 200, a task deployment location acquisition module 210, a UAV task allocation module 220, and a UAV task route planning module 230, wherein:

[0130] The communication task information acquisition module 200 is used to acquire the area of ​​the connection area to be restored, the number of connector nodes, and the initial positions of multiple UAVs;

[0131] The deployment task location acquisition module 210 is used to find a set of connector node settings that maximizes the connection area in the area to be restored, and use this set of locations as the target locations for multi-UAV deployment tasks.

[0132] The UAV task allocation module 220 is used to cluster the multi-UAV deployment tasks with the initial position of each UAV as the cluster center, with the goal of minimizing the total flight path of each UAV, to obtain a deployment task set corresponding to each UAV.

[0133] The UAV mission route planning module 230 is used to plan the path for each UAV to complete all delivery tasks in the corresponding delivery task set using the optimized ocean predator algorithm for each delivery task set, so as to obtain the network communication task plan for each UAV.

[0134] Specific limitations regarding the network communication task planning device based on multiple UAVs can be found in the limitations of the network communication task planning method based on multiple UAVs mentioned above, and will not be repeated here. Each module in the aforementioned network communication task planning device based on multiple UAVs can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0135] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a network communication task planning method based on multiple unmanned aerial vehicles (UAVs). The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0136] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0138] Obtain the area of ​​the region to be reconnected, the number of connector nodes, and the initial positions of multiple drones;

[0139] Find a set of connector node locations that maximize the connectivity area in the area to be restored, and use this set of locations as the target locations for multi-drone deployment missions.

[0140] With the goal of minimizing the total flight path of each drone, the initial position of each drone is used as the cluster center to cluster the multi-drone deployment tasks, thereby obtaining a deployment task set corresponding to each drone.

[0141] For each of the aforementioned delivery task sets, the optimized Ocean Predator algorithm is used to plan the paths for each UAV to complete all delivery tasks in the corresponding delivery task set, thereby obtaining the network communication task plan for each UAV.

[0142] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0143] Obtain the area of ​​the region to be reconnected, the number of connector nodes, and the initial positions of multiple drones;

[0144] Find a set of connector node locations that maximize the connectivity area in the area to be restored, and use this set of locations as the target locations for multi-drone deployment missions.

[0145] With the goal of minimizing the total flight path of each drone, the initial position of each drone is used as the cluster center to cluster the multi-drone deployment tasks, thereby obtaining a deployment task set corresponding to each drone.

[0146] For each of the aforementioned delivery task sets, the optimized Ocean Predator algorithm is used to plan the paths for each UAV to complete all delivery tasks in the corresponding delivery task set, thereby obtaining the network communication task plan for each UAV.

[0147] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0148] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A network communication task planning method based on multiple unmanned aerial vehicles (UAVs), characterized in that, The method includes: Obtain the area of ​​the region to be reconnected, the number of connector nodes, and the initial positions of multiple drones; Find a set of connector node locations that maximize the connectivity area in the area to be restored, and use this set of locations as the target locations for multi-UAV deployment missions. Finding a set of connector node locations that maximizes the connectivity area in the area to be restored includes: dividing the area to be restored into multiple circular sub-regions of different areas, each sub-region represented on a two-dimensional plane by the coordinates of its center point and radius; obtaining the connectivity area of ​​each connector node based on its position coordinates and sensing radius; defining whether a sub-region is covered by a connector node based on the distance from the center of the sub-region to the center of the connector node and the connector's sensing radius; defining the regional connectivity rate of all connector nodes in the area to be restored as the ratio of the unconnected sub-area covered by the connector node set to the total area of ​​the area to be restored; and finding a set of connector node coordinates that maximizes the regional connectivity rate. With the goal of minimizing the total flight path of each drone, the initial position of each drone is used as the cluster center to cluster the multi-drone deployment tasks, thereby obtaining a deployment task set corresponding to each drone. For each of the aforementioned delivery task sets, the optimized Ocean Predator algorithm is used to plan the paths for each UAV to complete all delivery tasks in the corresponding delivery task set, thereby obtaining the network communication task plan for each UAV.

2. The network communication task planning method according to claim 1, characterized in that, A set of connector node coordinates that maximizes the connectivity rate of the region is obtained by using a 0-1 perception model.

3. The network communication task planning method according to claim 2, characterized in that, When clustering the delivery tasks, the k-means clustering algorithm is used.

4. The network communication task planning method according to any one of claims 1-3, characterized in that, When using the optimized Ocean Predator algorithm for path planning for each drone, the objective function is expressed as: In the above formula, the set of deployment tasks corresponding to a certain drone is represented as: The deployment order of the connector nodes is represented as follows: ,in, ,and .

5. The network communication task planning method according to claim 4, characterized in that, The optimized marine predator algorithm combines the marine predator algorithm with... - A greedy strategy, which, at different iteration stages, also relies on a pre-defined... The strategy used to determine the value and random number.

6. The network communication task planning method according to claim 5, characterized in that, The optimized marine predator algorithm includes: In the initial stage of iteration, if the random number is less than the preset value... If the value is greater than or equal to the preset value, the first strategy is used to search within a wide range. If the value is not specified, then the second or third strategy will be randomly selected for the search. In the middle stage of the iteration, if the random number is less than the preset value... If the value is greater than or equal to the preset value, then the second strategy is randomly used to search within a small range. If the value is not specified, then either the first or third strategy will be randomly selected for the search. In the final stage of the iteration, if the random number is less than the preset value... If the value is greater than or equal to the preset value, then a third strategy is randomly adopted to search within a local range. If the value is not specified, then either the first strategy or the second strategy will be randomly selected for the search.

7. A network communication task planning device based on multiple unmanned aerial vehicles (UAVs), characterized in that, The device includes: The communication task information acquisition module is used to acquire the area of ​​the area to be restored, the number of connector nodes, and the initial positions of multiple drones; The deployment task location acquisition module is used to find a set of connector node settings that maximize the connectivity area in the area to be restored, and to use this set of locations as the target locations for multi-UAV deployment tasks. Finding a set of connector node settings that maximizes the connectivity area in the area to be restored includes: dividing the area to be restored into multiple circular sub-regions of different areas, each sub-region represented on a two-dimensional plane by the coordinates of its center point and its radius; obtaining the connectivity area of ​​each connector node based on its position coordinates and sensing radius; defining whether a sub-region is covered by a connector node based on the distance from the center of the sub-region to the center of the connector node and the connector's sensing radius; defining the regional connectivity rate of all connector nodes in the area to be restored as the ratio of the unconnected sub-area covered by the connector node set to the total area of ​​the area to be restored; and finding a set of connector node coordinates that maximizes the regional connectivity rate. The drone task allocation module is used to cluster the multi-drone deployment tasks with the initial position of each drone as the cluster center, with the goal of minimizing the total flight path of each drone, to obtain a deployment task set corresponding to each drone. The UAV mission route planning module is used to plan the path for each UAV to complete all delivery tasks in the corresponding delivery task set using the optimized ocean predator algorithm for each delivery task set, thereby obtaining the network communication task plan for each UAV.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images