Kmeans-based unmanned aerial vehicle cluster communication networking reconstruction method and device

Abstract

The application relates to a Kmeans-based unmanned aerial vehicle cluster communication networking reconstruction method and device. The method comprises the following steps: acquiring position information of unmanned aerial vehicle nodes in unmanned aerial vehicle cluster communication networking as a data set. The distance between the position information of an initial cluster head unmanned aerial vehicle and the position information of the unmanned aerial vehicle nodes is calculated according to the data set, an internal cluster distance set is obtained, and a new unmanned aerial vehicle cluster is determined according to the internal cluster distance set. The mean value of the position information of the unmanned aerial vehicle nodes in the new unmanned aerial vehicle cluster is obtained by using a Kmeans algorithm, clustering iteration is carried out, the center position information is obtained, and the unmanned aerial vehicle cluster communication networking is reconstructed according to the center position information. By using the method, unmanned aerial vehicle cluster flexible self-networking clustering and cluster head selection reconstruction in a high dynamic environment can be realized, and the stability of large-scale unmanned aerial vehicle cluster communication networking in an emergency rescue environment can be improved.

Description

Technical Field

[0001] This application relates to the field of UAV swarm communication networking technology, and in particular to a method and apparatus for reconstructing UAV swarm communication networks based on Kmeans. Background Technology

[0002] Drone swarm communication network architectures can be broadly categorized into three types: star-shaped drone swarms, mesh-shaped drone swarms, and hybrid networks based on terminal-to-delivery (D2D) technology. Star-shaped drone swarms use a single drone as the swarm center or a ground base station as the center, with other drones acting as communication terminals. They employ traditional cellular communication, with service data and control signaling relayed through the swarm center or ground base station. Network resources are centrally managed by the base station, and interference between users is controllable. However, in this architecture, all communication between drones requires relaying through the base station, consuming uplink and downlink resources, resulting in significant latency and low spectrum utilization. Furthermore, the low power of individual drones limits their energy, leading to short communication distances between drones and ground base stations. Attacks on base stations or excessive distances can cause network collapse. Mesh-shaped drone swarms, also known as distributed networks, have less dependence on ground base stations compared to star-shaped networks. Communication within the network is achieved through multi-hop forwarding, and terrain factors have minimal impact on the network. Therefore, the network coverage area can be adjusted in real-time according to mission requirements. This networking method results in a complex autonomous distributed cluster network that lacks a central hub for unified scheduling and management of the cluster. Interference is uncontrollable, and the link latency is high with complex routing strategies. Summary of the Invention

[0003] Therefore, it is necessary to provide a method and apparatus for reconstructing UAV swarm communication networks based on K-means to address the aforementioned technical problems.

[0004] A method for reconstructing UAV swarm communication networks based on K-means is provided for use in UAV swarm communication networks, wherein the UAV swarm communication network architecture includes multiple UAV swarms. The method includes:

[0005] The location information of drone nodes in the drone swarm communication network is obtained as a dataset.

[0006] The distance between the initial cluster head UAV's position information and the UAV node's position information is calculated based on the dataset to obtain the internal cluster distance set. The new UAV cluster is then determined based on the internal cluster distance set.

[0007] The K-means algorithm is used to calculate the mean of the location information of UAV nodes in the new cluster of the UAV swarm, and then iterative clustering is performed to obtain the center location information. The UAV swarm communication network is reconstructed based on the center location information.

[0008] In one embodiment, the method further includes: constructing a drone swarm communication network, dividing the drone swarm communication network into several drone subgroups, determining the initial cluster head drone in the drone subgroup, and obtaining the location information of drone nodes in the drone subgroup as a dataset through the initial cluster head drone.

[0009] In one embodiment, the method further includes: calculating the distance between the position information of the initial cluster head drone and the position information of the drone node in each drone subgroup according to the dataset, obtaining the internal cluster distance set from the drone node to each initial cluster head drone, classifying the initial cluster head drone and the drone node corresponding to the minimum value of the internal cluster distance set into the same new drone cluster, and continuing until all drone nodes in the drone cluster communication network have completed the division of new drone clusters, resulting in several new drone clusters.

[0010] In one embodiment, the method further includes: using the Kmeans algorithm to calculate the mean of the location information of drone nodes in each new cluster of drone cluster, obtaining the center drone node corresponding to the mean, and performing clustering iterative clustering of the location information of the center drone node according to a preset number of iterations to obtain the center location information.

[0011] In one embodiment, the method further includes: using the drone node corresponding to the central location as the leader drone of the new drone cluster, the leader drone establishes a D2D base communication connection with the remaining drone nodes in the new drone cluster through a control signaling link, and establishes a D2D cross-cluster communication connection with the leader drones of the other new drone clusters in the drone cluster communication network, and reconstructs the drone cluster communication network based on the leader drone and the new drone cluster.

[0012] In one embodiment, the drone swarm includes a cluster leader drone and several member drones. Member drones communicate with each other via data service links within the cluster (D2D).

[0013] A K-means-based UAV swarm communication network reconstruction device, the device comprising:

[0014] The dataset acquisition module is used to acquire the location information of drone nodes in the drone swarm communication network as a dataset.

[0015] The UAV swarm new cluster acquisition module is used to calculate the distance between the position information of the initial cluster head UAV and the position information of the UAV nodes based on the dataset, obtain the internal cluster distance set, and determine the new UAV swarm based on the internal cluster distance set.

[0016] The network reconstruction module is used to use the Kmeans algorithm to calculate the mean of the location information of the UAV nodes in the new cluster of the UAV swarm, and to perform clustering iteratively to obtain the center location information. Based on the center location information, the UAV swarm communication network is reconstructed.

[0017] 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:

[0018] The location information of drone nodes in the drone swarm communication network is obtained as a dataset.

[0019] The distance between the initial cluster head UAV's position information and the UAV node's position information is calculated based on the dataset to obtain the internal cluster distance set. The new UAV cluster is then determined based on the internal cluster distance set.

[0020] The K-means algorithm is used to calculate the mean of the location information of UAV nodes in the new cluster of the UAV swarm, and then iterative clustering is performed to obtain the center location information. The UAV swarm communication network is reconstructed based on the center location information.

[0021] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0022] The location information of drone nodes in the drone swarm communication network is obtained as a dataset.

[0023] The distance between the initial cluster head UAV's position information and the UAV node's position information is calculated based on the dataset to obtain the internal cluster distance set. The new UAV cluster is then determined based on the internal cluster distance set.

[0024] The K-means algorithm is used to calculate the mean of the location information of UAV nodes in the new cluster of the UAV swarm, and then iterative clustering is performed to obtain the center location information. The UAV swarm communication network is reconstructed based on the center location information.

[0025] The aforementioned method and apparatus for reconstructing UAV swarm communication networks based on K-means calculates the distance between the initial cluster head UAV's location information and the location information of other UAV nodes based on the dataset, re-selects the cluster head UAV, and establishes the shortest and optimal communication line. Communication between UAVs within the same cluster is uniformly controlled by the cluster head, and communication connections between new UAV clusters are established by the cluster head UAV. This method saves data, bandwidth, and other resources while improving information transmission efficiency. Based on this, iterative clustering is continuously performed, and the network can be expanded according to actual task needs through collaborative communication between cluster centers. It has strong robustness and resilience, can achieve overall resource scheduling, has a central point that can be flexibly replaced, and realizes flexible self-organizing network clustering and cluster head selection and reconstruction of UAV swarms in highly dynamic environments. This improves the stability of large-scale UAV swarm communication networks in emergency rescue environments and enhances the flexibility of self-organizing networks. Attached Figure Description

[0026] Figure 1 This is an application scenario diagram of a UAV swarm communication network reconstruction method based on Kmeans in one embodiment;

[0027] Figure 2 This is a flowchart illustrating a method for reconstructing a drone swarm communication network based on Kmeans in one embodiment.

[0028] Figure 3 A model diagram of clustering and selecting cluster centers for a drone swarm in one embodiment;

[0029] Figure 4 This is a schematic diagram illustrating the re-clustering and center selection results of a drone swarm after being disturbed, as shown in one embodiment.

[0030] Figure 5 This is a structural block diagram of a UAV swarm communication network reconstruction device based on Kmeans in one embodiment;

[0031] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0032] 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.

[0033] The K-means-based UAV swarm communication network reconstruction method provided in this application can be applied to, for example... Figure 1The diagram illustrates a D2D-based drone swarm communication network application environment. This D2D-based drone swarm network comprises multiple drone sub-swarms, i.e., drone clusters (small FANET3). Within each cluster, a leader drone is selected as the leader drone, and the remaining drone nodes serve as member drones. Furthermore, communication between drone clusters is achieved through communication links established by the cluster leader (i.e., the leader drone). Communication between member drones is achieved through data service links established using D2D technology. Communication between the leader drone and several member drones within the same cluster is achieved through control signaling links. The leader drone also performs overall control of the drone sub-swarm.

[0034] In one embodiment, such as Figure 2 As shown, a method for reconstructing UAV swarm communication networks based on K-means is provided, and this method is applied to... Figure 1 Taking D2D-based drone swarm communication networking as an example, the following steps are included:

[0035] Step 202: Obtain the location information of the drone nodes in the drone swarm communication network as a dataset.

[0036] Specifically, the location information of drone nodes can be obtained through the drone's own GPS positioning, inertial measurement unit (IMU) and other sensors. In D2D-based drone swarm communication network, the leader drone within the drone swarm obtains the node location information of the member drones in the same swarm. Using the inter-cluster communication link, the leader drones coordinate and interact with each other to obtain their own location information, thereby obtaining the location information of all nodes in the entire drone swarm communication network and using it as the dataset under the current networking conditions.

[0037] Step 204: Calculate the distance between the initial cluster head UAV's position information and the UAV node's position information based on the dataset to obtain the internal cluster distance set, and determine the new UAV cluster based on the internal cluster distance set.

[0038] Specifically, for each drone node, the distance to the initial cluster head drone node is calculated, and it is assigned to the cluster with the closest distance.

[0039] Step 206: The Kmeans algorithm is used to calculate the mean of the location information of the UAV nodes in the new cluster of the UAV swarm, and then iterative clustering is performed to obtain the center location information. The UAV swarm communication network is reconstructed based on the center location information.

[0040] Specifically, the average x-coordinate and average y-coordinate of the location information of each drone node are calculated based on the dataset:

[0041]

[0042] Where, x i For the first i The x-coordinate of each drone node, y i For the first i The ordinate of each drone node, The x-coordinate of the center position, The ordinate of the center position, N This represents the number of drone nodes in a new cluster of drone swarms.

[0043] Furthermore, the Euclidean distance between the coordinates of each drone and the average coordinate center is calculated sequentially:

[0044]

[0045] Where, x j Let y be the x-coordinate of the j-th drone node excluding the drone node at the center position. j Let be the ordinate of the j-th drone node excluding the drone node at the center position. The x-coordinate of the center position, Let d be the ordinate of the center position, N be the number of drones in the new drone cluster excluding the drone node corresponding to the center position, and d be the number of drones in the cluster. j Let be the Euclidean real distance of the j-th drone node excluding the drone node at the center position. Then, the drone node with the closest coordinates to the center node is determined to be the center node.

[0046] In one embodiment, such as Figure 3 As shown, an environmental experiment simulation was created, assuming a drone swarm of 40 sorties. Based on mission requirements, the drones were divided into 3 clusters. Clustering was performed to obtain drone clusters, and cluster centers were selected. The centers and ranges of each cluster were marked on the graph, and communication was established between the centers of each cluster after they were determined.

[0047] Specifically, when the rescue environment changes dynamically, if four drones are lost during the rescue, the drone swarm can quickly adjust its position and re-cluster, based on the flexibility of the wireless mesh network, to obtain new clusters and cluster centers. Figure 4 As shown, the rapid dynamic reconstruction caused by the increase or decrease in the number of drones and changes in their classification was successfully simulated.

[0048] Therefore, it can be seen that by adopting this method, when the emergency rescue scenario changes, the D2D-based drone swarm communication network can be re-clustered and the cluster center can be selected through Kmeans, which can realize the dynamic and flexible reconstruction of a large-scale drone network.

[0049] In the aforementioned K-means-based UAV swarm communication network reconstruction method, the distance between the initial cluster head UAV's location information and the UAV node's location information is calculated based on the dataset. The cluster head UAV is then re-selected, thereby establishing the shortest and optimal communication line. Communication between UAVs within the same cluster is uniformly controlled by the cluster head, and communication connections between new UAV clusters are established by the cluster head UAV. This UAV swarm communication network saves data, bandwidth, and other resources while improving information transmission efficiency. Based on this, continuous clustering and iterative clustering can be performed. According to actual task needs, network expansion can be carried out through collaborative communication between cluster centers. It has strong robustness and resilience, can achieve overall resource scheduling, has a central point that can be flexibly replaced, and realizes flexible self-organizing network clustering and cluster head selection and reconstruction of UAV swarms in highly dynamic environments. This improves the stability of large-scale UAV swarm communication networks in emergency rescue environments and the flexibility of self-organizing networks.

[0050] In one embodiment, a drone swarm communication network is constructed, which is divided into several drone subgroups. An initial cluster leader drone is determined in each drone subgroup, and the location information of drone nodes in the drone subgroup is obtained as a dataset through the initial cluster leader drone.

[0051] In one embodiment, the distance between the position information of the initial cluster head drone and the position information of the drone node in each drone subgroup is calculated based on the dataset to obtain the internal cluster distance set from the drone node to each initial cluster head drone. The initial cluster head drone and the drone node corresponding to the minimum value of the internal cluster distance set are grouped into the same new drone cluster. This process continues until all drone nodes in the drone cluster communication network have completed the division of new drone clusters, resulting in several new drone clusters.

[0052] In one embodiment, the K-means algorithm is used to calculate the mean of the location information of drone nodes in each new cluster of drone cluster, and the center drone node corresponding to the mean is obtained. The location information of the center drone node is then clustered iteratively according to a preset number of iterations to obtain the center location information.

[0053] In one embodiment, the drone node corresponding to the central position is used as the leader drone of the new drone cluster. The leader drone establishes a D2D base communication connection with the remaining drone nodes in the new drone cluster through the control signaling link, and establishes a D2D cross-cluster communication connection with the leader drones of the other new drone clusters in the drone cluster communication network. The drone cluster communication network is reconstructed based on the leader drone and the new drone cluster.

[0054] It is worth noting that if the network cluster center is destroyed, the drone swarm will generate a new cluster center. Damage to any drone terminal will not affect the normal operation of other drones, thereby improving the overall robustness and resilience of the network. At the same time, drone swarm communication networking can add new drone nodes and expand the cluster size. Utilizing the scalability advantage of mesh self-organizing networks, it can achieve large-area multi-drone network communication and coordination, thereby enabling timely dynamic reconstruction of network communication.

[0055] In one embodiment, the drone swarm includes a cluster leader drone and several member drones. Member drones communicate with each other via data service links within the cluster (D2D).

[0056] In one embodiment, the K-means algorithm can be used for clustering and cluster head selection in drone applications. The cluster head plays a crucial role in a drone swarm, responsible for coordinating and controlling the entire swarm's actions. Using the K-means algorithm, drones in the swarm can be divided into several clusters, and then a drone from each cluster can be selected as the cluster head to achieve collaborative control of the drone swarm. The specific implementation process is as follows:

[0057] (1) The location information of the drones in the drone cluster is used as a dataset, and the location information of each drone is represented by a vector.

[0058] (2) K UAVs were randomly selected as the initial cluster heads.

[0059] (3) Calculate the distance between each UAV and k cluster heads, and classify it according to the cluster head it is closest to.

[0060] (4) Update the cluster head position of each cluster, that is, calculate the average position information of all UAVs in the cluster as the new center point.

[0061] (5) Repeat steps (3) and (4) until the center point of the cluster no longer changes or the preset number of iterations is reached.

[0062] (6) Select the UAV closest to the cluster head from each cluster as the cluster head.

[0063] It should be understood that, although Figure 2 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 herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2At 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.

[0064] In one embodiment, such as Figure 5 As shown, a UAV swarm communication network reconstruction device based on K-means is provided, including: a dataset acquisition module 502, a UAV swarm new cluster acquisition module 504, and a network reconstruction module 506, wherein:

[0065] The dataset acquisition module 502 is used to acquire the location information of drone nodes in the drone cluster communication network as a dataset.

[0066] The UAV swarm new cluster acquisition module 504 is used to calculate the distance between the position information of the initial cluster head UAV and the position information of the UAV nodes based on the dataset, obtain the internal cluster distance set, and determine the new UAV swarm based on the internal cluster distance set.

[0067] The network reconstruction module 506 is used to use the Kmeans algorithm to calculate the mean of the location information of the UAV nodes in the new cluster of the UAV cluster, and to perform clustering iteratively to obtain the center location information, and to reconstruct the UAV cluster communication network based on the center location information.

[0068] Specific limitations regarding the K-means-based UAV swarm communication network reconstruction device can be found in the limitations of the K-means-based UAV swarm communication network reconstruction method described above, and will not be repeated here. Each module in the aforementioned K-means-based UAV swarm communication network reconstruction device 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 corresponding operations of each module.

[0069] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6As 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 K-means-based method for reconstructing a UAV swarm communication network. 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.

[0070] Those skilled in the art will understand that Figures 5-6 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.

[0071] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to perform the following steps:

[0072] The location information of drone nodes in the drone swarm communication network is obtained as a dataset.

[0073] The distance between the initial cluster head UAV's position information and the UAV node's position information is calculated based on the dataset to obtain the internal cluster distance set. The new UAV cluster is then determined based on the internal cluster distance set.

[0074] The K-means algorithm is used to calculate the mean of the location information of UAV nodes in the new cluster of the UAV swarm, and then iterative clustering is performed to obtain the center location information. The UAV swarm communication network is reconstructed based on the center location information.

[0075] In one embodiment, when the processor executes the computer program, it further implements the following steps: calculating the distance between the position information of the initial cluster head drone and the position information of the drone node in each drone sub-swarm according to the dataset, obtaining the internal cluster distance set from the drone node to each initial cluster head drone, classifying the initial cluster head drone and the drone node corresponding to the minimum value of the internal cluster distance set into the same new drone cluster, and continuing until all drone nodes in the drone swarm communication network have completed the division of new drone clusters, resulting in several new drone swarm clusters.

[0076] 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:

[0077] The location information of drone nodes in the drone swarm communication network is obtained as a dataset.

[0078] The distance between the initial cluster head UAV's position information and the UAV node's position information is calculated based on the dataset to obtain the internal cluster distance set. The new UAV cluster is then determined based on the internal cluster distance set.

[0079] The K-means algorithm is used to calculate the mean of the location information of UAV nodes in the new cluster of the UAV swarm, and then iterative clustering is performed to obtain the center location information. The UAV swarm communication network is reconstructed based on the center location information.

[0080] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: calculating the distance between the position information of the initial cluster head drone and the position information of the drone node in each drone sub-swarm according to the dataset, obtaining the internal cluster distance set from the drone node to each initial cluster head drone, classifying the initial cluster head drone and the drone node corresponding to the minimum value of the internal cluster distance set into the same new drone cluster, and continuing until all drone nodes in the drone swarm communication network have completed the division of new drone clusters, resulting in several new drone swarm clusters.

[0081] 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.

[0082] 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.

[0083] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. 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 application should be determined by the appended claims.

Claims

1. A method for reconstructing UAV swarm communication networks based on K-means, characterized in that, Used in unmanned aerial vehicle (UAV) swarm communication networking, the UAV swarm communication networking architecture includes multiple UAV swarms; The method includes: The location information of the drone nodes in the drone swarm communication network is obtained as a dataset. A drone swarm communication network is constructed, which is divided into several drone subgroups. An initial cluster leader drone is determined in the drone subgroup, and the location information of drone nodes in the drone subgroup is obtained through the initial cluster leader drone as a dataset. The distance between the position information of the initial cluster head UAV and the position information of the UAV node is calculated based on the dataset to obtain the internal cluster distance set. The new UAV cluster is determined based on the internal cluster distance set. Based on the dataset, the distance between the position information of the initial cluster head drone and the position information of the drone node in each drone sub-swarm is calculated to obtain the internal cluster distance set from the drone node to each initial cluster head drone. The initial cluster head drone corresponding to the minimum value of the internal cluster distance set and the drone node are grouped into the same new drone cluster. This process continues until all drone nodes in the drone swarm communication network have completed the division of the new drone clusters, resulting in several new drone swarm clusters. The K-means algorithm is used to calculate the mean of the location information of the drone nodes in the new cluster of the drone cluster, and then iteratively clusters them to obtain the center location information. The specific steps are as follows: the K-means algorithm is used to calculate the mean of the location information of the drone nodes in each new cluster of the drone cluster, and the center drone node corresponding to the mean is obtained. The location information of the center drone node is then iteratively clustered according to a preset number of iterations to obtain the center location information. The UAV swarm communication network is reconstructed based on the central location information.

2. The method according to claim 1, characterized in that, Reconstructing the UAV swarm communication network based on the central location information includes: The drone node corresponding to the central location serves as the leader drone of the new drone cluster. The leader drone establishes a D2D base communication connection with the remaining drone nodes in the new drone cluster through a control signaling link, and establishes a D2D cross-cluster communication connection with the leader drones of the other new drone clusters in the drone cluster communication network. The drone cluster communication network is then reconstructed based on the leader drone and the new drone cluster.

3. The method according to any one of claims 1 to 2, characterized in that, The drone swarm consists of a head drone and several member drones; The member drones communicate with each other via a data service link within the D2D cluster.

4. A UAV swarm communication network reconstruction device based on K-means, characterized in that, The apparatus for implementing the method according to any one of claims 1 to 3, the apparatus comprising: The dataset acquisition module is used to acquire the location information of the drone nodes in the drone cluster communication network as a dataset. The UAV swarm new cluster acquisition module is used to calculate the distance between the position information of the initial cluster head UAV and the position information of the UAV nodes based on the dataset, obtain the internal cluster distance set, and determine the new UAV swarm based on the internal cluster distance set. The network reconstruction module is used to use the K-means algorithm to calculate the mean of the location information of the UAV nodes in the new cluster of the UAV cluster, and to perform clustering iteratively to obtain the center location information, and to reconstruct the UAV cluster communication network based on the center location information.

5. 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 3.

6. 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 3.

Images