Unmanned aerial vehicle edge cooperative computing method and system for unmanned aerial vehicle airport cluster

Abstract

The invention relates to the technical field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle edge cooperative computing method and system for an unmanned aerial vehicle airport cluster, and the method comprises the following steps: analyzing the type of an unmanned aerial vehicle and a real-time network data flow based on an unmanned aerial vehicle communication network, evaluating the congestion condition of the current network, and determining the congestion condition of the current network according to the network condition and the data type; and adjusting a data compression ratio and transmission priorities of the plurality of data packets, optimizing a data transmission path, and generating a transmission efficiency optimization record. According to the method, the transmission efficiency and the network response speed are improved by evaluating the network congestion condition, adjusting the data compression proportion and priority and optimizing the data transmission path, the stability of the network and the reliability of task execution are guaranteed by combining real-time monitoring of node activity and rapidly recognizing fault nodes, the processing task is refined into a plurality of processes, and the efficiency of the network is improved. And the processing capabilities of the plurality of nodes are analyzed, so that the scientificity and the high efficiency of task allocation are ensured, and the cooperative efficiency of the unmanned aerial vehicle is optimized.

Description

Technical Field

[0001] The present invention relates to the field of drone control technology, and in particular to a drone edge collaborative computing method and system for drone airport clusters. Background Art

[0002] The field of UAV control technology focuses on the automated operation and management of UAVs, including flight control systems, navigation technology, task allocation and execution, and communication and collaboration with the ground and other UAVs. It involves flight stability control, flight path planning, obstacle avoidance algorithms, real-time data transmission, and condition-based autonomous decision-making. By integrating sensor data processing, flight control algorithms, and communication technologies, it supports the effective operation of UAVs in a variety of environments and mission scenarios, aiming to improve the operational efficiency and safety of UAVs in a variety of environments and achieve autonomy and adaptability in multi-task environments.

[0003] Among them, the UAV edge collaborative computing method refers to the joint completion of tasks through collaboration between UAVs or between UAVs and control systems, including real-time position and status exchange between UAVs, dynamic task redistribution based on status and real-time coordination of instruction transmission, instant information sharing through wireless communication protocols, and the use of control algorithms to adjust the behavior and response of UAVs. Combined with the control logic for real-time monitoring and adjustment of the tasks performed by UAVs, it provides real-time data exchange and instruction execution support to achieve effective collaboration between UAVs.

[0004] Traditional drone edge collaborative computing methods have certain limitations in handling data transmission and task collaboration in large-scale drone networks. They lack sufficient flexibility and real-time performance in real-time assessment and dynamic adjustment of network congestion, which makes drones prone to communication delays and data loss when performing multiple tasks. In terms of fault identification and task process management, they rely on preset parameters and static processing logic, lack sufficient adaptability and foresight, and may lead to inefficient execution and slow response in rapidly changing mission environments. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a drone edge collaborative computing method and system for drone airport clusters.

[0006] To achieve the above objectives, the present invention adopts the following technical solution, which is a UAV edge collaborative computing method for UAV airport clusters, including the following steps: S1: Based on the drone communication network, analyze the drone type and real-time network data flow, evaluate the current network congestion, and adjust the data compression ratio and transmission priority of multiple data packets according to the network status and data type, optimize the data transmission path, and generate transmission efficiency optimization records; S2: Using the transmission efficiency optimization record, constructing a network topology diagram based on the connection status between nodes, monitoring the activity status of multiple nodes in real time, identifying faulty nodes by detecting abnormal activity data, and generating a faulty node detection record; S3: Analyze the task based on the fault node detection record and the input UAV task information, identify the task type, decompose the task into multiple processes and build a process list to generate a task process analysis result; S4: Based on the task process analysis results, by real-time monitoring the task processing efficiency and task completion rate of multiple nodes in the drone swarm, analyzing the performance level and task processing capability of multiple nodes, and generating node performance evaluation information; S5: According to the node performance evaluation information, based on the task processing capabilities and task process decomposition list of multiple nodes, and considering the task processing efficiency, the task allocation parameters of the target UAV task are adjusted to obtain the UAV collaboration parameters.

[0007] As a further solution of the present invention, the transmission efficiency optimization record specifically includes network congestion conditions, data compression ratio parameters, and data transmission paths; the fault node detection record includes the fault node location, abnormal activity data, and node connection status information; the task process analysis result specifically refers to the task type, task process list, and task decomposition record; the node performance evaluation information includes node task processing efficiency, task completion rate, and node performance level score; and the UAV collaboration parameters specifically include task processing efficiency information, task allocation list, and node efficiency monitoring record.

[0008] As a further solution of the present invention, based on the drone communication network, the drone type and real-time network data flow are analyzed, the current network congestion status is evaluated, and according to the network status and data type, the data compression ratio and the transmission priority of multiple data packets are adjusted, and the data transmission path is optimized. The specific steps of generating a transmission efficiency optimization record are as follows: S101: Based on the UAV communication network, identify the types of multiple UAVs in the network, monitor the data flow of the communication network in real time, including data flow and data transmission delay, evaluate the congestion status of the communication network, and obtain network congestion analysis results; S102: Based on the network congestion analysis result and taking into account data transmission efficiency, adjusting the data compression ratio, and adjusting the transmission priority of multiple data packets according to the data type, to generate data packet adjustment parameters; S103: Based on the data packet adjustment parameters, the data transmission path is adjusted by comparing the transmission delays before and after the adjustment, and a transmission efficiency optimization record is generated.

[0009] As a further solution of the present invention, the specific formula for evaluating the congestion status of the communication network is: ; in, Represents the network congestion index, Representative The network traffic value of each data point, Representatives and The time factor associated with each data point, Representative The data transmission delay of data points, Representative The weight of the data point, Represents the total number of data points within the analysis window, Represents the sequence number of the data point currently being considered.

[0010] As a further solution of the present invention, the transmission efficiency optimization record is used to construct a network topology diagram based on the connection status between nodes, the activity status of multiple nodes is monitored in real time, and the faulty nodes are identified by detecting abnormal activity data. The steps of generating the faulty node detection record are specifically as follows: S201: Using the transmission efficiency optimization record, construct a network topology diagram according to the connection status between multiple nodes in the network; S202: Based on the network topology diagram, monitor the computing load, transmission flow and delay data of multiple nodes in real time, record the node activity status, and generate a node activity monitoring record; S203: Analyze the node activity monitoring record, analyze the data features of various node status data in real time, detect abnormal data and identify faulty nodes, and obtain faulty node detection records.

[0011] As a further solution of the present invention, the specific formula for detecting abnormal data and identifying faulty nodes is: ; in, represents the node abnormality, Representative Dimensional monitoring data characteristics, Representative The historical average of the dimension data, Representative The standard deviation of the dimensional data, Represents the total number of dimensions of monitoring data, Represents the dimension number of the data point currently being considered.

[0012] As a further solution of the present invention, based on the fault node detection record and the input drone mission information, the task is analyzed, the task type is identified, the task is decomposed into multiple processes and a process list is constructed. The steps of generating the task process analysis result are specifically as follows: S301: Based on the fault node detection record, by analyzing the input UAV mission information, the target mission is classified into monitoring, transportation, and communication, and a mission type identification result is obtained; S302: Based on the task type identification result, by analyzing the execution processes and processing requirements of various tasks, decompose the target task into multiple processing processes, including data collection, data transmission and data analysis, and generate a task decomposition process list; S303: Analyze and mark the requirements of multiple processing flows on the performance of multiple nodes according to the task decomposition process list, and generate a task process analysis result.

[0013] As a further solution of the present invention, based on the task process analysis results, by real-time monitoring the task processing efficiency and task completion rate of multiple nodes in the drone swarm, analyzing the performance level and task processing capability of multiple nodes, and generating node performance evaluation information, the specific steps are: S401: Based on the task flow analysis results and the model information of the multiple drones in the fleet, the hardware resource configurations of the multiple drones are identified, including CPU type, memory capacity, and sensor type, and node hardware configuration information is generated. S402: Based on the node hardware configuration information, monitor the computing resource usage of the node in real time when processing multiple tasks, and generate a computing resource usage record; S403: Analyze the computing resource occupancy record, analyze the performance levels of multiple nodes based on the task processing efficiency and completion rate of the nodes, evaluate the task processing capabilities, and generate node performance evaluation information.

[0014] As a further solution of the present invention, according to the node performance evaluation information, based on the task processing capabilities and task process decomposition list of multiple nodes, taking into account the task processing efficiency, the task allocation parameters of the target UAV task are adjusted, and the steps of obtaining the UAV collaboration parameters are specifically as follows: S501: Analyze the node performance evaluation information, extract performance data of multiple UAV nodes, identify the node's ability to handle various types of tasks, including the processing speed and efficiency of various tasks, and generate a node task processing capability table; S502: Based on the node task processing capability table and the task process decomposition list, matching processing processes for multiple nodes according to processing requirements of multiple task types to obtain processing task matching results; S503: Based on the processing task matching result and taking into account the task processing efficiency, the parameters of the UAV collaborative work are adjusted, including task allocation time, resource allocation and priority setting, to generate UAV collaborative parameters.

[0015] A drone edge collaborative computing system for drone airport clusters, the drone edge collaborative computing system for drone airport clusters is used to execute the above-mentioned drone edge collaborative computing method for drone airport clusters, and the system includes: The network flow analysis module is based on the UAV communication network, monitoring the data flow of the communication network in real time, analyzing the data traffic, evaluating the network congestion situation, adjusting the data compression ratio and transmission priority according to the data type, optimizing the data transmission path, and generating transmission efficiency optimization records; The network topology construction module uses the transmission efficiency optimization record to evaluate the connection status between multiple nodes in the network, construct a network topology diagram, monitor the activity status of the nodes, identify abnormal activity data, detect faulty nodes, and generate faulty node detection records; The task decomposition module analyzes the task type according to the fault node detection record and the input drone task information, decomposes the task into multiple execution processes, builds a process list, and generates a task process analysis result; The performance monitoring module monitors the task processing efficiency and task completion rate of multiple nodes in the drone swarm in real time based on the task process analysis results, evaluates the performance level and computing power of multiple nodes, and generates node performance evaluation information; The collaborative scheduling module adjusts the allocation parameters of the UAV tasks according to the node performance evaluation information, the task processing capabilities of multiple nodes and the task process decomposition list, optimizes the task processing efficiency, and generates UAV collaborative parameters.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In this invention, by evaluating the network congestion situation, adjusting the data compression ratio and priority, and optimizing the data transmission path, the transmission efficiency and network response speed are improved. Combined with the real-time monitoring of node activities, the faulty nodes are quickly identified to ensure the stability of the network and the reliability of task execution. By breaking down the processing tasks into multiple processes and analyzing the processing capabilities of multiple nodes, the scientific nature and efficiency of task allocation are ensured, and the collaborative efficiency of drones is optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 This is a detailed flow chart of S1 of the present invention; Figure 3 This is a detailed flow chart of S2 of the present invention; Figure 4 This is a detailed flow chart of S3 of the present invention; Figure 5 This is a detailed flow chart of S4 of the present invention; Figure 6 This is a detailed flow chart of S5 of the present invention; Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0019] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the described features. In the description of this application, "plurality" means two or more, unless otherwise specifically specified.

[0020] In the description of this application, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art will recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0021] See also Figure 1 The present invention provides a technical solution, a UAV edge collaborative computing method for UAV airport clusters, comprising the following steps: S1: Based on the drone communication network, analyze the drone type and real-time network data flow, evaluate the current network congestion, and adjust the data compression ratio and transmission priority of multiple data packets according to the network status and data type, optimize the data transmission path, and generate transmission efficiency optimization records; S2: Uses transmission efficiency optimization records to build a network topology diagram based on the connection status between nodes, monitors the activity status of multiple nodes in real time, identifies faulty nodes by detecting abnormal activity data, and generates faulty node detection records; S3: Based on the fault node detection record and the input drone mission information, the task is analyzed, the task type is identified, the task is decomposed into multiple processes and a process list is constructed to generate the task process analysis results; S4: Based on the task process analysis results, the task processing efficiency and task completion rate of multiple nodes in the UAV swarm are monitored in real time, the performance level and task processing capability of multiple nodes are analyzed, and node performance evaluation information is generated; S5: According to the node performance evaluation information, based on the task processing capabilities and task flow decomposition list of multiple nodes, and considering the task processing efficiency, the task allocation parameters of the target UAV task are adjusted to obtain the UAV collaboration parameters.

[0022] Transmission efficiency optimization records specifically include network congestion conditions, data compression ratio parameters, and data transmission paths. Fault node detection records include fault node locations, abnormal activity data, and node connection status information. Task process analysis results specifically refer to task types, task process lists, and task decomposition records. Node performance evaluation information includes node task processing efficiency, task completion rate, and node performance level scores. UAV collaboration parameters specifically include task processing efficiency information, task allocation lists, and node efficiency monitoring records.

[0023] See also Figure 2 ,Based on the UAV communication network, analyze the UAV type and real-time network data flow, evaluate the current network congestion, and adjust the data compression ratio and transmission priority of multiple data packets according to the network status and data type, and optimize the data transmission path.,The specific steps for generating transmission efficiency optimization records are as follows: S101: Based on the UAV communication network, identify the types of multiple UAVs in the network, monitor the data flow of the communication network in real time, including data flow and data transmission delay, evaluate the congestion status of the communication network, and obtain network congestion analysis results; The specific formula for evaluating the congestion status of the communication network is: ; in, Represents the network congestion index, Representative The network traffic value of each data point, Representatives and The time factor associated with each data point, Representative The data transmission delay of data points, Representative The weight of the data point, Represents the total number of data points within the analysis window, Represents the sequence number of the data point currently being considered.

[0024] formula: ; Detailed explanation of the formula and the process of formula calculation and derivation: The formula is used to calculate the network congestion index, which reflects the real-time congestion status of the drone communication network; Parameter meaning and setting value: For the The network traffic value of each data point; For the The time factor associated with each data point; For the Data transmission delay of each data point; For the The weight of each data point; the total number of data points considered for the analysis; Suppose there are three data points, where MB / s, , ms, ; Substitute the parameters into the formula for calculation: ; ; ; ; result This shows the degree of congestion in the current state of the network, indicating that the UAV communication network may need to adjust its data transmission strategy during peak hours to alleviate congestion.

[0025] S102: Based on the network congestion analysis results and taking into account data transmission efficiency, the data compression ratio is adjusted, and the transmission priorities of multiple data packets are adjusted according to the data types to generate data packet adjustment parameters; In sub-step S102, a data compression algorithm, such as Huffman coding technology, is used to adjust the data compression ratio according to the importance and urgency of each type of data, so that critical data can be transmitted quickly and non-critical data can have a higher compression rate. The adjustment is performed through an automated data management system, which automatically proposes a compression ratio based on the network status and data type. The packet transmission priority is adjusted through a priority scheduling algorithm. The algorithm reorders the sending order of the data packets according to the data type and service quality requirements to reduce the waiting time of critical data. The process includes analyzing the data type, calculating and setting the priority of each type of data, and updating it in real time to the configuration of network routers and switches to improve the efficiency of data circulation in the network and generate packet adjustment parameters.

[0026] S103: Based on the data packet adjustment parameters, the data transmission path is adjusted by comparing the transmission delays before and after the adjustment, and a transmission efficiency optimization record is generated; In sub-step S103, the adjusted network data traffic and delay are monitored, and network performance testing tools such as Wireshark and Ping tools are used to measure the response time of key links and nodes. The data transmission efficiency before and after the adjustment is compared, including during high-traffic periods. The target test results are used to analyze the efficiency changes of the data transmission path. If it is found that the adjusted delay still does not meet the expected target, the routing algorithm is adjusted or the bandwidth is increased. Path optimization is implemented through dynamic routing protocols, including Open Shortest Path First or Border Gateway Protocol. According to real-time traffic and delay data, the routing table is dynamically adjusted to optimize the data transmission path and generate a transmission efficiency optimization record.

[0027] See also Figure 3 ,Use transmission efficiency optimization records, build a network topology diagram based on the connection status of nodes, monitor the activity status of multiple nodes in real time, and identify faulty nodes by detecting abnormal activity data.,The steps for generating faulty node detection records are as follows: S201: Using the transmission efficiency optimization record, construct a network topology diagram according to the connection status between multiple nodes in the network; In sub-step S201, network analysis software, such as NetBrain, is used in combination with recorded data, such as the data transmission rate and delay information of each node, to construct a network topology diagram, which shows the connection status and communication quality between each node in the network. The network topology diagram is created by an automated graphics generation tool, which includes information such as the physical location of the node, connection type, and bandwidth utilization. The data collection work involved in the process involves data collection, integration, and visual presentation, ensuring that network managers can intuitively see the structure and key performance indicators of the entire network, providing decision support for network maintenance and optimization.

[0028] S202: Based on the network topology diagram, monitor the computing load, transmission flow and delay data of multiple nodes in real time, record the node activity status, and generate a node activity monitoring record; In sub-step S202, a real-time network monitoring tool, such as SolarWinds Network Performance Monitor, is used to monitor the computing load, transmission traffic, and data delay of each node in the network. The target monitoring tool can provide real-time data updates and historical data comparisons. The computing load data includes CPU and memory usage, and the transmission traffic data records the number of bytes transmitted per second. The delay data represents the time interval for data to be transmitted from one node to another. The monitoring process is fully automatic. The monitoring system will automatically record the status that exceeds the normal range according to the preset threshold and generate node activity monitoring records. The target records help network administrators quickly identify potential network bottlenecks and nodes with degraded performance.

[0029] S203: Analyze node activity monitoring records, analyze data features of various node status data in real time, detect abnormal data and identify faulty nodes, and obtain faulty node detection records; The specific formula for detecting abnormal data and identifying faulty nodes is: ; in, represents the node abnormality, Representative Dimensional monitoring data characteristics, Representative The historical average of the dimension data, Representative The standard deviation of the dimensional data, Represents the total number of dimensions of monitoring data, Represents the dimension number of the data point currently being considered.

[0030] formula: ; Detailed explanation of the formula and the process of formula calculation and derivation: The formula is used to calculate the abnormality of a node, evaluate the health of multiple nodes in the drone network and identify potential failures; Parameter meaning and setting value: : No. Real-time monitoring data of each node; : No. The historical average CPU usage of each node; : No. The standard deviation of the historical data of CPU usage of each node; : the total number of nodes; Assume that the monitoring data points represent the CPU usage data of 5 different nodes, where: %, %, %; Substitute the parameters into the formula for calculation: ; ; ; ; ; ; ; result It shows the degree of deviation of nodes in the network. The value is used to indicate node performance problems or potential failures, maintaining the stability and efficiency of the network.

[0031] See also Figure 4 ,According to the fault node detection record and the input UAV mission ,information, the task is analyzed, the task type is identified, the ,task is decomposed into multiple processes and a process list is constructed.,The specific steps for generating the task process analysis results are: S301: Based on the fault node detection record, the input UAV mission information is analyzed to classify the target mission, including monitoring, transportation, and communication, and obtain a mission type identification result; In sub-step S301, the types of various tasks such as monitoring tasks, transportation tasks and communication tasks are identified. The process is implemented through a task classification system. The system has built-in multiple predefined task templates and classification algorithms, such as decision tree classifiers, to identify and classify tasks. Task information includes the starting point of the task, estimated time, required resources, etc. The target data is input from the console of the drone system, and various tasks are automatically classified, and a detailed list of each task type is generated. This list is updated in the drone operation interface for the operator to refer to and adjust the task allocation strategy to obtain the task type identification result.

[0032] S302: Based on the task type identification results, by analyzing the execution processes and processing requirements of various tasks, the target task is decomposed into multiple processing processes, including data collection, data transmission, and data analysis, and a task decomposition process list is generated; In sub-step S302, task decomposition technology is used to analyze the processes required for each type of task execution, such as data collection, data transmission and data analysis. Task decomposition is completed through a series of process analysis tools, such as using flowchart software such as Microsoft Visio to depict the steps of each task. The processing requirements of each task are determined according to the operating capabilities and resource availability of the drone. For example, monitoring tasks may require high-frequency data collection, while transportation tasks emphasize path efficiency. During the decomposition process, the requirements and expected results of each step are defined, including the required data type, collection frequency, data volume and transmission speed, to help the operation team clarify the details and requirements of each task process, ensure the effective execution of the task, and generate a comprehensive task decomposition process list.

[0033] S303: Analyze and mark the requirements of multiple processing processes for various node performances based on the task decomposition process list, and generate task process analysis results; In sub-step S303, the computing power, storage space, and network bandwidth required for each process are calculated. The performance requirement analysis uses a series of performance evaluation tools and simulation software, such as MATLAB and Simulink. The target tools simulate the performance of various data flows and processing processes in the actual network environment. Through target simulation, it is identified which nodes may become performance bottlenecks and which nodes have sufficient resources to handle high-load tasks. The specific requirements of each process for node performance are marked and recorded in a comprehensive task process analysis result report. The report is provided to the network management and task scheduling teams so that they can optimize network configuration and task scheduling strategies.

[0034] See also Figure 5 ,According to the results of task process analysis, by real-time monitoring the task processing efficiency and task completion rate of multiple nodes in the UAV swarm, the performance level and task processing capability of multiple nodes are analyzed, and the specific steps for generating node performance evaluation information are as follows: S401: Based on the task process analysis results and the model information of multiple drones in the fleet, the hardware resource configuration of the multiple drones is identified, including CPU type, memory capacity, and sensor type, and node hardware configuration information is generated; In sub-step S401, the device management software is used to read the system information of each drone, including key hardware parameters such as CPU type, memory capacity and sensor type. For drones using high-performance computing tasks, the software checks whether its CPU is a multi-core processor, whether the memory capacity is large enough, and whether it is equipped with high-precision sensors. It also evaluates whether the target hardware configuration meets the needs of current and future tasks. All target information is automatically summarized by the system and a node hardware configuration information report is generated. The report includes a detailed hardware configuration data table and performance evaluation of each drone, providing a basis for subsequent task allocation and resource optimization.

[0035] S402: Based on the node hardware configuration information, monitor the computing resource usage of the node in real time when processing multiple tasks, and generate a computing resource usage record; In sub-step S402, resource monitoring tools such as Nagios or Zabbix are used to monitor in real time the computing resource usage of each drone node in the execution of various tasks. The target tool can track in detail the CPU utilization, memory usage and storage occupancy of each node during task execution. During the monitoring process, if resource usage is found to exceed expectations, the system will automatically record the target abnormality and generate real-time computing resource usage records. The records reflect the resource usage status of each node and help identify which drones may affect the task execution efficiency due to insufficient resources. Through this real-time monitoring, the management team can adjust resource allocation in time to ensure that all tasks can proceed smoothly.

[0036] S403: Analyze computing resource usage records, analyze the performance levels of multiple nodes based on the task processing efficiency and completion rate of the nodes, evaluate the task processing capabilities, and generate node performance evaluation information; In sub-step S403, the performance of each drone node in mission execution is evaluated. Data analysis and performance evaluation software, such as Tableau and Excel, are used to analyze the task processing efficiency and task completion rate of each node. The average processing time, error rate, and proportion of successfully completed tasks for each node are calculated. Based on the target data, the team generates a node performance evaluation report, which describes in detail the performance level and task processing capabilities of each node. It provides accurate performance information to the drone operation and maintenance team, helping them identify nodes with lower performance and take measures to optimize or replace equipment to improve the operational efficiency and reliability of the entire fleet.

[0037] See also Figure 6 ,According to the node performance evaluation information, according to the task processing capabilities and task flow decomposition list of multiple nodes, considering the task processing efficiency, the task allocation parameters of the target UAV task are adjusted, and the steps to obtain the UAV collaboration parameters are as follows: S501: Analyze node performance evaluation information, extract performance data of multiple UAV nodes, identify the node's ability to handle various types of tasks, including the processing speed and efficiency of various tasks, and generate a node task processing capability table; In sub-step S501, SAS or SPSS is used to extract key performance data for each drone node, including task completion time, success rate, and computing resource consumption. The performance data of each drone node is analyzed through a complex data processing process to determine its ability to handle different task types—such as monitoring, communication, or logistics transportation. This includes evaluating the processing speed and efficiency of each node under high and low load conditions, and generating a node task processing capacity table. This table lists the performance of each drone node under different task types, providing an accurate basis for subsequent task scheduling and resource allocation.

[0038] S502: Based on the node task processing capability table and the task process decomposition list, processing processes are matched for multiple nodes according to the processing requirements of multiple task types to obtain processing task matching results; In sub-step S502, task scheduling software, such as Microsoft Project, is used in combination with a task process decomposition list. Taking into account the specific processing requirements of each task type, including the required time, resources, and priority, a genetic algorithm is used to automatically match each drone node with the task process that best suits its capabilities. The algorithm optimizes task allocation based on node performance evaluation to ensure that each task can be processed by the most appropriate node, thereby improving the operational efficiency of the entire network. Through this sophisticated matching process, a processing task matching result is obtained, which ensures that all tasks are allocated and executed in the most optimized manner.

[0039] S503: Based on the task matching results and taking into account the task processing efficiency, the parameters of the UAV collaborative work are adjusted, including task allocation time, resource allocation, and priority setting, to generate UAV collaborative parameters; In sub-step S503, project management tools such as Oracle Primavera are used to refine task allocation time, resource allocation, and task priority setting. Target adjustments are made based on actual operational needs to improve the task processing efficiency of the entire drone network. By monitoring the performance feedback of each drone node in real time, parameters are adjusted to ensure maximum efficiency and optimal resource utilization in task collaboration operations. The adjusted parameters are recorded in the drone collaboration parameter table, which includes the start time, required resources, and priority of each task, providing a precise operational guide for efficient collaboration of the drone swarm.

[0040] See also Figure 7 , a drone edge collaborative computing system for drone airport clusters, a drone edge collaborative computing system for drone airport clusters, is used to execute the above-mentioned drone edge collaborative computing method for drone airport clusters, and the system includes: The network flow analysis module is based on the UAV communication network, monitoring the data flow of the communication network in real time, analyzing the data traffic, evaluating the network congestion situation, adjusting the data compression ratio and transmission priority according to the data type, optimizing the data transmission path, and generating transmission efficiency optimization records; The network topology construction module uses transmission efficiency optimization records to evaluate the connection status between multiple nodes in the network, build a network topology diagram, monitor the activity status of nodes, identify abnormal activity data, detect faulty nodes, and generate faulty node detection records; The task decomposition module analyzes the task type based on the fault node detection records and the input drone task information, decomposes the task into multiple execution processes, builds a process list, and generates task process analysis results; The performance monitoring module monitors the task processing efficiency and task completion rate of multiple nodes in the drone swarm in real time based on the results of task process analysis, evaluates the performance level and computing power of multiple nodes, and generates node performance evaluation information; The collaborative scheduling module adjusts the allocation parameters of UAV tasks, optimizes task processing efficiency, and generates UAV collaborative parameters based on the node performance evaluation information and the task processing capabilities and task flow decomposition list of multiple nodes.

[0041] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0042] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0043] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0044] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0045] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0046] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A UAV edge collaborative computing method for UAV airport clusters, characterized by: The following steps are involved: S1: Based on the drone communication network, analyze the drone type and real-time network data flow, evaluate the current network congestion, and adjust the data compression ratio and transmission priority of multiple data packets according to the network status and data type, optimize the data transmission path, and generate transmission efficiency optimization records; S2: Using the transmission efficiency optimization record, constructing a network topology diagram based on the connection status between nodes, monitoring the activity status of multiple nodes in real time, identifying faulty nodes by detecting abnormal activity data, and generating a faulty node detection record; S3: Analyze the task based on the fault node detection record and the input UAV task information, identify the task type, decompose the task into multiple processes and build a process list to generate a task process analysis result; S4: Based on the task process analysis results, by real-time monitoring the task processing efficiency and task completion rate of multiple nodes in the drone swarm, analyzing the performance level and task processing capability of multiple nodes, and generating node performance evaluation information; S5: According to the node performance evaluation information, based on the task processing capabilities and task process decomposition list of multiple nodes, and considering the task processing efficiency, the task allocation parameters of the target UAV task are adjusted to obtain the UAV collaboration parameters.

2. The UAV edge collaborative computing method for UAV airport cluster according to claim 1 is characterized in that: The transmission efficiency optimization record specifically includes network congestion conditions, data compression ratio parameters, and data transmission paths. The fault node detection record includes the fault node location, abnormal activity data, and node connection status information. The task process analysis results specifically refer to task types, task process lists, and task decomposition records. The node performance evaluation information includes node task processing efficiency, task completion rate, and node performance level score. The UAV collaboration parameters specifically include task processing efficiency information, task allocation list, and node efficiency monitoring records.

3. The drone edge collaborative computing method for drone airport clusters according to claim 1 is characterized in that: Based on the drone communication network, analyze the drone type and real-time network data flow, evaluate the current network congestion, and adjust the data compression ratio and transmission priority of multiple data packets according to the network status and data type, and optimize the data transmission path. The specific steps to generate the transmission efficiency optimization record are as follows: S101: Based on the UAV communication network, identify the types of multiple UAVs in the network, monitor the data flow of the communication network in real time, including data flow and data transmission delay, evaluate the congestion status of the communication network, and obtain network congestion analysis results; S102: Based on the network congestion analysis result and taking into account data transmission efficiency, adjusting the data compression ratio, and adjusting the transmission priority of multiple data packets according to the data type, to generate data packet adjustment parameters; S103: Based on the data packet adjustment parameters, the data transmission path is adjusted by comparing the transmission delays before and after the adjustment, and a transmission efficiency optimization record is generated.

4. The UAV edge collaborative computing method for UAV airport cluster according to claim 3 is characterized in that: The specific formula for evaluating the congestion status of the communication network is: ； in, Represents the network congestion index, Representative The network traffic value of each data point, Representatives and The time factor associated with each data point, Representative The data transmission delay of data points, Representative The weight of the data point, Represents the total number of data points within the analysis window, Represents the sequence number of the data point currently being considered.

5. The drone edge collaborative computing method for drone airport clusters according to claim 1 is characterized in that: Using the transmission efficiency optimization record, a network topology diagram is constructed based on the connection status between nodes, the activity status of multiple nodes is monitored in real time, and faulty nodes are identified by detecting abnormal activity data. The specific steps of generating a faulty node detection record are as follows: S201: Using the transmission efficiency optimization record, construct a network topology diagram according to the connection status between multiple nodes in the network; S202: Based on the network topology diagram, monitor the computing load, transmission flow and delay data of multiple nodes in real time, record the node activity status, and generate a node activity monitoring record; S203: Analyze the node activity monitoring record, analyze the data features of various node status data in real time, detect abnormal data and identify faulty nodes, and obtain faulty node detection records.

6. The drone edge collaborative computing method for drone airport clusters according to claim 5 is characterized in that: The specific formula for detecting abnormal data and identifying faulty nodes is: ； in, represents the node abnormality, Representative Dimensional monitoring data characteristics, Representative The historical average of the dimension data, Representative The standard deviation of the dimensional data, Represents the total number of dimensions of monitoring data, Represents the dimension number of the data point currently being considered.

7. The UAV edge collaborative computing method for UAV airport cluster according to claim 1 is characterized in that: According to the fault node detection record and the input drone mission information, the task is analyzed, the task type is identified, the task is decomposed into multiple processes and a process list is constructed. The specific steps for generating the task process analysis result are as follows: S301: Based on the fault node detection record, by analyzing the input UAV mission information, the target mission is classified into monitoring, transportation, and communication, and a mission type identification result is obtained; S302: Based on the task type identification result, by analyzing the execution processes and processing requirements of various tasks, decompose the target task into multiple processing processes, including data collection, data transmission and data analysis, and generate a task decomposition process list; S303: Analyze and mark the requirements of multiple processing flows on the performance of multiple nodes according to the task decomposition process list, and generate a task process analysis result.

8. The UAV edge collaborative computing method for UAV airport cluster according to claim 1 is characterized in that: Based on the task process analysis results, the steps of generating node performance evaluation information by real-time monitoring of the task processing efficiency and task completion rate of multiple nodes in the drone swarm and analyzing the performance level and task processing capability of multiple nodes are as follows: S401: Based on the task flow analysis results and the model information of the multiple drones in the fleet, the hardware resource configurations of the multiple drones are identified, including CPU type, memory capacity, and sensor type, and node hardware configuration information is generated. S402: Based on the node hardware configuration information, monitor the computing resource usage of the node in real time when processing multiple tasks, and generate a computing resource usage record; S403: Analyze the computing resource occupancy record, analyze the performance levels of multiple nodes based on the task processing efficiency and completion rate of the nodes, evaluate the task processing capabilities, and generate node performance evaluation information.

9. The drone edge collaborative computing method for drone airport clusters according to claim 1 is characterized in that: According to the node performance evaluation information, based on the task processing capabilities and task process decomposition list of multiple nodes, and taking into account the task processing efficiency, the task allocation parameters of the target UAV task are adjusted to obtain the UAV coordination parameters in the following steps: S501: Analyze the node performance evaluation information, extract performance data of multiple UAV nodes, identify the node's ability to handle various types of tasks, including the processing speed and efficiency of various tasks, and generate a node task processing capability table; S502: Based on the node task processing capability table and the task process decomposition list, matching processing processes for multiple nodes according to processing requirements of multiple task types to obtain processing task matching results; S503: Based on the processing task matching result and taking into account the task processing efficiency, the parameters of the UAV collaborative work are adjusted, including task allocation time, resource allocation and priority setting, to generate UAV collaborative parameters.

10. The UAV edge collaborative computing system for UAV airport clusters is characterized by: The drone edge collaborative computing method for drone airport clusters according to any one of claims 1 to 9, wherein the system comprises: The network flow analysis module is based on the UAV communication network, monitoring the data flow of the communication network in real time, analyzing the data traffic, evaluating the network congestion situation, adjusting the data compression ratio and transmission priority according to the data type, optimizing the data transmission path, and generating transmission efficiency optimization records; The network topology construction module uses the transmission efficiency optimization record to evaluate the connection status between multiple nodes in the network, construct a network topology diagram, monitor the activity status of the nodes, identify abnormal activity data, detect faulty nodes, and generate faulty node detection records; The task decomposition module analyzes the task type according to the fault node detection record and the input drone task information, decomposes the task into multiple execution processes, builds a process list, and generates a task process analysis result; The performance monitoring module monitors the task processing efficiency and task completion rate of multiple nodes in the drone swarm in real time based on the task process analysis results, evaluates the performance level and computing power of multiple nodes, and generates node performance evaluation information; The collaborative scheduling module adjusts the allocation parameters of the UAV tasks according to the node performance evaluation information, the task processing capabilities of multiple nodes and the task process decomposition list, optimizes the task processing efficiency, and generates UAV collaborative parameters.

Images