Unmanned aerial vehicle distribution scheduling method and system applied to communication interruption area

Abstract

The invention provides an unmanned aerial vehicle distribution scheduling method and system applied to a communication interruption region, and the method comprises the steps: determining unmanned aerial vehicle information used for the communication interruption region, and carrying out the air networking of all unmanned aerial vehicles according to the unmanned aerial vehicle information; after networking succeeds, defining a coordinate set of all the unmanned aerial vehicles participating in networking, constructing a logarithmic path loss model according to the coordinate set, and obtaining the signal propagation intensity of any position point of the communication interruption region according to the path loss model; constructing a signal coverage rate objective function according to the signal propagation intensity, and constructing a network average link quality objective function and a node energy consumption balance objective function to obtain a comprehensive objective function; and taking the maximization of the comprehensive objective function as a target, and solving by adopting an improved particle swarm optimization algorithm to obtain the deployment positions of all the unmanned aerial vehicles in the communication interruption region. According to the invention, the deployment efficiency and reliability of the disaster area communication system can be significantly improved.

Description

Technical Field

[0001] This invention relates to the field of distributed scheduling technology for unmanned aerial vehicles (UAVs), and in particular to a distributed scheduling method and system for UAVs applied in areas with communication disruptions. Background Art

[0002] In extreme situations such as natural disasters, traditional communication facilities are easily damaged, leading to widespread communication disruptions and severely impacting rescue efficiency. Although some drone platforms have been applied to emergency communications, their limited battery life and stability make it difficult to operate for extended periods in complex environments. Therefore, how to quickly and effectively restore and maintain communication services remains a pressing issue.

[0003] Unmanned aerial vehicles (UAVs) are considered an ideal choice for providing temporary communication services in areas with communication disruptions due to their flexible deployment and rapid response capabilities. However, efficiently scheduling multiple UAVs to achieve optimal communication coverage, link quality, and energy consumption balance remains a current technical challenge. Traditional UAV scheduling methods often overlook the unique environmental factors in areas with communication disruptions, such as complex terrain and uneven signal attenuation, leading to poor scheduling results. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for the distributed scheduling of unmanned aerial vehicles (UAVs) in areas with communication disruptions, aiming to solve the problems of the lack of UAV scheduling methods or poor scheduling effects in traditional technologies for providing temporary communication services in areas with communication disruptions.

[0005] In a first aspect, the present invention provides a method for the distributed scheduling of unmanned aerial vehicles (UAVs) in areas with communication disruptions, the method comprising: Identify drone information for areas with communication disruptions, and establish an aerial network for all drones based on this information; After the network is successfully established, the coordinate set of all UAVs participating in the network is defined, and a logarithmic path loss model is constructed based on the coordinate set. The signal propagation strength at any point in the communication interruption area is obtained based on the path loss model. Based on the signal propagation strength, construct a signal coverage objective function, a network average link quality objective function, and a node energy consumption balance objective function, and then construct a comprehensive objective function based on the signal coverage objective function, the network average link quality objective function, and the node energy consumption balance objective function. The deployment locations of all UAVs in the communication interruption area were obtained by maximizing the comprehensive objective function and solving it using an improved particle swarm optimization algorithm.

[0006] Secondly, the present invention provides a distributed dispatching system for unmanned aerial vehicles (UAVs) applied in areas with communication disruptions, the system comprising: The networking module is used to determine the drone information for areas with communication interruptions, and to form an aerial network for all drones based on the drone information. The model building module is used to define the coordinate set of all UAVs participating in the network after successful network formation, construct a logarithmic path loss model based on the coordinate set, and obtain the signal propagation strength at any point in the communication interruption area based on the path loss model. The objective function construction module is used to construct a signal coverage objective function based on the signal propagation strength, and to construct a network average link quality objective function and a node energy consumption balance objective function, and to construct a comprehensive objective function based on the signal coverage objective function, the network average link quality objective function, and the node energy consumption balance objective function; The deployment location solution module is used to maximize the comprehensive objective function and solve it using an improved particle swarm optimization algorithm to obtain the deployment locations of all UAVs in the communication interruption area.

[0007] Thirdly, the present invention provides a storage medium that stores one or more programs, which, when executed by a processor, implement the above-described method for distributed scheduling of unmanned aerial vehicles (UAVs) in areas with communication disruptions.

[0008] Fourthly, the present invention provides an electronic device, the electronic device comprising a memory and a processor, wherein: The memory is used to store computer programs; When the processor executes the computer program stored in the memory, it implements the above-described method for distributed scheduling of unmanned aerial vehicles (UAVs) in areas with communication disruptions.

[0009] Compared with the prior art, the present invention has the following advantages: This invention accurately determines the information of UAVs participating in communication tasks and completes aerial networking, which can fully adapt to the complex environment of communication interruption areas, such as terrain undulations and obstacle distribution, making the networking more scientific and reasonable, and laying a solid foundation for subsequent work. After networking, a logarithmic path loss model is constructed, which can accurately calculate the signal propagation intensity at any location in the area, clearly present the distribution of signal coverage strength, quickly locate signal blind spots, and provide accurate data support for optimized scheduling. The subsequent construction of signal coverage, average network link quality, node energy consumption balance objective functions, and comprehensive objective functions comprehensively considers the key elements of communication recovery. It ensures that the signal can cover a wide area, allowing more areas to restore communication; it also focuses on link quality to ensure stable and reliable data transmission; and it also takes into account the energy consumption balance of UAV nodes to prevent some UAVs from prematurely exiting due to excessive energy consumption, thus prolonging the working time of the entire communication network. The subsequent construction of signal coverage, average network link quality, node energy consumption balance objective functions, and comprehensive objective functions comprehensively considers the key elements of communication recovery. It ensures wide signal coverage, allowing more areas to resume communication; it also emphasizes link quality to ensure stable and reliable data transmission; and it takes into account the balanced energy consumption of drone nodes to prevent some drones from prematurely exiting due to excessive energy consumption, thus extending the working time of the entire communication network. Attached Figure Description

[0010] Figure 1 This is a flowchart of a UAV distributed scheduling method for communication interruption areas proposed in an embodiment of the present invention; Figure 2 This is a network topology diagram illustrating an example of the present invention; Figure 3 This is a schematic diagram of the structure of a distributed scheduling system for unmanned aerial vehicles (UAVs) applied to areas with communication disruptions, as proposed in an embodiment of the present invention.

[0011] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art. The terms "comprising" and similar expressions used herein mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but does not exclude other elements or objects.

[0013] like Figure 1 As shown, an embodiment of the present invention proposes a method for distributed scheduling of unmanned aerial vehicles (UAVs) in areas with communication disruptions. This method includes steps S101 to S104, wherein: Step S101: Determine the drone information for the communication interruption area, and form an aerial network for all drones based on the drone information; It should be noted that the drone in this embodiment is equipped with a gripper structure. First, it detects the position of the high-voltage power line using a wire sensor, then autonomously flies close to and grips the line. A current transformer, based on the principle of electromagnetic induction, induces a secondary current from the primary high-voltage bus, which continuously powers the drone's battery through power conversion and energy storage circuitry. This power supply method overcomes battery life limitations, enabling the drone to hover and operate continuously for extended periods.

[0014] Secondly, after the drone is positioned on the cable, it first completes the initialization of the communication module and the loading of the communication driver, supporting multiple communication protocols such as LoRa and 5G to ensure flexible communication capabilities in different environments. Upon startup, the drone periodically broadcasts its own status information, including its unique identifier (ID), current location coordinates, remaining battery power, received signal strength (RSSI), signal-to-noise ratio (SNR), timestamp, and available routing information. This information provides nearby drones with real-time communication quality and resource status references.

[0015] After receiving status information from neighboring nodes, each drone stores the relevant data in its local neighbor table and updates it periodically. By statistically analyzing the signal strength and link stability of neighboring nodes, a sliding window algorithm is used to calculate the mean and stability of the signals, filtering out short-term fluctuations and ensuring the accuracy and robustness of the link quality assessment.

[0016] Based on the link quality data recorded in the neighbor table, the drone nodes run a dynamic routing protocol, which intelligently establishes end-to-end routing paths by combining the least hop count and optimal link quality strategies.

[0017] For example, suppose there are three drones capable of cable-connected power and aerial networking. Upon arriving at the mission location, these three drones clamp onto the cable to draw power. At this point, each drone begins status broadcasting. These three drones send their status information to surrounding drones, including: ID, coordinates, remaining battery power, Received Signal Strength Indicator (RSSI), Signal-to-Noise Ratio (SNR), timestamp, and available routing information. For instance, drone A will receive status information from drones B and C, and similarly, drone B will receive status information from drones A and C. The received status information is used to build a neighbor table, which records the status information of all nearby drones received by that drone. Then, link establishment begins, and the three drones run a dynamic routing protocol based on the neighbor table to calculate the optimal route path.

[0018] For example: the link quality between A and B is good; the link quality between B and C is good; the link quality between A and C is poor; the link quality between A and D is poor; the link quality between B and D is good; and the link quality between C and D is poor. As shown in the diagram below, the routing protocol will select the route with the best link quality to establish a connection, such as from A to B to D. Specifically... Figure 2 As shown.

[0019] Step S102: After successful network formation, define the coordinate set of all UAVs participating in the network, construct a logarithmic path loss model based on the coordinate set, and obtain the signal propagation strength at any location in the communication interruption area based on the path loss model. It should be noted that in this step, the number of drones participating in the network is first defined as N, and the coordinate set is: ,in, Let i be the spatial coordinates of the i-th UAV. Let x, y, and altitude be the x-coordinate, y-coordinate, and altitude of the i-th drone, respectively, and T be the coordinate set.

[0020] Then, a logarithmic path loss model is constructed based on the following formula: ; in, Let i be the spatial position of the i-th drone. The signal propagation strength, These are the transmit and receive gains, respectively. The reference path loss is n, where n is the environmental loss factor. Let be the transmit power of the i-th UAV. This is a reference distance, used as the unit distance for power attenuation calculation in the logarithmic path loss model, typically taken as 10m for long-distance communication. Simulate multipath fading for Gaussian random variables.

[0021] It should be noted that traditional deployment methods often ignore complex factors such as terrain obstruction and building reflections, relying solely on simplified distance models or ideal coverage radii. This leads to frequent deployment blind spots and communication dead zones. Therefore, the aforementioned path loss model, based on the principle of logarithmic path loss and combined with Gaussian fading modeling of signal attenuation in real-world environments, is used to evaluate the received signal strength at any point. This model accurately describes propagation loss through environmental loss factors and fading terms, improving the simulation capability and prediction accuracy of wireless channels in complex disaster areas.

[0022] Step S103: Construct a signal coverage objective function based on the signal propagation strength, and construct a network average link quality objective function and a node energy consumption balance objective function, and construct a comprehensive objective function based on the signal coverage objective function, the network average link quality objective function, and the node energy consumption balance objective function; It should be noted that, in some embodiments, it is assumed that the communication interruption area is gridded into M spatial points, and if the spatial position of the j-th spatial point... If the signal propagation strength is greater than the first threshold, then the signal coverage objective function is constructed according to the following formula: ; in, Let the objective function be the signal coverage rate, and if the spatial location... Whether it is covered by the i-th drone, then =1, otherwise 0; if spatial position If it is covered by at least one drone, then =1, otherwise =0; If the i-th drone is in spatial location If the signal propagation strength is greater than or equal to a preset strength threshold, then the spatial location is determined. Covered by the i-th drone; If the i-th drone is in spatial location If the signal propagation strength is less than a preset strength threshold, then the spatial location is determined. It was not covered by the i-th drone.

[0023] It should be noted that traditional methods often use regular grids or empirical point placement, which are difficult to adapt to the actual terrain and distribution of mission objectives, resulting in limited coverage. Based on this, a signal coverage objective function is constructed to maximize the proportion of effective communication points in the area, ensuring that the relay platform achieves the maximum signal penetration rate in the disaster area.

[0024] Furthermore, in some embodiments, the network average link quality objective function is constructed according to the following formula: ; Construct the node energy consumption balance objective function according to the following formula: ; Traditional solutions fail to consider differences in load and power supply capacity among nodes, potentially leading to some nodes operating at high loads for extended periods or prematurely disconnecting from the network, causing network fragmentation or paralysis. Therefore, this paper proposes a node energy consumption balancing objective function that binds energy consumption to available energy, achieving load balancing through globally coordinated deployment.

[0025] Construct the comprehensive objective function based on the following formula: ; in, , , These are the network average link quality objective function, the node energy consumption balance objective function, and the comprehensive objective function, respectively. For a set of links, Let be the signal-to-noise ratio of the inter-link between the i-th drone and the j-th drone. Let i be the online time of the i-th drone. For the data forwarding payload of the i-th drone, This is the maximum output power of the current transformer. All are adjustable weighting factors.

[0026] In summary, the comprehensive objective function integrates multiple key indicators such as signal coverage, average network link quality, and node energy balance. Signal coverage ensures that as many locations as possible in areas of communication interruption can receive effective signals, which is a fundamental requirement for communication recovery. Average network link quality focuses on the stability and reliability of communication links, ensuring accurate data transmission. Node energy balance focuses on the endurance of UAVs, preventing some UAVs from prematurely ceasing operation due to excessive energy consumption. By combining these indicators, the merits of UAV distribution scheduling schemes can be comprehensively evaluated, avoiding the one-sidedness of evaluation by a single indicator.

[0027] Step S104: With the goal of maximizing the comprehensive objective function, and using the improved particle swarm optimization algorithm to solve the problem, the deployment locations of all UAVs in the communication interruption area are obtained.

[0028] It should be noted that in the specific solution process, K particles are first randomly generated. Each particle represents a set of deployment schemes for all drones. Each set of deployment schemes includes the three-dimensional spatial deployment coordinates of N drones. After t iterations, the formula for updating the d-dimensional velocity of the i-th UAV in the k-th particle is: ; in, , Let be the d-dimensional velocity of the i-th drone in the k-th particle of the (t+1)-th iteration and the t-th iteration, respectively. For inertial weights, , These are all learning factors used to adjust individual and global learning weights. , All are random factors. The historical best drone coordinates are for the i-th drone in the k-th particle of the t-th iteration. The global particle history optimal solution is represented in the d-dimensional UAV coordinates. Update the drone's position based on the d-th dimension velocity: ; in, , These are the three-dimensional spatial deployment coordinates of the i-th UAV in the k-th particle of the t-th and t+1-th iterations, respectively. A position matrix is ​​constructed based on the drone's location, and the globally optimal position is determined based on the position matrix: ; in, Let be the value of the comprehensive objective function in the t-th iteration. , , Let be the objective function values ​​for signal coverage, average network link quality, and node energy consumption balance in the t-th iteration; The algorithm terminates when the number of iterations reaches the second threshold or the comprehensive objective function converges to the third threshold, and outputs the globally optimal position layout.

[0029] It should be noted that traditional optimization methods such as greedy search or grid exhaustive search are prone to getting stuck in local optima or incurring high computational costs in complex, high-dimensional scenarios. Therefore, an improved particle swarm optimization algorithm is designed to simulate swarm behavior and gradually approach optimal deployment, thereby achieving low-cost, high-precision adaptive deployment, improving deployment efficiency and network quality, and is suitable for tasks such as real-time disaster area communication support. Furthermore, in updating the drone's position, the new velocity is first calculated using inertia, individual optimal guidance, and global optimal guidance. The new drone position is obtained by combining "current coordinates + new velocity," where velocity is equivalent to a displacement. This velocity is updated independently for each coordinate dimension (e.g., x, y, h), thus completing the next deployment step for the entire drone group.

[0030] Furthermore, in some embodiments, a position matrix is ​​constructed using the x, y, and z coordinates as column names and the drone number in the k-th particle as the row name: ; in, This is the position matrix corresponding to the k-th particle in the t-th iteration. , , Let x, y, and z be the x, y, and z coordinates of the first UAV in the k-th particle of the t-th iteration, respectively. , , Let x, y, and z be the x, y, and z coordinates of the second UAV in the k-th particle of the t-th iteration, respectively. , , These are the x, y, and z coordinates of the Nth UAV in the kth particle of the t-th iteration.

[0031] In summary, by randomly generating K particles containing the 3D spatial deployment coordinates of the UAVs as deployment schemes, diverse starting points are provided for the search. During the iteration process, in the velocity update formula of the i-th UAV in the d-th dimension, the inertial weight dynamically adjusts the influence of the particle's original velocity. The learning factor and the random factor work together, enabling the particle to learn from its own historical best and the global historical best. This ensures both global search capability to explore better solution regions and avoid getting trapped in local optima, and also provides local exploration capability, accelerating the convergence process and reducing the number of iterations and computational resource consumption. The UAV position is updated based on the velocity, and a position matrix is ​​constructed to determine the global optimal position. The optimal deployment layout of the UAVs that meets the multi-objective requirements is finally obtained through evaluation by a comprehensive objective function (covering signal coverage, average network link quality, and node energy consumption balance objective function value).

[0032] like Figure 3 As shown, one embodiment of the present invention proposes a distributed scheduling system for unmanned aerial vehicles (UAVs) applied in areas with communication disruptions. The system includes: The networking module 10 is used to determine the drone information for areas with communication interruptions, and to form an aerial network for all drones based on the drone information. The model building module 20 is used to define the coordinate set of all UAVs participating in the network after the network is successfully formed, and to build a logarithmic path loss model based on the coordinate set, and to obtain the signal propagation strength at any point in the communication interruption area based on the path loss model. The objective function construction module 30 is used to construct a signal coverage objective function based on the signal propagation strength, and to construct a network average link quality objective function and a node energy consumption balance objective function, and to construct a comprehensive objective function based on the signal coverage objective function, the network average link quality objective function, and the node energy consumption balance objective function; The deployment location solution module 40 is used to maximize the comprehensive objective function and solve it using an improved particle swarm optimization algorithm to obtain the deployment locations of all UAVs in the communication interruption area.

[0033] In another aspect, the present invention also proposes a storage medium on which one or more programs are stored, which, when executed by a processor, implement the above-described method for distributed scheduling of unmanned aerial vehicles (UAVs) in areas with communication disruptions.

[0034] In another aspect, the present invention also proposes an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so as to realize the above-mentioned UAV distributed scheduling method applied to areas with communication interruption.

[0035] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain stored, communicated, propagated, or transmitted programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0036] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0037] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0038] While embodiments of the present invention have been described in detail above, it will be apparent to those skilled in the art that various modifications and variations can be made to these embodiments. However, it should be understood that such modifications and variations fall within the scope and spirit of the invention as set forth in the claims. Furthermore, the invention described herein may have other embodiments and can be implemented or carried out in various ways.

Claims

1. A method for distributed scheduling of unmanned aerial vehicles (UAVs) in areas with communication disruptions, characterized in that, The method includes: Identify drone information for areas with communication disruptions, and establish an aerial network for all drones based on this information; After the network is successfully established, the coordinate set of all UAVs participating in the network is defined, and a logarithmic path loss model is constructed based on the coordinate set. The signal propagation strength at any point in the communication interruption area is obtained based on the path loss model. Based on the signal propagation strength, construct a signal coverage objective function, a network average link quality objective function, and a node energy consumption balance objective function, and then construct a comprehensive objective function based on the signal coverage objective function, the network average link quality objective function, and the node energy consumption balance objective function. The deployment locations of all UAVs in the communication interruption area were obtained by maximizing the comprehensive objective function and solving it using an improved particle swarm optimization algorithm.

2. The UAV distribution scheduling method applied to areas with communication disruptions according to claim 1, characterized in that, The steps of defining the coordinate set of all UAVs participating in the network, constructing a logarithmic path loss model based on the coordinate set, and obtaining the signal propagation strength at any point in the communication interruption area based on the path loss model include: The number of drones participating in the network is defined as N, and the coordinate set is: ,in, Let i be the spatial coordinates of the i-th UAV. Let x, y, and altitude be the x-coordinate, y-coordinate, and altitude of the i-th drone, respectively, and T be the coordinate set; Construct a logarithmic path loss model based on the following formula: ； in, Let i be the spatial position of the i-th drone. The signal propagation strength, These are the transmit and receive gains, respectively. The reference path loss is n, where n is the environmental loss factor. Let be the transmission power of the i-th drone. For reference distance, Simulate multipath fading for Gaussian random variables.

3. The UAV distribution scheduling method applied to areas with communication disruptions according to claim 2, characterized in that, The step of constructing the signal coverage objective function based on the signal propagation intensity includes: Assuming the communication interruption area is gridded into M spatial points, if the spatial location of the j-th spatial point... If the signal propagation strength is greater than the first threshold, then the signal coverage objective function is constructed according to the following formula: ； in, Let the objective function be the signal coverage rate, and if the spatial location... Whether it is covered by the i-th drone, then =1, otherwise =0; if spatial position If it is covered by at least one drone, then =1, otherwise =0; If the i-th drone is in spatial location If the signal propagation strength is greater than or equal to a preset strength threshold, then the spatial location is determined. Covered by the i-th drone; If the i-th drone is in spatial location If the signal propagation strength is less than a preset strength threshold, then the spatial location is determined. It was not covered by the i-th drone.

4. The UAV distribution and scheduling method applied to areas with communication disruptions according to claim 3, characterized in that, The steps of constructing the network average link quality objective function and the node energy consumption balance objective function, and constructing a comprehensive objective function based on the signal coverage objective function, the network average link quality objective function, and the node energy consumption balance objective function include: Construct the network average link quality objective function based on the following formula: ； Construct the node energy consumption balance objective function according to the following formula: ； Construct the comprehensive objective function based on the following formula: ； in, , , These are the network average link quality objective function, the node energy consumption balance objective function, and the comprehensive objective function, respectively. For a set of links, Let be the signal-to-noise ratio of the inter-link between the i-th drone and the j-th drone. Let i be the online time of the i-th drone. For the data forwarding payload of the i-th drone, This is the maximum output power of the current transformer. All are adjustable weighting factors.

5. The UAV distribution scheduling method applied to areas with communication disruptions according to claim 4, characterized in that, The step of obtaining the deployment locations of all UAVs in the communication interruption area by maximizing the comprehensive objective function and solving it using an improved particle swarm optimization algorithm includes: K particles are randomly generated, each particle representing a set of deployment schemes for all drones. Each set of deployment schemes includes the three-dimensional spatial deployment coordinates of N drones. After t iterations, the formula for updating the d-dimensional velocity of the i-th UAV in the k-th particle is: ； in, , Let be the d-dimensional velocity of the i-th drone in the k-th particle of the (t+1)-th iteration and the t-th iteration, respectively. For inertial weights, , These are all learning factors used to adjust individual and global learning weights. , All are random factors. The historical best drone coordinates are for the i-th drone in the k-th particle of the t-th iteration. The global particle history optimal solution is represented in the d-dimensional UAV coordinates. Update the drone's position based on the d-th dimension velocity: ； in, , These are the three-dimensional spatial deployment coordinates of the i-th UAV in the k-th particle during the t-th and t+1-th iterations, respectively. A position matrix is ​​constructed based on the drone's location, and the globally optimal position is determined based on the position matrix: ； in, Let be the value of the comprehensive objective function in the t-th iteration. , , Let be the objective function values ​​for signal coverage, average network link quality, and node energy consumption balance in the t-th iteration; The algorithm terminates when the number of iterations reaches the second threshold or the comprehensive objective function converges to the third threshold, and outputs the globally optimal position layout.

6. The UAV distribution scheduling method applied to areas with communication disruptions according to claim 5, characterized in that, The step of constructing a position matrix based on the location of the UAV includes: Using the x, y, and z coordinates as column names and the drone number in the k-th particle as the row name, a position matrix is ​​constructed: ； in, This is the position matrix corresponding to the k-th particle in the t-th iteration. , , Let x, y, and z be the x, y, and z coordinates of the first UAV in the k-th particle of the t-th iteration, respectively. , , Let x, y, and z be the x, y, and z coordinates of the second UAV in the k-th particle of the t-th iteration, respectively. , , These are the x, y, and z coordinates of the Nth UAV in the kth particle of the t-th iteration.

7. A distributed dispatch system for unmanned aerial vehicles (UAVs) applied in areas with communication disruptions, characterized in that, The system includes: The networking module is used to determine the drone information for areas with communication interruptions, and to form an aerial network for all drones based on the drone information. The model building module is used to define the coordinate set of all UAVs participating in the network after successful network formation, construct a logarithmic path loss model based on the coordinate set, and obtain the signal propagation strength at any point in the communication interruption area based on the path loss model. The objective function construction module is used to construct a signal coverage objective function based on the signal propagation strength, and to construct a network average link quality objective function and a node energy consumption balance objective function, and to construct a comprehensive objective function based on the signal coverage objective function, the network average link quality objective function, and the node energy consumption balance objective function; The deployment location solution module is used to maximize the comprehensive objective function and solve it using an improved particle swarm optimization algorithm to obtain the deployment locations of all UAVs in the communication interruption area.

8. A storage medium, characterized in that, The storage medium stores one or more programs that, when executed by a processor, implement the UAV distributed scheduling method for communication-disrupted areas as described in any one of claims 1-6.

9. An electronic device comprising a memory and a processor, wherein: The memory is used to store computer programs; When the processor executes the computer program stored in the memory, it implements the UAV distribution scheduling method for communication interruption areas as described in any one of claims 1-6.

Images