Multi-unmanned aerial vehicle power transmission line inspection method and system based on compressed communication and FedADMM optimization

Abstract

The invention provides a multi-unmanned aerial vehicle power transmission line inspection method and system based on compressed communication and FedADMM optimization, and belongs to the field of information transmission and intelligent control. The method mainly comprises the processes of local updating, compression transmission and total end aggregation of data of multiple unmanned aerial vehicles. The method comprises the following steps: firstly, generating a target function for collected data, distributing weights, and executing a FedADMM optimization algorithm to update local data; in the compression transmission process, the local data is compressed through a compression communication algorithm and then transmitted to the main end; and in the aggregation process of the total terminal, the FedADMM optimization algorithm is executed, and the total terminal aggregates data sent by the multiple unmanned aerial vehicles and broadcasts own information to the multiple unmanned aerial vehicles, so that a final consistent value is achieved. On the basis of ensuring efficient cooperative inspection of multiple unmanned aerial vehicles, efficient communication is ensured through data compression, the consistency of communication information is realized by means of an optimization algorithm, and the intelligent level and the overall efficiency of transmission line inspection are powerfully improved.

Description

Technical Field

[0001] The present invention relates to the field of information transmission and intelligent control, and in particular to a multi-UAV power transmission line inspection technology based on compressed communication and FedADMM optimization. Background Art

[0002] In modern power systems, transmission lines are critical infrastructure for power transmission, and their safe and stable operation is crucial to ensuring the reliability of power supply. As the scale of power grids continues to expand, transmission lines are becoming increasingly widespread. Multi-drone transmission line inspection technology, with its advantages such as efficiency, flexibility, and ability to cover complex terrain, has gradually become a research hotspot and development trend in the field of transmission line inspection. However, each drone has limited battery life, and inspection missions often require drones to fly for long periods of time and over large areas, making power consumption a key factor limiting the effectiveness of drone inspections. These issues not only increase inspection costs but can also result in drones being unable to complete their missions due to insufficient power. They can even risk loss of connection or crashes in remote areas, leading to equipment and data loss. Therefore, minimizing communication energy consumption while ensuring accurate drone data transmission is crucial.

[0003] To achieve a globally consistent solution for multiple drones, this paper considers a FedADMM algorithm. Under this algorithm, multiple drones rely solely on their own information and that of the central server. They update their parameters locally based on this information and send their own information to the central server, which aggregates it and sends it to each drone to reach a final consistent solution. However, under this framework, the large amount of data transmitted often leads to significant power consumption, making it highly unsafe. Summary of the Invention

[0004] Purpose of the invention: The purpose of the present invention is to propose a multi-UAV power transmission line inspection method and system based on compressed communication and FedADMM optimization, which can reduce the power loss caused by communication while ensuring that each UAV obtains a globally consistent solution.

[0005] Technical solution: To achieve the above-mentioned purpose, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization, including local update of UAV data, compressed transmission and central aggregation; the local update of UAV data includes:

[0007] The i-th UAV determines its own energy consumption objective function;

[0008] Data transmitted by the i-th drone satisfy σi Greater than 0 means the importance of is the physical parameter of the i-th UAV that needs to communicate, is the cumulative error, α i is a constant weight, f i (·) is the energy consumption objective function, are the initial physical parameters, represents the gradient;

[0009] The main terminal randomly selects a subset of drones and calculates global parameters And broadcast to the drones in this subset, where represents the sum of all weights, m represents the total number of drones, They are compressed variables and compressed data respectively;

[0010] Received The i-th UAV first updates the error tolerance value internally. Satisfy in

[0011] Between [0.5,1), ensure that the error tolerance value tends to 0; then update the compression variable in is a positive real number, and the communication parameters are updated Satisfy in ‖·‖ represents the 2-norm; the final update cumulative error and transmit data and compressed data Where C(·) is the compression function; for the drone that does not receive the signal, its parameters remain unchanged;

[0012] The central terminal aggregation process includes: after the central terminal receives the transmission data of the drones in the selected subset, it updates

[0013] Represents the final data of the drone.

[0014] As a preference, the main terminal generates α according to the priority of each UAV's mission execution. i , the higher the priority α i The larger the value, the greater the i >0.

[0015] As a preference, the main terminal randomly selects a subset of drones as follows in Select all drones, and when k>0, randomly select some drones, and then ensure that all drones are selected at least once in each sequence containing s0 sets; k and k0 are the number of local iterations of the drone and the communication cycle between the drone and the main terminal, respectively. Indicates rounding up.

[0016] As a preference, the compression function C(x) satisfies E c [‖C(x)-x‖ 2 ]≤r‖x‖ 2 ,r∈[0,1),E C [·] denotes the expectation on the internal randomness of the random compression operator C.

[0017] In the second aspect, the present invention provides a multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization. The difference from the first aspect is that the main end calculates the global parameters according to the following formula: Drone local parameters include is the compression variable, For new compressed data; update local parameters according to the following formula: internal update error tolerance value Satisfy Next, update the compression variable And update the communication parameters Satisfy in Then update the accumulated error and transmit data and compressed data Finally update the new local parameters and γ is a positive real number.

[0018] In a third aspect, the present invention provides a multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, comprising multiple UAV nodes, which form a transmission network with a central terminal, constituting a UAV swarm; each UAV node includes a sensor for monitoring the UAV status and a client data transmission module, the client data transmission template includes a client data local update unit and a compressed transmission unit, and the central terminal is provided with an aggregation unit;

[0019] The client data local updating unit is used to:

[0020] The i-th UAV determines its own energy consumption objective function;

[0021] Data transmitted by the i-th drone satisfy σ i Greater than 0 means the importance of is the physical parameter of the i-th UAV that needs to communicate, is the cumulative error, α i is a constant weight, f i (·) is the energy consumption objective function, are the initial physical parameters, represents the gradient;

[0022] Receive global parameters calculated by the main end The i-th drone, where represents the sum of all weights, m represents the total number of drones, are compressed variables and compressed data respectively; first, the error tolerance value is updated internally Satisfy in Between [0.5,1), ensure that the error tolerance value tends to 0; then update the compression variable in is a positive real number, and the communication parameters are updated Satisfy in ‖·‖ represents the 2-norm; the final update cumulative error and transmit data and compressed data Where C(·) is the compression function; for the drone that does not receive the signal, its parameters remain unchanged;

[0023] The compression transmission unit is used to: when communicating with the main end, the i-th drone will transmit data Compress to Then compress the data and compressed variables Transmit to the main terminal;

[0024] The aggregation unit is used to update the transmission data of the drones in the selected subset after the main end receives the transmission data of the drones in the selected subset. Represents the final data of the drone.

[0025] In a fourth aspect, the present invention provides a multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, which differs from the system in the third aspect in that: in the aggregation unit, the main end calculates the global parameters according to the following formula:

[0026] In the client data local update unit, the drone local parameters include is the compression variable, For new compressed data; update local parameters according to the following formula: internal update error tolerance value Satisfy Next, update the compression variable And update the communication parameters Satisfy in Then update the accumulated error and transmit data and compressed data Finally update the new local parameters and γ is a positive real number.

[0027] In a fifth aspect, the present invention provides a multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, comprising a plurality of UAV nodes, wherein a transmission network is formed between the plurality of UAV nodes and a main terminal, constituting a UAV swarm;

[0028] Each drone node includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of local update and compressed transmission of drone data in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization described in the first aspect or the second aspect are implemented;

[0029] The main end includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, the main end aggregation step in the multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization described in the first aspect or the second aspect is implemented.

[0030] In a sixth aspect, the present invention provides a computer system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of local update and compressed transmission of drone data, or the step of total-end aggregation, are implemented in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization described in the first or second aspect.

[0031] In a seventh aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of local update and compressed transmission of drone data, or the step of total-end aggregation, in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization described in the first aspect or the second aspect.

[0032] Beneficial Effects: The present invention proposes a multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization. The information transmitted by the UAVs is compressed and a special FedADMM algorithm is designed. This method can successfully reduce communication traffic without compromising the effectiveness of the original algorithm. Because the present invention is an improved distributed algorithm based on the FedADMM algorithm, compared to conventional centralized algorithms, it solves the problem of excessive transmission load near the central server-side node in traditional transmission methods. Experimental analysis confirms that the present invention simultaneously ensures consistency and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Schematic diagram of an application scenario of an embodiment of the present invention.

[0034] Figure 2 Flowchart of a method according to an embodiment of the present invention.

[0035] Figure 3 This is an experimental simulation diagram in an embodiment of the present invention.

[0036] Figure 4 4 is a diagram of simulation results in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0038] Example 1

[0039] like Figure 1 As shown, an application scenario of a multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization provided by an embodiment of the present invention. Using the method of this embodiment, the ground control station only needs to aggregate the compressed parameters to know the overall optimal parameter results, and adjust the communication parameters in real time to better reduce the transmission volume and reduce energy consumption.

[0040] like Figure 2As shown, an embodiment of the present invention provides a multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization. First, multiple UAVs determine the energy consumption target function and update local parameters in real time for subsequent compression processing; then the UAVs transmit the compressed data to the ground control station (main terminal) to reduce the amount of communication; finally, the ground control station (main terminal) aggregates the data sent by the UAVs and broadcasts its own information data to the UAVs to achieve the final average consistent value of the power consumption information. The specific process is as follows:

[0041] 1. Local update of drone data: The local update of drone data mainly includes measuring the energy consumption objective function, generating transmission weights, and updating local data using the FedADMM optimization algorithm.

[0042] Step 101 measures the energy consumption objective function: the i-th UAV determines its own energy consumption objective function expressed as f according to its mission completion status, remaining power, and inspection distance. i (w). Exemplarily, the objective function can be where d i is the number of samples (such as a positive integer in [50,100]), t represents the t-th sample, <·,·> represents the inner product between vectors, is an n-dimensional column vector, is a real number, and w is the physical parameter that needs to be communicated, including the current speed, acceleration, remaining power and other status information of the drone in all directions.

[0043] Step 102 Transmission weight generation: Each i-th drone will generate a constant denoted as α i As the weight, the generation method is as follows:

[0044] The main terminal generates α according to the priority of each drone’s mission. i , usually, the higher the priority α i The larger the value, the greater the i >0.

[0045] Then for the kth iteration, the data used for transmission is recorded as satisfy where σ i Represents a real number greater than 0 the importance of is the physical parameter of the i-th UAV, such as the speed parameter, is the cumulative error, in represents f i (w) The gradient at .

[0046] Step 103 Local parameter update: The central terminal will randomly select n drones to form a subset in k0 represents the communication cycle between the drone and the main terminal (number of communication intervals), and then the data transmitted by each drone is Compressed as Calculate global parameters in represents the sum of all weights, m represents the total number of drones, Broadcast to the drones in this subset through the wireless communication module, and the selection method is as follows:

[0047] Select all drones, and when k>0, randomly select some drones, and then satisfy the sequence of s0 sets in each group Make sure all drones are selected at least once.

[0048] Received Each drone i will execute the FedADMM optimization algorithm to update the error tolerance value Satisfy in Between [0.5,1), ensure that the error tolerance value tends to 0; then update the compression variable in is a positive real number, update the communication parameter Satisfy in represents f i (w) The gradient at , and finally update the accumulated error as well as Wherein C(x) represents a compression function, such as a rounding function.

[0049] For the drone i that does not receive the signal, its parameters Remain unchanged.

[0050] 2. Data compression processing: This process is the process of the drone compressing local information. At this time, all data has been updated to the latest form. Only the compression communication algorithm needs to be performed. The process is as follows:

[0051] Step 201 in the collection The i-th drone in the Perform compression processing and update internally to Finally got The transmission data is transmitted to the main terminal. k0 is the number of communication cycles or communication intervals; the compression function C(x) should satisfy E C [‖C(x)-x‖ 2 ]≤r‖x‖ 2 , where E C [·] denotes the expectation of the internal randomness of the random compression operator C, ‖·‖ denotes the 2-norm and r∈[0,1), and is an n-dimensional vector of all zeros, for

[0052] 3. Ground control station aggregation process: This process is the process in which the ground control station aggregates drone information and then broadcasts it to some drone nodes to reach a consistent value. At this time, the drone information has been compressed and only the FedADMM algorithm needs to be performed. The process is as follows:

[0053] Step 301 When k = {0, k0, 2k0, 3k0, ...}, the main terminal receives the set After the drone uploads the data, it will be updated Represents the final data of the drone.

[0054] Step 302: The main terminal will randomly select n drones to form a subset in Then put Broadcast to the drones in this subset via the wireless communication module; randomly selected as follows:

[0055] Select all drones, and when k>0, randomly select some drones, and then satisfy the sequence of s0 sets in each group Make sure all drones are selected at least once.

[0056] Example 2

[0057] An embodiment of the present invention provides a multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization. Compared with the method in Example 1, the main difference lies in the use of different update technologies.

[0058] Specifically, the local parameters of the drone also include is the compression variable, For new compressed data; update local parameters according to the following formula: internal update error tolerance value Satisfy in Between [0.5,1), ensuring that the error tolerance value tends to 0; secondly, update the compression variable in is a positive real number, and the communication parameters are updated Satisfy in and represents f i (w) The gradient at σ i is a real number greater than 0, and then the accumulated error is updated and transmit data and compressed data Finally update the new local parameters and γ is a positive real number; Ground control station aggregation process: Calculate the global parameter according to the following formula: When k = {0, k0, 2k0, 3k0, ...}, the central terminal receives the aggregate After the drone uploads the data, it will be updated Represents the final data of the drone.

[0059] The above-mentioned updating technology performs secondary compression on the transmitted data, so that the compression error can approach 0 more quickly, and the communication volume is only twice that of the method in Example 1, which allows the communication to reach a consistent result more quickly.

[0060] To verify the effectiveness of Example 1 and Example 2, Figure 3 Taking the cluster composed of 50 drones as an example, a simulation experiment is carried out. Figure 3 In the figure, each UAV transmits communication parameters to the ground control station along the arrows, and the energy consumption objective function is determined as a linear regression problem. Figure 4 As shown, quantize indicates that the compression function C(·) is an unbiased quantization function, norm-sign indicates that the compression function C(·) is a norm sign compression function, topk indicates that the compression function C(·) is a Top-k sparsification function, and uniform indicates that the compression function C(·) is a uniform quantization function. We can find that these compression functions, whether in Example 1 or Example 2, after a period of information transmission and update, the error tends to 0, where express The average value of Indicates that f(w) is The gradient of , which shows that each user has reached the optimal value point and achieved an average consistency result, while the communication volume BIT is significantly reduced compared to the original algorithm. In summary, the present invention can reduce the amount of data transmission and energy consumption while ensuring that each user obtains an average consistency result.

[0061] Example 3

[0062] Based on the same inventive concept as Example 1, an embodiment of the present invention provides a multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, including multiple UAV nodes. A transmission network is formed between the multiple UAV nodes and a central terminal, constituting a UAV swarm. Each UAV node includes a sensor and a client data transmission module. The sensor is used to monitor the UAV's power, location, mission completion status, and other status information. The client data transmission template includes a client data local update unit and a compression transmission unit. The central terminal is provided with an aggregation unit.

[0063] Client data local update unit, used for:

[0064] The i-th UAV determines its own energy consumption objective function;

[0065] Data transmitted by the i-th drone satisfy σ i Greater than 0 means the importance of is the physical parameter of the i-th UAV that needs to communicate, is the cumulative error, α i is a constant weight, f i (·) is the energy consumption objective function, are the initial physical parameters, represents the gradient;

[0066] Receive global parameters calculated by the main end The i-th drone, where represents the sum of all weights, m represents the total number of drones, are compressed variables and compressed data respectively; first, the error tolerance value is updated internally Satisfy in Between [0.5,1), ensure that the error tolerance value tends to 0; then update the compression variable in is a positive real number, and the communication parameters are updated Satisfy in ‖·‖ represents the 2-norm; the final update cumulative error and transmit data and compressed data Where C(·) is the compression function; for the drone that does not receive the signal, its parameters remain unchanged;

[0067] The compression transmission unit is used to: when communicating with the main terminal, the i-th drone will transmit data Compress to Then compress the data and compressed variables Transmit to the main terminal;

[0068] Aggregation unit, used to: update the transmission data of the selected UAVs after the main terminal receives the transmission data of the selected UAVs Represents the final data of the drone.

[0069] Example 4

[0070] Based on the same inventive concept as Example 2, this embodiment of the present invention provides a multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, which differs from Example 3 in that:

[0071] In the aggregation unit, the headend calculates global parameters according to the following formula: In the client data local update unit, the drone local parameters include is the compression variable, For new compressed data; update local parameters according to the following formula: internal update error tolerance value Satisfy Next, update the compression variable And update the communication parameters Satisfy in Then update the accumulated error and transmit data and compressed data Finally update the new local parameters and γ is a positive real number.

[0072] Example 5

[0073] An embodiment of the present invention provides a multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, comprising multiple UAV nodes, which form a transmission network with a main terminal to form a UAV swarm;

[0074] Each drone node includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of local update and compressed transmission of drone data in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization of embodiment 1 or embodiment 2 are implemented;

[0075] The main end includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, the main end aggregation step in the multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization of Example 1 or Example 2 is implemented.

[0076] Example 6

[0077] A computer system provided by an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of local update and compressed transmission of drone data, or the step of total-end aggregation, are implemented in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization of embodiment 1 or embodiment 2.

[0078] Example 7

[0079] A computer program product provided by an embodiment of the present invention includes a computer program, which, when executed by a processor, implements the steps of local update and compressed transmission of drone data, or the step of central aggregation, in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization of embodiment 1 or embodiment 2.

[0080] It should be noted that the above-described embodiments only represent some embodiments of the present invention, and their descriptions should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make several improvements without departing from the scope of the present invention, and these improvements should fall within the scope of protection of the present invention.

Claims

1. A multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization, characterized by: This includes the process of local update, compressed transmission and central aggregation of drone data. The local update of drone data includes: The i-th UAV determines its own energy consumption objective function; Data transmitted by the i-th drone satisfy σ i Greater than 0 means the importance of is the physical parameter of the i-th UAV that needs to communicate, is the cumulative error, α i is a constant weight, f i (·) is the energy consumption objective function, are the initial physical parameters, represents the gradient; The main terminal randomly selects a subset of drones and calculates global parameters And broadcast to the drones in this subset, where represents the sum of all weights, m represents the total number of drones, They are compressed variables and compressed data respectively; Received The i-th UAV first updates the error tolerance value internally. Satisfy where θ i Between [0.5,1), ensure that the error tolerance value tends to 0; then update the compression variable in is a positive real number, and the communication parameters are updated Satisfy in ‖·‖ represents the 2-norm; the final update cumulative error and transmit data and compressed data Where C(·) is the compression function; for the drone that does not receive the signal, its parameters remain unchanged; The central terminal aggregation process includes: after the central terminal receives the transmission data of the drones in the selected subset, it updates Represents the final data of the drone.

2. The multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization according to claim 1 is characterized by: The main terminal generates α according to the priority of each drone’s mission. i , the higher the priority α i The larger the value, the greater the i >0.

3. The multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization according to claim 1 is characterized by: The main terminal randomly selects a subset of drones as follows in Select all drones, and when k>0, randomly select some drones, and then ensure that all drones are selected at least once in each sequence containing s0 sets; k and k0 are the number of local iterations of the drone and the communication cycle between the drone and the main terminal, respectively. Indicates rounding up.

4. The multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization according to claim 1 is characterized by: The compression function C(x) satisfies E c [‖C(x)-x‖ 2 ]≤r‖x‖ 2 ,r∈[0,1),E C [·] denotes the expectation on the internal randomness of the random compression operator C.

5. The multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization according to claim 1 is characterized in that: The main end calculates global parameters according to the following formula: Drone local parameters include is the compression variable, For new compressed data; update local parameters according to the following formula: internal update error tolerance value Satisfy Next, update the compression variable And update the communication parameters Satisfy in Then update the accumulated error and transmit data and compressed data Finally update the new local parameters and γ is a positive real number.

6. A multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, characterized by: It includes multiple drone nodes, which form a transmission network with the main terminal to form a drone swarm. Each drone node includes a sensor for monitoring the drone status and a client data transmission module. The client data transmission template includes a client data local update unit and a compression transmission unit. The main terminal is equipped with an aggregation unit. The client data local updating unit is used to: The i-th UAV determines its own energy consumption objective function; Data transmitted by the i-th drone satisfy σ i Greater than 0 means the importance of is the physical parameter of the i-th UAV that needs to communicate, is the cumulative error, α i is a constant weight, f i (·) is the energy consumption objective function, are the initial physical parameters, represents the gradient; Receive global parameters calculated by the main end The i-th drone, where represents the sum of all weights, m represents the total number of drones, are compressed variables and compressed data respectively; first, the error tolerance value is updated internally Satisfy where θ i Between [0.5,1), ensure that the error tolerance value tends to 0; then update the compression variable in is a positive real number, and the communication parameters are updated Satisfy in ‖·‖ represents the 2-norm; the final update cumulative error and transmit data and compressed data Where C(·) is the compression function; for the drone that does not receive the signal, its parameters remain unchanged; The compression transmission unit is used to: when communicating with the main end, the i-th drone will transmit data Compress to Then compress the data and compressed variables Transmit to the main terminal; The aggregation unit is used to update the transmission data of the drones in the selected subset after the main end receives the transmission data of the drones in the selected subset. Represents the final data of the drone.

7. The multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization according to claim 6 is characterized by: In the aggregation unit, the head end calculates the global parameters according to the following formula: In the client data local update unit, the drone local parameters include is the compression variable, For new compressed data; update local parameters according to the following formula: internal update error tolerance value Satisfy Next, update the compression variable And update the communication parameters Satisfy in Then update the accumulated error and transmit data and compressed data Finally update the new local parameters and γ is a positive real number.

8. A multi-UAV power transmission line inspection system based on compressed communication and FedADMM optimization, characterized by: It includes multiple drone nodes, which form a transmission network with the main terminal to form a drone swarm; Each UAV node includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of local update and compressed transmission of UAV data in the multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization according to any one of claims 1 to 5 are implemented; The main end includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, the main end aggregation step in the multi-UAV power transmission line inspection method based on compressed communication and FedADMM optimization according to any one of claims 1 to 5 is implemented.

9. A computer system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by the processor, the steps of local update and compressed transmission of drone data, or the step of total end aggregation, are implemented in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization according to any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by the processor, the steps of local update and compressed transmission of drone data, or the step of total end aggregation, are implemented in the multi-drone power transmission line inspection method based on compressed communication and FedADMM optimization according to any one of claims 1 to 5.

Images