Improved ant colony unmanned aerial vehicle inspection method for satellite integrated smart power grid

Abstract

The invention provides an improved ant colony unmanned aerial vehicle inspection method for a satellite integrated smart power grid, and the method achieves the efficient inspection of a power transmission line and key parts through the combination of a satellite communication technology and an unmanned aerial vehicle. A pre-clustering traveling salesman model is adopted, nodes to be inspected are clustered, and the route planning complexity is simplified. On the basis of an improved ant colony algorithm (XACO), through a double-layer pheromone updating mechanism and heuristic information dynamic adjustment, the convergence speed and the optimal solution quality of path selection are improved. The method is excellent in performance in a large-scale scene, the efficiency and the safety of intelligent power grid inspection are remarkably improved, the cost and the risk of manual inspection are reduced, and the method is suitable for power grid monitoring and maintenance in remote and complex areas.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to an improved ant colony drone inspection method for satellite integrated smart grids. Background Art

[0002] With the widespread application of smart grids, the reliability requirements of their communication systems are constantly increasing. By integrating satellite communication technology, smart grids can provide wider communication coverage in complex terrain and remote areas, and ensure the stability and robustness of the system. The traditional method of power transmission line inspection relies on manual inspection, which is not only inefficient and costly, but also faces problems such as high complexity and safety hazards, and cannot effectively ensure the efficient operation of the power grid.

[0003] In order to improve the efficiency of smart grid inspection, in recent years, drone inspection systems combined with satellite communication technology have gradually become an important technical means. Drones can autonomously perform line inspection tasks, especially in a wide-coverage, large-scale smart grid environment. The use of drones for automated inspection of transmission lines can significantly improve the speed and accuracy of inspections. During the inspection process, drones can use preset path planning algorithms to perform regular inspections of transmission lines, key areas, and important components. Especially in the event of natural disasters or emergencies, drones can quickly enter the fault area, perform accurate image and data collection, and transmit real-time data to the control center via satellite communications, helping operation and maintenance personnel make decisions quickly, reduce problem-solving costs, and improve the operational flexibility of smart grids.

[0004] However, for large-scale smart grid inspection tasks, how to formulate efficient inspection path planning is a key issue. The path planning of drones needs to solve multiple constraints, including flight distance, energy consumption, task priority, etc. Existing research mainly uses heuristic algorithms and machine learning algorithms to optimize to improve the reliability and efficiency of inspection tasks. Among them, the ant colony algorithm, as a classic heuristic optimization algorithm, has been widely used to solve path planning problems. By simulating the behavior of ants in finding the optimal path during foraging, the ant colony algorithm can find a near-optimal solution in a relatively short time. Summary of the invention

[0005] In view of the defects of the prior art, the present invention provides an improved ant colony drone inspection method for satellite integrated smart grid.

[0006] In order to achieve the above invention object, the technical solution adopted by the present invention is as follows:

[0007] An improved ant colony drone inspection method for satellite integrated smart grid includes the following steps:

[0008] Integrate drones into smart grids using satellite communication technology to inspect and monitor transmission lines and key components;

[0009] The drone is equipped with a satellite positioning system, which enables it to take off at key nodes and transmit inspection data to the control center in real time via satellite communications;

[0010] The inspection task of UAV is abstracted into the traveling salesman problem (TSP). By optimizing the flight distance, energy consumption and inspection priority, the optimal path that meets the automated inspection needs of smart grid is obtained.

[0011] The ant colony algorithm is used to optimize the drone inspection path. The ant colony algorithm accelerates the convergence of the path and improves the inspection efficiency by adjusting the release and evaporation mechanism of pheromones.

[0012] Furthermore, the pre-clustering traveling salesman model is used in the path planning process to cluster the transmission lines and key components that need to be inspected. The number of clusters is determined according to the number of channels within the inspection range to improve the inspection efficiency and path optimization effect.

[0013] Furthermore, the pre-clustering process uses the K-means algorithm to perform unsupervised learning on the inspection nodes in the inspection task.

[0014] Furthermore, the K-means algorithm comprises the following steps:

[0015] Select k initial cluster centers and assign each inspection node to the nearest cluster center based on the Euclidean distance. The number of k is related to the number of channels within the inspection range.

[0016] Recalculate the center point of each cluster and repeat the above steps until the cluster centers converge or the maximum number of iterations is reached.

[0017] Furthermore, the ant colony algorithm is an improved ant colony algorithm, and the improvements include the following points:

[0018] Pheromone update mechanism: When selecting a path, a double-layer pheromone update strategy is adopted, that is, different update rules are applied to the global optimal path and the local optimal path, which enhances the global search capability of the algorithm;

[0019] Heuristic information adjustment: By dynamically adjusting the parameter weights (α, β) in the heuristic information, the influence of pheromones and heuristic factors is adaptively adjusted according to different stages of the task to avoid falling into local optimality at an early stage;

[0020] Path selection strategy: Pre-clustering heuristic parameters are introduced for the path selection of cluster head nodes (key nodes), and the optimal path is selected according to the location of the cluster center, thereby optimizing the overall efficiency of the inspection.

[0021] Furthermore, the improved ant colony algorithm follows the following strategy in path planning:

[0022] The optimal path is selected based on the Euclidean distance and pheromone concentration between nodes, combined with dynamically adjusted heuristic parameters;

[0023] In the pheromone updating process, the global optimal ant releases more pheromones, while the local optimal ant path updates less pheromones, ensuring that both the global and local optimal paths can be optimized;

[0024] Through the evaporation mechanism of pheromones, excessive accumulation of pheromones is prevented and the algorithm is prevented from falling into the local optimum.

[0025] Compared with the prior art, the advantages of the present invention are:

[0026] 1. Improve inspection efficiency and accuracy

[0027] By introducing satellite communication technology, drones can perform inspection tasks of power transmission lines and their key components in remote areas or areas with unstable communications. Real-time data is transmitted to the control center to ensure the accuracy and timeliness of the inspection. Compared with traditional manual inspections, this method can significantly reduce the time spent on inspections and reduce the errors caused by human operations during the inspection process.

[0028] 2. Path optimization based on pre-clustering to improve the processing capabilities of large-scale scenarios

[0029] The present invention adopts the pre-clustering traveling salesman model to cluster the nodes to be inspected, and the number of clusters is adjusted according to the number of channels within the inspection range. This pre-processing method can effectively simplify the complexity of path planning, so that the drone can still efficiently complete the inspection task in large-scale inspection tasks, and improve the scalability and adaptability of the system.

[0030] 3. Improved ant colony algorithm (XACO) improves convergence speed and optimal path selection ability

[0031] By improving the pheromone update mechanism and path selection strategy in the ant colony algorithm, the algorithm has stronger global search capabilities and faster convergence speed. The introduction of a double-layer pheromone update strategy and dynamic adjustment of heuristic information effectively prevents the algorithm from falling into local optimality, and can quickly find the optimal path in multi-task or large-scale scenarios. Simulation experiments have shown that in the test environment of 60 and 120 nodes, the XACO algorithm has a significant optimization effect compared with the traditional ant colony algorithm (ACO) and the maximum minimum ant colony algorithm (MMAS), especially in terms of convergence speed and path quality.

[0032] 4.Excellent performance in large-scale and complex inspection tasks

[0033] The improved ant colony algorithm of the present invention has a significant performance improvement when processing large-scale, multi-path inspection tasks. Through the cooperation of the pre-clustering method, the XACO algorithm can effectively reduce the complexity of path search and always show a stable optimization effect in scenarios with different numbers of nodes, especially in the case of a large number of nodes, it has higher efficiency and reliability than traditional algorithms.

[0034] 5. Enhanced the stability and emergency response capabilities of smart grids

[0035] By integrating satellite communication technology, the present invention can monitor the operation status of smart grids in real time, especially in remote and communication-restricted areas, ensuring efficient inspection of key transmission lines and equipment. The system can quickly detect equipment failures and take timely countermeasures, improving the overall stability and emergency response capabilities of smart grids, reducing grid maintenance costs, and improving the safety of grid operations.

[0036] 6. Replace manual inspections to reduce costs and risks

[0037] By adopting the drone automated inspection system, the present invention replaces the traditional manual inspection method, which not only reduces the high cost of manual inspection, but also avoids the safety risks that may be faced when conducting manual inspections in harsh environments or high-risk areas, thereby improving the safety and efficiency of the inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a model diagram of a UAV inspection system in a satellite-integrated smart grid according to an embodiment of the present invention;

[0039] Figure 2 It is a flow chart of an improved ant colony inspection method for satellite integrated smart grid according to an embodiment of the present invention;

[0040] Figure 3 is a flow chart of cluster preprocessing according to an embodiment of the present invention;

[0041] Figure 4 is a flowchart of an improved ant colony algorithm according to an embodiment of the present invention;

[0042] Figure 5 This is a preliminary pilot location diagram of an embodiment of the present invention;

[0043] Figure 6 is an optimization result diagram of an embodiment of the present invention;

[0044] Figure 7 It is a convergence comparison diagram of the inspection algorithm in 60 point scenarios of the embodiment of the present invention;

[0045] Figure 8 It is a convergence comparison diagram of the inspection algorithm in 120 point scenarios of the embodiment of the present invention. Specific Embodiments

[0046] To make the objectives, technical solutions and advantages of the present invention more clear and understandable, the following provides further detailed descriptions of the present invention based on the accompanying drawings and by way of examples.

[0047] The present invention provides an improved ant colony UAV inspection method for a satellite integrated smart grid. Figure 1 The UAV inspection system model in the satellite integrated smart grid proposed by the present invention includes:

[0048] The inspection of the satellite integrated smart grid includes the inspection of key areas and key components such as insulators on transmission line towers, as well as the inspection of specific transmission line corridors.

[0049] Specifically, for the UAV flight trajectory optimization problem, a pre-clustering traveling salesman model can be established, and the number of clusters is determined by the number of corridors within the inspection range.

[0050] The traveling salesman problem (TSP) is a classic optimization problem. Its general form is: Given a set of cities and the distances between each pair of cities, find the shortest path that visits each city and returns to the starting city. Suppose the total number of cities to be visited is n, and let V = {v 1 , v 2 ,..., v n} represent the set of cities, and E = {(i, j): i, j ∈ V, i < j} represent the paths between them. TSP can be defined as a complete undirected graph, G = (V, E), where V represents the set of vertices and E represents the set of edges. Let D = (d ij ) represent the cost matrix. For the given vertex coordinates P i = (X i , Y i ), represents the Euclidean distance between two vertices.

[0051] The total number of traversable paths is (n - 1)! / 2.

[0052] Let the variable x ij represent whether the edge (i, j) is selected by the optimal path. x ij = 1 if and only if x ij is in the optimal path. The TSP optimization problem can be expressed as follows:

[0053]

[0054] In this formula, the constraint conditions (2) are respectively called the degree constraint, the sub-path elimination constraint, and the integrity constraint.

[0055] Since the inspection of power grid involves the inspection of key components of transmission towers and the detection of channels of specific transmission lines, the above complex situations should be comprehensively considered in path planning. It is a feasible solution to first classify the nodes that need to be traversed.

[0056] According to an embodiment of the present invention, an improved ant colony inspection method for satellite integrated smart grid is provided. Figure 2 As shown, the following steps are included:

[0057] Step 101: pre-clustering processing.

[0058] Specifically, according to the area and number of nodes that need to be inspected in the inspection task, the paths are preliminarily classified and clustered. This step uses the K-means algorithm to divide the nodes that need to be traversed into different clusters, thereby reducing the complexity of subsequent path planning.

[0059] The number of clusters is related to the number of paths within the inspection range, which can enable the system to handle large-scale inspection tasks more efficiently. The input of the K-means clustering algorithm is a set of unlabeled nodes that need to be traversed, denoted as V = {v 1 ,v 2 ,...,v n}, it is necessary to divide the samples into k clusters through unsupervised learning.

[0060] like Figure 3 As shown, clustering preprocessing includes:

[0061] Step 201, select the initial cluster center.

[0062] Specifically, k cluster centers are selected, that is, there are k clusters c k ,

[0063] μ 1 ,μ 2 ,...,μ k ∈R n (3)

[0064] Step 202, each data point is assigned to the nearest cluster center

[0065] Specifically, for each node v i , calculate its relationship with each cluster center μ j The distance v i Belongs to the nearest cluster c j ,

[0066] c j =argmin j ||X i -μ j || 2 ,j∈1,2,...,k. (4)

[0067] Step 203, recalculate the cluster center.

[0068] Specifically, for each cluster c j , recalculate the center point,

[0069]

[0070] Step 202 and step 203 are repeated until the algorithm converges or the maximum number of iterations is reached.

[0071] The number of clusters k is related to the number of paths within the inspection range.

[0072] Step 102, improving the ant colony inspection algorithm.

[0073] Specifically, the ant colony algorithm is designed based on the characteristic that ants tend to choose trajectories with high pheromone concentrations when searching for paths. Ants release pheromones when foraging, and the pheromones evaporate over time. Based on this characteristic, shorter paths can retain more pheromones, and over time, most ants will choose shorter paths, thus finding the shortest path. In the basic ant colony algorithm, artificial ants have the following characteristics:

[0074] (1) Artificial ants in the city i Select the next city based on pheromones and heuristic information v j .

[0075] (2) When the artificial ants move from the city v i Move to the city v j Or when a cycle is completed, the ant will release a certain amount of pheromone τ(i,j) on the path (i,j).

[0076] (3) In a cycle, artificial ants will not choose cities that they have already visited.

[0077] The kth artificial ant in the city v i Select next cityv j The probability is expressed as:

[0078]

[0079] Where η(i,j) is the pheromone concentration on the path (i,j). In the TSP problem, usually η(i,j) is the inverse of the length of the path (i,j). is the set of all cities that the kth artificial ant has not passed through, and α, β represent the relative weights of pheromone and heuristic information, which are used to control the proportion of τ(i, j) and η(i, j) in decision making.

[0080] In the ant colony system, the global optimal artificial ant performs global pheromone release, and the update rule is as follows:

[0081] τ(i,j)←(1 - ω)τ(i,j)+ωΔτ(i,j) (7)

[0082]

[0083] where ω is the evaporation coefficient of the global pheromone (0 < ω < 1), and L gb represents the length of the global optimal path.

[0084] The non - global optimal artificial ants update the pheromone according to the following rule:

[0085] τ(i,j)←(1 - r)τ(i,j)+rΔτ(i,j) (9)

[0086] where r ∈ (0 < r < 1) is the local pheromone parameter.

[0087] Figure 4 shows the pre - clustering process of the improved ant colony algorithm (XACO) in the power grid inspection path. When the artificial ant traverses a node, if the node is judged to be a cluster - head node, the path selection is based on the heuristic parameters provided by this node.

[0088] Step 103, simulation experiment verification.

[0089] Specifically, a comparison is made among the standard ant colony algorithm (Ant Colony Algorithm, ACO), the max - min ant system (Max - Min Ant System, MMAS), and the improved ant colony algorithm (XACO). The test maps used include 60 nodes on 2 paths and 120 nodes on 3 paths, aiming to test the performance of the algorithms under different numbers of nodes. The simulation experiment runs on the Windows 10 Professional 22H2 operating system and is implemented using Python 3.8.10 and standard libraries (such as NumPy, SciPy, Matplotlib). In terms of hardware configuration, the processor is an AMD Ryzen 7 3700X 8 - core processor with a main frequency of 3.59 GHz and a memory capacity of 16.0 GB.

[0090] In a 100×100 area, 60 points are randomly scattered to construct the position information and lines required for satellite - integrated smart grid inspection. Figure 5 shows the position distribution of the initial points.

[0091] The optimization results are as Figure 6 shown. It can be clearly seen the trajectories of the two paths in the case of 60 nodes.

[0092] Comparison of algorithm convergence in 60-node scenario Figure 7 As shown in the figure, it can be clearly seen that the XACO algorithm shows a faster convergence speed in the early stage of the search. The final performance of the evaluation function of the XACO algorithm is also the best, and the convergence is completed at the 94th iteration. In contrast, the final paths of the mACO algorithm and the ACO algorithm are relatively long. Compared with ACO and mACO, XACO improves the evaluation function by 1.30% and 1.66% on average, respectively.

[0093] Comparison of algorithm convergence in 120-node scenario Figure 8 As shown. Unlike the 60-node scenario, the XACO algorithm took the lead in the early stages of the algorithm, and in the case of multiple paths, the pre-clustering algorithm was more able to demonstrate its advantages. In the subsequent convergence process, ACO and mACO crossed in the first 20 iterations, and the XACO algorithm always converged faster throughout the search process. In the end, in terms of the evaluation function, the XACO algorithm was 8.18% and 4.55% higher than ACO and mACO on average, respectively.

[0094] Satellite-integrated smart grids have shown significant advantages in scenarios such as communication coverage in remote areas, network anomaly detection, and efficient emergency response. By establishing a pre-clustered traveling salesman model, a UAV dynamic path planning strategy based on an improved ant colony algorithm was designed to achieve efficient and reliable inspections of key monitoring areas, important equipment components, and key transmission cable paths in smart grids, thereby replacing the traditional manual inspection method that is costly, risky, and difficult. Simulation results show that the proposed XACO algorithm is superior to the ACO and mACO algorithms in terms of convergence speed and evaluation effect, especially in large-scale scenarios.

[0095] The method according to the present invention described above may be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and will be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor, or hardware, the improved ant colony drone inspection method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the processing shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the processing shown herein.

[0096] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the implementation methods of the present invention, and should be understood that the protection scope of the present invention is not limited to such special statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. An improved ant colony drone inspection method for satellite integrated smart grid, characterized in that: The following steps are involved: Integrate drones into smart grids using satellite communication technology to inspect and monitor transmission lines and key components; The drone is equipped with a satellite positioning system, which enables it to take off at key nodes and transmit inspection data to the control center in real time via satellite communications; The inspection task of drones is abstracted into the traveling salesman problem (TSP). By optimizing the flight distance, energy consumption and inspection priority, the optimal path that meets the needs of automated inspection of smart grids is obtained. The ant colony algorithm is used to optimize the drone inspection path. The ant colony algorithm accelerates the convergence of the path and improves the inspection efficiency by adjusting the release and evaporation mechanism of pheromones.

2. The improved ant colony drone inspection method according to claim 1 is characterized by: The pre-clustering traveling salesman model is used in the path planning process to cluster the transmission lines and key components that need to be inspected. The number of clusters is determined according to the number of channels within the inspection range to improve the inspection efficiency and path optimization effect.

3. The improved ant colony drone inspection method according to claim 1 is characterized in that: The pre-clustering process uses the K-means algorithm to perform unsupervised learning on the inspection nodes in the inspection task.

4. The improved ant colony drone inspection method according to claim 3 is characterized by: The K-means algorithm includes the following steps: Select k initial cluster centers and assign each inspection node to the nearest cluster center based on the Euclidean distance. The number of k is related to the number of channels within the inspection range. Recalculate the center point of each cluster and repeat the above steps until the cluster centers converge or the maximum number of iterations is reached.

5. The improved ant colony drone inspection method according to claim 1 is characterized by: The ant colony algorithm is an improved ant colony algorithm, and the improvements include the following points: Pheromone update mechanism: When selecting a path, a double-layer pheromone update strategy is adopted, that is, different update rules are applied to the global optimal path and the local optimal path, which enhances the global search capability of the algorithm; Heuristic information adjustment: By dynamically adjusting the parameter weights in the heuristic information, the influence of pheromones and heuristic factors can be adaptively adjusted according to the different stages of the task to avoid falling into the local optimum at an early stage; Path selection strategy: Pre-clustering heuristic parameters are introduced into the path selection of cluster head nodes, and the optimal path is selected according to the location of the cluster center, thereby optimizing the overall efficiency of the inspection.

6. The improved ant colony drone inspection method according to claim 5 is characterized by: The improved ant colony algorithm follows the following strategies when planning paths: The optimal path is selected based on the Euclidean distance and pheromone concentration between nodes, combined with dynamically adjusted heuristic parameters; In the pheromone updating process, the global optimal ant releases more pheromones, while the local optimal ant path updates less pheromones, ensuring that both the global and local optimal paths can be optimized; Through the evaporation mechanism of pheromones, excessive accumulation of pheromones is prevented and the algorithm is prevented from falling into the local optimum.

Images