High-voltage line tower path planning algorithm based on genetic algorithm
By applying a path planning algorithm based on genetic algorithm in high-voltage transmission line path planning, the problem that traditional methods are difficult to make optimal decisions in complex environments is solved, and efficient and accurate path planning is achieved, which is suitable for changing environments. Power line layout.
Patent Information
- Application Number
- CN202411502565.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2025-02-07
AI Technical Summary
Traditional high-voltage transmission line path planning methods are difficult to make optimal decisions under variable terrain, geological, environmental and meteorological conditions, and are difficult to effectively integrate and utilize large amounts of data to support complex decision-making processes.
Using a path planning algorithm based on genetic algorithm, unavailable areas are eliminated and buffers are established through data preprocessing, grids are divided and feasibility index is evaluated, and path optimization is used by genetic algorithms, including initial path generation, path selection, crossover, mutation and Post-processing.
It improves the speed and accuracy of path planning, and can quickly obtain high-quality line solutions in complex environments. Taking into account a variety of factors, it improves the adaptability and overall performance of the line.
Smart Images
Figure CN119398294A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of electric power engineering, and in particular relates to a high-voltage line tower path planning algorithm based on a genetic algorithm. Background Art
[0002] In the field of power engineering, path planning of high-voltage transmission lines is crucial to ensure the safe, stable and economical operation of power systems. Traditional path planning methods mainly rely on engineers' experience and qualitative analysis, which often have difficulty in making optimal decisions when faced with changing terrain, geology, environment and meteorological conditions. With the growth of electricity demand and the expansion of the scale of transmission lines, traditional planning methods can no longer meet the requirements of modern power systems for high efficiency and high precision.
[0003] In addition, although modern technology has made significant progress in data collection and processing, how to effectively integrate and utilize this data to support complex decision-making processes remains a challenge. Existing technical means, including but not limited to topographic mapping, geological exploration, and environmental assessment, although providing the necessary data support for path planning, still have certain limitations in converting this data into practical and feasible planning schemes. Therefore, the field of power engineering urgently needs a new path planning method that can consider various influencing factors more comprehensively and in-depth to achieve a more scientific and reasonable line layout. Summary of the invention
[0004] In view of the above problems, the present invention provides a high-voltage tower path planning algorithm based on genetic algorithm, which realizes automatic optimization of the path by simulating natural selection and genetic mechanism.
[0005] The specific technical solution is: a high-voltage tower path planning algorithm based on genetic algorithm, comprising the following steps: Data preprocessing: using existing data to exclude unavailable areas and establish buffer zones. Divide the available area into several grids and assess the feasibility index of each grid; Path planning algorithms, including primary path generation and genetic algorithm applications; The initial path generation includes: determining the safe area where the starting point and the end point can connect to other nodes (high-voltage towers), randomly selecting nodes (high-voltage towers) in the area and calculating their safe areas, repeating this process until the safe area of the end point is extended, and connecting the end point to obtain several paths, evaluating each path and setting threshold screening; Genetic algorithm applications include: Path selection based on sorting selection algorithm; Intersect the path sequence; Apply a mutation algorithm to the path sequence; Evaluate and iterate the paths; Post-processing, the generated path data are further selected and evaluated, and manually adjusted and improved.
[0006] Further, the method of using the existing data to exclude the unavailable area and establish the buffer zone includes: Utilizing existing digital elevation model data, cadastral data, geological data, environmental data, and meteorological data, the geographic information system is used to exclude unusable areas, establish buffer zones, and conduct overlay analysis.
[0007] Furthermore, the formula for evaluating the feasibility index of each grid is as follows: (1) Formula (1) uses the weighted summation method, where A(x, y) represents the comprehensive feasibility index of the pixel with coordinates (x, y); G(x, y) represents the feasibility of the geological conditions of the pixel; E(x, y) represents the feasibility of the electromagnetic environment of the pixel; M(x, y) represents the feasibility of the meteorological conditions of the pixel; O(x, y) is the feasibility of other influencing factors of the pixel; ω1, ω2, ω3, and ω4 are the weight coefficients of each feasibility, satisfying the condition that the sum of the weights is 1; this formula can be expanded or simplified according to actual needs.
[0008] Further, the path selection based on the sorting selection algorithm includes: Calculate the average feasibility index of the first generation paths and sort them according to the feasibility index; The selection probability is allocated based on the index allocation formula, so that the path with higher feasibility index has a higher selection probability; The paths are randomly selected based on the assigned probabilities.
[0009] Furthermore, the index allocation formula is as follows: Assume that there are N primary paths, and the probability of selecting the i-th path is P i The calculation formula is: (2) Here, e is the base of natural logarithms.
[0010] Further, the crossing of the path sequence includes: Based on single-point crossing, two paths with crossing nodes (high-voltage towers) are randomly selected, and the path sequence after the crossing node (high-voltage tower) is exchanged to generate two sub-paths; Based on double-point crossing, two paths with double crossing nodes (high-voltage towers) are randomly selected, and the path sequence between the two crossing nodes (high-voltage towers) is exchanged to generate two sub-paths.
[0011] Further, the applying a mutation algorithm to the path sequence includes: Based on Gaussian mutation, random values drawn from Gaussian distribution are added to the path sequence to introduce mutation; Based on the idea of non-uniform variation, the amplitude of the above Gaussian variation gradually decreases with the increase of the number of iterations.
[0012] Further, the Gaussian variation method includes: Remove the starting point and the end point, randomly select the path and the node (high-voltage tower) on the path, and add Gaussian noise to the coordinates of the node (high-voltage tower); For a path X=(x1, x2, …, x n ), where x i represents the coordinates of a node (high-voltage line tower) on the path, then the Gaussian variation formula is as follows: (3) Where N(μ,σ) represents Gaussian noise with mean μ and standard deviation σ.
[0013] Further, the evaluating and iterating the path includes: Evaluate the feasibility index of the offspring paths generated after each round of applying the genetic algorithm; Set the threshold to filter the descendant paths; The genetic algorithm is applied again to the offspring path and iterated until a certain feasibility index or number of iterations is reached.
[0014] Further, the post-processing includes: Based on the actual application scenarios, safety, efficiency and cost-effectiveness of the path, the iterative results are further selected and evaluated, and the iterative results are manually locally optimized, the obstacle avoidance strategy is adjusted, and the path is smoothed.
[0015] Beneficial effects of the invention: The invention solves the complex optimization problem in high-voltage tower path planning by introducing a genetic algorithm. The proposed path planning method has significant advantages in algorithm efficiency and solution quality, and is particularly suitable for power line layout in a changing environment, showing broad application potential.
[0016] It can be seen that the present invention has the following advantages over the traditional path planning method: 1. Efficiency and accuracy: The present invention greatly improves the speed and accuracy of path planning, ensuring that high-quality route plans can be quickly obtained even in complex environments.
[0017] 2. Comprehensive consideration of multiple factors such as terrain, geology, environment and meteorology enables multi-dimensional evaluation and optimization of the route plan, improving the adaptability and overall performance of the route.
[0018] 3. While maintaining the advantages of the algorithm, it also takes into account the special needs of actual engineering, enhancing the practicality and flexibility of the solution. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 It is a basic flow chart of a high-voltage tower path planning algorithm based on a genetic algorithm in an embodiment of the present invention; Figure 2 A schematic diagram of gridding of available areas in an embodiment of the present invention; Figure 3 A schematic diagram of finding a safe area for any node in an embodiment of the present invention; Figure 4 A schematic diagram of a single-point intersection of paths in an embodiment of the present invention; Figure 5 Schematic diagram of a double-point intersection of paths in an embodiment of the present invention. DETAILED DESCRIPTION
[0020] In order to make the technical problems and technical solutions solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0021] like Figure 1 As shown, the present invention provides a high-voltage tower path planning algorithm based on a genetic algorithm, which specifically includes the following steps: S100. Data preprocessing: using existing data to exclude unavailable areas and establish buffer zones. Divide the available areas into several grids and assess the feasibility index of each grid; S200. Path planning algorithms, including primary path generation and genetic algorithm application; S300. Post-processing, further selection and evaluation of the generated path data, and allowing manual adjustment and improvement.
[0022] In this embodiment, the preprocessing described in step S100 includes: S101. Establishing Availability Zones Specifically, the existing digital elevation model data, cadastral data, geological data, environmental data and meteorological data are utilized, and the geographic information system is used to exclude unavailable areas, establish buffer zones and conduct overlay analysis.
[0023] S102. Grid area, assess feasibility grid by grid Specifically, refer to Figure 2,Due to the complexity of the actual area, a single evaluation method may not be able to fully reflect the construction suitability of each area. ,It is necessary to grid the available areas and conduct a comprehensive evaluation of each grid area to ,solve the problem of a single evaluation method.
[0024] Furthermore, the formula for calculating the feasibility index of each grid is as follows: (1) Formula (1) uses the weighted summation method, where A(x, y) represents the comprehensive feasibility index of the pixel with coordinates (x, y); G(x, y) represents the feasibility of the geological conditions of the pixel; E(x, y) represents the feasibility of the electromagnetic environment of the pixel; M(x, y) represents the feasibility of the meteorological conditions of the pixel; O(x, y) is the feasibility of other influencing factors of the pixel; ω1, ω2, ω3, and ω4 are the weight coefficients of each feasibility, satisfying the condition that the sum of the weights is 1; this formula can be expanded or simplified according to actual needs.
[0025] In this embodiment, the path planning algorithm described in step S200 includes: S201. Initial path generation Specifically, refer to Figure 2 and Figure 3 ,Since the lack of effective initial paths may lead to slow convergence of the ,generic algorithm, it is necessary to generate the initial path that meets ,safety requirements in the available area to solve the problem of algorithm ,startup efficiency.
[0026] Further, such as Figure 2 As shown, the starting point and the end point are marked in the available area, and the shortest and longest safe distances between the two points for placing subsequent nodes (high-voltage towers) in any direction are calculated according to the feasibility index of the grid around the node (high-voltage tower), and the enclosed area and the available area are superimposed to obtain the safety area of the point; several nodes are randomly selected in the safety area of the starting point, and the safety area of the node is calculated; the above steps are repeated, and subsequent path nodes are randomly selected until the safety area of the end point is extended, and the end point is connected to obtain several paths; each path is then evaluated and a threshold is set for screening.
[0027] Furthermore, the shortest and longest safe distances of nodes (high-voltage towers) are calculated based on the feasibility index of the grid around the node, including: Figure 3 As shown, the shortest and longest safety distances are set, and within the limit range, the grids are traversed from the outside to the inside; the current grid is connected to the previous node, and the average feasibility index of the passing grids is calculated; a feasibility index threshold is set, and when the average feasibility index of the passing grids is greater than the threshold, the distance from the grid to the previous node is the shortest or longest safety distance in this direction.
[0028] S202. Genetic Algorithm Application Specifically, refer to Figure 4 and Figure 5 , step S202 includes: S2021. Path selection Specifically, the average feasibility index of the first generation of paths is calculated and sorted according to the feasibility index; the selection probability is allocated based on the index allocation formula so that the path with a higher feasibility index has a higher selection probability; and the path is randomly selected based on the allocated probability.
[0029] Furthermore, the index allocation formula is as follows: Assume that there are N primary paths, and the probability of selecting the i-th path is P i The calculation formula is: (2) Here, e is the base of natural logarithms.
[0030] S2022. Paths Crossing Specifically, a single path is regarded as a chromosome, and the path node is regarded as a single gene, then crossover can be regarded as a gene exchange operation between chromosomes.
[0031] Furthermore, the present invention is based on two crossover methods, namely: based on single-point crossover, such as Figure 3 As shown in , two paths with crossing nodes (high-voltage towers) are randomly selected, and the path sequence after the crossing node (high-voltage tower) is exchanged to generate two sub-paths; based on the double-point crossing, as Figure 4 As shown, two paths with double crossing nodes (high-voltage towers) are randomly selected, and the path sequence between the two crossing nodes (high-voltage towers) is exchanged to generate two sub-paths.
[0032] S2023. Mutation Algorithm Specifically, since genetic algorithms may have convergence problems during the iteration process, it is necessary to apply mutation algorithms to introduce new path features to solve the problem of insufficient algorithm convergence.
[0033] Furthermore, the present invention is based on two mutation methods, namely: based on Gaussian mutation, random values drawn from Gaussian distribution are added to the path sequence to introduce mutation; based on the idea of non-uniform mutation, the amplitude of the above Gaussian mutation gradually decreases with the increase of the number of iterations.
[0034] Furthermore, the Gaussian mutation method includes: removing the starting point and the end point, randomly selecting the path and the nodes (high-voltage towers) on the path, and adding Gaussian noise to the coordinates of the nodes (high-voltage towers); for the path X=(x1, x2, …, x n ), where x irepresents the coordinates of a node (high-voltage line tower) on the path, then the Gaussian variation formula is as follows: (3) Where N(μ,σ) represents Gaussian noise with mean μ and standard deviation σ.
[0035] S2024. Evaluate and Iterate Specifically, the feasibility index of the offspring path generated after each round of applying the genetic algorithm is evaluated; a threshold is set to screen the offspring path; the genetic algorithm is applied to the offspring path again and iterated until a certain feasibility index or number of iterations is reached.
[0036] In this embodiment, the post-processing in step S300 includes: S301. Further selection and evaluation Specifically, the iteration results are further selected and evaluated based on the actual application scenarios, safety, efficiency, and cost-effectiveness of the paths.
[0037] S302. Manual optimization adjustment Specifically, the iterative results are manually optimized locally, the obstacle avoidance strategy is adjusted, and the path is smoothed.
[0038] The present invention is described in detail above through specific and preferred embodiments, but those skilled in the art should understand that the present invention is not limited to the embodiments described above, and any modifications, equivalent substitutions, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A high-voltage tower path planning algorithm based on genetic algorithm, characterized in that: The following steps are involved: Data preprocessing: using existing data to exclude unavailable areas and establish buffer zones. Divide the available area into several grids and assess the feasibility index of each grid; Path planning algorithms, including primary path generation and genetic algorithm applications; The initial path generation includes: determining the safe area where the starting point and the end point can connect to other nodes, randomly selecting nodes in the area and calculating their safe areas, repeating this process until the safe area of the end point is extended, and connecting the end point to obtain several paths, evaluating each path and setting a threshold for screening; Genetic algorithm applications include: Path selection based on sorting selection algorithm; Intersect the path sequence; Apply a mutation algorithm to the path sequence; Evaluate and iterate the paths; Post-processing, the generated path data are further selected and evaluated, and manually adjusted and improved.
2. A high-voltage tower path planning algorithm based on genetic algorithm according to claim 1, characterized in that: The method of using the existing data to exclude the unavailable area and establish the buffer zone includes: Utilizing existing digital elevation model data, cadastral data, geological data, environmental data, and meteorological data, the geographic information system is used to exclude unusable areas, establish buffer zones, and conduct overlay analysis.
3. The high-voltage line tower path planning algorithm based on genetic algorithm according to claim 1 is characterized in that: The formula for evaluating the feasibility index of each grid is as follows: （1） Formula (1) uses the weighted summation method, where A(x, y) represents the comprehensive feasibility index of the pixel with coordinates (x, y); G(x, y) represents the feasibility of the geological conditions of the pixel; E(x, y) represents the feasibility of the electromagnetic environment of the pixel; M(x, y) represents the feasibility of the meteorological conditions of the pixel; O(x, y) is the feasibility of other influencing factors of the pixel; ω1, ω2, ω3, and ω4 are the weight coefficients of each feasibility, satisfying the condition that the sum of the weights is 1; this formula can be expanded or simplified according to actual needs.
4. The high-voltage line tower path planning algorithm based on genetic algorithm according to claim 1 is characterized in that: The path selection based on the sorting selection algorithm includes: Calculate the average feasibility index of the first generation paths and sort them according to the feasibility index; The selection probability is allocated based on the index allocation formula, so that the path with higher feasibility index has a higher selection probability; The paths are randomly selected based on the assigned probabilities.
5. A high-voltage tower path planning algorithm based on genetic algorithm according to claim 4, characterized in that: The index allocation formula is as follows: Assume that there are N primary paths, and the probability of selecting the i-th path is P i The calculation formula is: （2） Here, e is the base of natural logarithms.
6. The high-voltage tower path planning algorithm based on genetic algorithm according to claim 1 is characterized in that: The crossing of the path sequence comprises: Based on single-point crossover, two paths with crossover nodes are randomly selected, and the path sequence after the crossover node is exchanged to generate two sub-paths; Based on double-point crossover, two paths with double crossover nodes are randomly selected, and the path sequence between the two crossover nodes is exchanged to generate two sub-paths.
7. The high-voltage line tower path planning algorithm based on genetic algorithm according to claim 1 is characterized in that: The applying a mutation algorithm to the path sequence comprises: Based on Gaussian mutation, random values drawn from Gaussian distribution are added to the path sequence to introduce mutation; Based on the idea of non-uniform variation, the amplitude of the above Gaussian variation gradually decreases with the increase of the number of iterations.
8. The high-voltage tower path planning algorithm based on genetic algorithm according to claim 7 is characterized in that: The Gaussian variation method includes: Remove the starting point and the end point, randomly select the path and the nodes on the path, and add Gaussian noise to the node coordinates; For a path X=(x1, x2, …, x n ), where x i represents the coordinates of a node on the path, then the Gaussian variation formula is as follows: （3） Where N(μ,σ) represents Gaussian noise with mean μ and standard deviation σ.
9. The high-voltage tower path planning algorithm based on genetic algorithm according to claim 1, characterized in that: The evaluating and iterating the path includes: Evaluate the feasibility index of the offspring paths generated after each round of applying the genetic algorithm; Set the threshold to filter the descendant paths; The genetic algorithm is applied again to the offspring path and iterated until a certain feasibility index or number of iterations is reached.
10. The high-voltage tower path planning algorithm based on genetic algorithm according to claim 1, characterized in that: The post-processing includes: Based on the actual application scenarios, safety, efficiency and cost-effectiveness of the path, the iterative results are further selected and evaluated, and the iterative results are manually locally optimized, the obstacle avoidance strategy is adjusted, and the path is smoothed.