Power transmission line path planning method and control device

Abstract

The application discloses a power transmission line path planning method and a control device, and relates to the technical field of power transmission line path planning. The method comprises the following steps: acquiring a plurality of target planning times and a plurality of space parameters corresponding to a target planning area, and unifying the time bases of the plurality of space parameters based on the plurality of target planning times to construct a multi-source space-time parameter library corresponding to the plurality of target planning times and comprising a plurality of grid units; calculating the comprehensive cost of each grid unit in the multi-source space-time parameter library under each target planning time based on a continuous penalty function to construct a space-time cost surface corresponding to the plurality of target planning times; searching the space-time cost surface of the plurality of target planning times based on an NSGA-II algorithm to generate a Pareto optimal path of the target planning area corresponding to the plurality of target planning times, so as to acquire an optimal planning path of the power transmission line in the target planning area. The application aims to improve the adaptability of automatic route selection of the power transmission line.

Description

Technical Field

[0001] This invention relates to the field of power transmission line route planning technology, and in particular to a power transmission line route planning method and control device. Background Technology

[0002] Traditional transmission line selection methods mainly rely on manual surveying and experience-based judgment, which suffers from drawbacks such as low efficiency, high subjectivity, and difficulty in quantitative evaluation. Although GIS-based automated route selection technology has been applied, the following problems still exist: 1. Existing GIS route selection methods are all based on static data from a single time section for route planning, ignoring dynamic factors such as the evolution of geological disaster risks over time, the annual expansion of urban planning boundaries, and the regular revision of ecological protection policies. This will lead to the forced relocation of power transmission lines, resulting in wasted engineering investment.

[0003] 2. Existing methods typically impose hard constraints on specific terrain conditions (such as the need to avoid areas with slopes greater than 25°), leading to a severe contraction or even no solution in complex terrain areas (such as Yunnan, where mountains account for more than 80%). Furthermore, traditional cost modeling simply binarizes constraints (pass / fail), lacking a quantitative description of the intermediate state of "passable but requiring additional costs," thus failing to flexibly weigh trade-offs in route selection optimization.

[0004] Therefore, existing automated route selection technologies suffer from poor adaptability. Summary of the Invention

[0005] The main objective of this invention is to provide a method and control device for power transmission line route planning, which aims to improve the adaptability of automated route selection for power transmission lines.

[0006] To achieve the above objectives, this invention proposes a method for planning transmission line routes, the method comprising: The target planning location is obtained by acquiring multiple target planning times and multiple spatial parameters, and the time base of multiple spatial parameters is unified based on multiple target planning times. The target planning location is also gridded to construct a multi-source spatiotemporal parameter library that corresponds to multiple target planning times and includes multiple grid cells. The comprehensive cost calculation of each grid cell in the multi-source spatiotemporal parameter library under each target planning time is based on the continuous penalty function to construct the spatiotemporal cost surface corresponding to multiple target planning times; The spatiotemporal cost surface of multiple target planning times is searched based on the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times. Based on the Pareto optimal path of the target planning location for multiple target planning times, the optimal planning path of the transmission line to the target planning location is obtained through path migration analysis, cost sensitivity analysis, and robust path recommendation.

[0007] In one embodiment, the step of obtaining multiple target planning times and multiple spatial parameters corresponding to the target planning location, and unifying the time base of the multiple spatial parameters based on the multiple target planning times to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells specifically includes: Obtain multiple target planning times corresponding to the target planning location; Acquire terrain data, environmental constraint data, environmental planning data, and power grid data corresponding to multiple target planning times in the target planning area, and transform the terrain data, environmental constraint data, environmental planning data, and power grid data to a preset projection coordinate system based on multiple target planning times to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells; Among them, terrain data, environmental constraint data, environmental planning data and power grid data between multiple target planning times are obtained through spatiotemporal kriging interpolation and then converted to a preset projection coordinate system based on a unified time reference for multiple target planning times.

[0008] In one embodiment, the terrain data includes a digital elevation model, a digital surface model, and slope and aspect derived data; the environmental constraint data includes ecological protection red line vector data and geological disaster risk time-series raster; the environmental planning data includes urban master planning map patches, territorial spatial planning data, and transportation network planning alignments; and the power grid data includes the location and capacity of existing substations, coordinates of planned load centers, and predicted load values.

[0009] In one embodiment, the step of calculating the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library for each target planning time based on a continuous penalty function to construct a spatiotemporal cost surface corresponding to multiple target planning times specifically includes: Based on the sum of the basic terrain cost function, environmental constraint cost function, and planning conflict cost function, the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library under each target planning time is determined, so as to construct a spatiotemporal cost surface corresponding to multiple target planning times.

[0010] In one embodiment; The comprehensive cost is ; Wherein, the basic terrain cost function is The environmental constraint cost function is: The planning conflict cost function is: The For the slope, the For the degree of terrain roughness, the The normalization coefficient; For the first The time-varying weights of environmental constraints in year t The distance decay function is defined as the distance between the core area, buffer zone, and outer perimeter. as well as, ,and Each target planning time Monotonically increasing, For grid cells.

[0011] In one embodiment, the core area cost is set to a maximum value. The buffer is based on distance. exponential decay function Calculate the cost, the The attenuation constant is used; the cost of the outer area is set to 1.5 times the preset base cost.

[0012] In one embodiment, the step of searching the spatiotemporal cost surface of multiple target planning times based on the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to the multiple target planning times specifically includes: Based on the comprehensive cost of each grid cell in the spatiotemporal cost surface with multiple target planning times, multiple planning paths with planning path costs within the target cost range are generated; the planning path is a set of ordered grid node sequences. , Starting from, The endpoint is defined as the grid cell with adjacent nodes connected within 8 neighborhoods; the planned path cost is the sum of the total costs of all grid cells from the starting point to the endpoint. Based on the generated multiple planned paths, the overall path cost, total path length, and corner smoothness are minimized to obtain the optimized planned path. Based on the continuous penalty function, multiple optimization planning paths are screened to obtain multiple constrained planning paths; The NSGA-II algorithm is used to filter multiple constrained planning paths to generate Pareto optimal paths for target planning locations corresponding to multiple target planning times.

[0013] In one embodiment, the step of filtering multiple constrained planning paths based on the NSGA-II algorithm to generate Pareto optimal paths for target planning locations corresponding to multiple target planning times specifically includes: Based on path topology, the crossover operator and adaptive variable asynchronous length pair are used to cross multiple constrained planning paths at the common nodes of the two parent paths to obtain the Pareto optimal path set for the target planning location at multiple target planning times. Based on the inflection point automatic screening mechanism, Pareto optimal paths for target planning locations corresponding to multiple target planning times are generated by calculating the marginal substitution rate change between adjacent path solutions in the Pareto optimal path set.

[0014] In one embodiment, the adaptive variable asynchronous length includes an exponential decay function. ; Among them, the For the initial variable asynchronous length, the For the current algebra, It is the largest algebra.

[0015] The present invention also proposes a control device comprising a memory, a processor, and a transmission line path planning program stored in the memory and executable on the processor, the transmission line path planning program being configured to implement the steps of the transmission line path planning method as described in any of the preceding claims.

[0016] This invention employs a transmission line route planning method that effectively improves the adaptability of automated transmission line route selection. It acquires multiple target planning times and spatial parameters corresponding to the target planning location, unifies the time base of the spatial parameters based on the multiple target planning times, and performs gridding processing on the target planning location to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells. Based on a continuous penalty function, it calculates the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library for each target planning time to construct a spatiotemporal cost surface corresponding to multiple target planning times. It then searches the spatiotemporal cost surface of multiple target planning times using the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to the multiple target planning times. Based on the Pareto optimal path of the target planning location for multiple target planning times, it obtains the optimal planned path of the transmission line to the target planning location through path migration analysis, cost sensitivity analysis, and robust path recommendation. This approach enables intelligent route selection for transmission lines in complex scenarios that comprehensively consider topography, ecological environment, dynamic changes in urban planning, and multi-dimensional cost trade-offs. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the transmission line path planning method of the present invention; Figure 2 This is a flowchart illustrating an embodiment of the transmission line path planning method of the present invention; Figure 3 This is a flowchart illustrating another embodiment of the transmission line path planning method of the present invention; Figure 4 This is a flowchart illustrating another embodiment of the transmission line path planning method of the present invention; Figure 5 This is a schematic diagram of the spatiotemporal cost surface in the transmission line path planning method of the present invention; Figure 6 This is a schematic diagram of the Pareto optimal path under multiple target planning times in the transmission line path planning method of the present invention.

[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0022] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0023] Traditional transmission line selection methods mainly rely on manual surveying and experience-based judgment, which suffers from drawbacks such as low efficiency, high subjectivity, and difficulty in quantitative evaluation. Although GIS-based automated route selection technology has been applied, the following problems still exist: 1. Existing GIS route selection methods are all based on static data from a single time section for route planning, ignoring dynamic factors such as the evolution of geological disaster risks over time, the annual expansion of urban planning boundaries, and the regular revision of ecological protection policies. This will lead to the forced relocation of power transmission lines, resulting in wasted engineering investment.

[0024] 2. Existing methods typically impose hard constraints on specific terrain conditions (such as the need to avoid areas with slopes greater than 25°), leading to a severe contraction or even no solution in complex terrain areas (such as Yunnan, where mountains account for more than 80%). Furthermore, traditional cost modeling simply binarizes constraints (pass / fail), lacking a quantitative description of the intermediate state of "passable but requiring additional costs," thus failing to flexibly weigh trade-offs in route selection optimization.

[0025] Therefore, existing automated route selection technologies suffer from poor adaptability.

[0026] To solve the above problems, refer to Figure 1 and Figure 6 This invention proposes a method for planning transmission line routes, the method comprising: Step S100: Obtain multiple target planning times and multiple spatial parameters corresponding to the target planning location, unify the time base of multiple spatial parameters based on multiple target planning times, and perform gridding processing on the target planning location to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells; Step S200: Calculate the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library for each target planning time based on the continuous penalty function, so as to construct the spatiotemporal cost surface corresponding to multiple target planning times; Step S300: Search the spatiotemporal cost surface of multiple target planning times based on the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times; Step S400: Based on the Pareto optimal path of the target planning location for multiple target planning times, obtain the optimal planning path of the transmission line to the target planning location through path migration analysis, cost sensitivity analysis, and robust path recommendation.

[0027] It is understandable that the planning of transmission line routes needs to consider the spatial characteristics of the target planning area. However, the planning of transmission line routes needs to consider not only spatial characteristics but also time factors. This is because the spatial characteristics of the target planning area may change over time. Therefore, when planning the number of transmission line routes, it is necessary to consider the changes in the spatial characteristics of the target planning area under different time conditions to ensure that the laying of transmission lines meets the requirements of budget costs, topography, ecological environment, and dynamic changes in urban planning.

[0028] In this embodiment, the transmission line route planning method first needs to obtain multiple target planning times and multiple spatial parameters corresponding to the target planning location. The target planning location is the area where the transmission line needs to be erected; the target planning time is the optional time for the transmission line erection, for example, if the current time is 2020, the multiple target planning times could be 2022, 2024, 2026, etc.; the spatial parameters are the spatial characteristics of the target planning location, such as terrain data, environmental constraint data, environmental planning data, and power grid data. It is important to note that the multiple spatial parameters need to be unified based on the multiple target planning times to obtain integrated spatial parameters, avoiding the problem of multiple spatial parameters not corresponding in time. For example, if the target planning time is 2022, the multiple spatial parameters should correspond to the target planning time of 2022. Based on this, a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells is constructed. It is understood that the multiple spatial parameters are different for different target planning times. Therefore, it is necessary to obtain multiple multi-source spatiotemporal parameter databases corresponding to the target planning time based on the corresponding division. It is important to note that these databases include multiple raster cells representing the target planning location through gridding, facilitating subsequent processing. These raster cells in the multi-source spatiotemporal parameter database serve as the foundational data carriers for constructing environmental models and performing path searches. By discretizing and regularizing continuous and complex geographic space, they become the smallest basic units, enabling subsequent algorithms to find the optimal route scheme that balances economy, safety, and environmental protection within the geographic data.

[0029] In this embodiment, the cost of constructing transmission lines varies for different grid cells. Quantifying this cost requires considering various factors, such as terrain, ecological environment, and urban planning. Therefore, it is necessary to consider the weights of different factors in the overall cost to generate a spatiotemporal cost surface that meets practical needs. The weights can be set according to the actual needs of the target planning location. For example, if the target planning location emphasizes ecological environment protection, the weights related to the ecological environment can be increased. In this embodiment, a continuous penalty function is used to calculate the overall cost for each grid cell in the multi-source spatiotemporal parameter library at each target planning time. It can be understood that by using a continuous penalty function, the original constrained optimization problem can be transformed into an unconstrained optimization problem. That is, when the solution in the optimization process satisfies the constraints, the penalty term has a value of 0 and will not have an additional impact on the objective function; when the solution violates the constraints, the penalty term will generate a positive value, and this value will monotonically increase with the degree of constraint violation, thereby transforming the original rigid problem into a cost problem. For example, the original transmission line route planning might prohibit passage through terrain with a slope greater than 25°. However, by using a continuous penalty function, this rigidity problem of terrain slopes greater than 25° can be transformed into a cost problem. By setting a continuous penalty function, a fine balance can be achieved between feasibility and economy in the planning of transmission lines, thereby constructing a spatiotemporal cost surface corresponding to multiple target planning times.

[0030] In this embodiment, the spatiotemporal cost surface merely labels multiple grid cells in the multi-source spatiotemporal parameter library with cost under the target comprehensive cost weight; it does not perform precise path planning for these grid cells. Therefore, it is necessary to select the corresponding path based on the spatiotemporal cost surface. It is understandable that in multi-objective optimization, there is usually no single solution that is absolutely optimal across all objectives. Therefore, NSGA-II uses the Pareto optimality concept to find a set of non-dominated solutions—solutions that cannot further optimize a particular objective without worsening other objectives. The set of these solutions constitutes the Pareto front. Specifically, the NSGA-II algorithm first stratifies individual grid cells in the spatiotemporal cost surface according to their degree of domination, prioritizing the retention of non-dominated solutions. Within the same non-dominated level, it prioritizes retaining grid cells with sparser surrounding solutions, thereby maintaining the diversity of the spatiotemporal cost surface and preventing the algorithm from getting trapped in local optima. This ensures that the optimal solution of the previous generation can directly enter the next generation, guaranteeing the convergence of the algorithm. In this way, the control device can search the spatiotemporal cost surface at multiple target planning times to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times.

[0031] In this embodiment, the NSGA-II algorithm is used to search the spatiotemporal cost surfaces of multiple target planning times, generating a set of Pareto optimal paths for the target planning locations corresponding to multiple target planning times. However, an optimal planning path is still not generated. Therefore, the control device needs to further select the optimal planning path from the set of Pareto optimal paths. The optimal planning path is obtained through path migration analysis, cost sensitivity analysis, and robust path recommendation. Path migration analysis calculates the Hausdorff distance between the optimal paths at adjacent path solution planning times to quantify the spatial drift of the path over time. Cost sensitivity analysis overlays the three-dimensional Pareto fronts of each target planning time in the same coordinate system, analyzes the evolution direction of the Pareto front in the time dimension, and identifies key time-sensitive factors that constrain path optimization. Robust path recommendation selects the path scheme located in the "middle" of the Pareto front at each target planning time as the robust recommendation, meaning that this path has superior multi-objective comprehensive performance in the short, medium, and long term. The optimal planning path is obtained through this method. For example, in... Figure 6 The three pathways for target planning times of 2030, 2040, and 2050 demonstrate a trend of the optimal pathway gradually shifting southwestward as urban planning expands and ecological policies become more stringent. The recommended pathway for 2050 represents a migration distance of approximately 1.2 km from Hausdorf compared to 2030.

[0032] Understandably, the establishment of the multi-source spatiotemporal database in step S100 provides a time-dimensional basis for dynamic cost calculation in step S200; the dynamic constraint modeling in step S200, by introducing a continuous penalty function to replace the rigid constraint spatiotemporal cost surface, provides a flexible basis for step S300 to use the NSGA-II algorithm to search for the Pareto optimal path set; step S400 performs scenario extrapolation and comparison of the target planning time on the Pareto optimal path set in step S300, thereby obtaining the optimal planning path of the transmission line to the target planning location.

[0033] By employing a transmission line route planning method, the adaptability of automated transmission line route selection can be effectively improved. This method involves acquiring multiple target planning times and spatial parameters corresponding to the target planning location, and unifying the time base of these spatial parameters based on the multiple target planning times to construct a multi-source spatiotemporal parameter library containing multiple grid cells corresponding to multiple target planning times. A comprehensive cost calculation is performed on each grid cell in the multi-source spatiotemporal parameter library for each target planning time using a continuous penalty function to construct a spatiotemporal cost surface corresponding to the multiple target planning times. The NSGA-II algorithm is used to search the spatiotemporal cost surfaces for the multiple target planning times to generate Pareto optimal paths for the target planning locations. Based on the Pareto optimal paths for the target planning locations across multiple target planning times, path migration analysis, cost sensitivity analysis, and robust path recommendation are used to obtain the optimal planned path for the transmission line to the target planning location. This approach enables intelligent route selection for transmission lines in complex scenarios that comprehensively consider topography, ecological environment, dynamic changes in urban planning, and multi-dimensional cost trade-offs.

[0034] refer to Figure 2 In one embodiment of the present invention, the step of obtaining multiple target planning times and multiple spatial parameters corresponding to the target planning location, and unifying the time base of the multiple spatial parameters based on the multiple target planning times to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells specifically includes: Step S110: Obtain multiple target planning times corresponding to the target planning location; Step S120: Obtain terrain data, environmental constraint data, environmental planning data and power grid data corresponding to multiple target planning times in the target planning area, and convert the terrain data, environmental constraint data, environmental planning data and power grid data to a preset projection coordinate system after unifying the time base based on multiple target planning times, so as to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells; Among them, terrain data, environmental constraint data, environmental planning data and power grid data between multiple target planning times are obtained through spatiotemporal kriging interpolation and then converted to a preset projection coordinate system based on a unified time reference for multiple target planning times.

[0035] It is understandable that multiple target planning times represent the possible times for the construction of transmission lines. For example, if the current time is 2020, the multiple target planning times could be 2022, 2024, 2026, etc. By obtaining the multiple target planning times corresponding to the target planning locations, the feasible time for the construction of transmission lines can be determined, thereby meeting the actual planning requirements for transmission lines.

[0036] In this embodiment, terrain data may include digital elevation models, digital surface models, and slope and aspect derived data, all uniformly resampled to 10m×10m grids. Environmental constraint data may include ecological protection red line vector data, geological hazard risk time-series grids, etc. Environmental planning data may include urban master planning map patches, land spatial planning data, and transportation network planning alignments, etc. Power grid data may include the location and capacity of existing substations, coordinates of planned load centers, and predicted load values, etc. The preset projection coordinate system can be implemented using the CGCS2000 coordinate system. By unifying the time base of terrain data, environmental constraint data, environmental planning data, and power grid data and converting them to the preset projection coordinate system, a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid units is constructed. It is understood that the acquired terrain data, environmental constraint data, environmental planning data, and power grid data all need to correspond to multiple target planning times to ensure the accuracy of spatial parameters. First, the spatial parameters accurately corresponding to multiple target planning times are converted to the preset projection coordinate system. Secondly, for spatial parameters spanning multiple target planning times, spatiotemporal kriging interpolation is employed. These parameters are then transformed into a preset projected coordinate system based on a unified time reference across the target planning times, thereby constructing a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple raster cells. Specifically, for spatial parameters of discontinuous target planning times, spatiotemporal kriging interpolation is used to generate continuously varying surfaces for intermediate years, with interpolation errors controlled within RMSE < 8%. For urban planning data, land expansion trends are predicted based on cellular automata models.

[0037] Optionally, the terrain data includes digital elevation models, digital surface models, and slope and aspect derived data; the environmental constraint data includes ecological protection red line vector data and geological disaster risk time-series raster; the environmental planning data includes urban master planning map patches, territorial spatial planning data, and transportation network planning alignments; and the power grid data includes the location and capacity of existing substations, coordinates of planned load centers, and predicted load values.

[0038] In addition, for multiple spatial parameters, the confidence weights The cost is determined based on the accuracy, timeliness, and authority of the data collection source. In subsequent cost calculations, the cost for low-confidence data areas is multiplied by a penalty factor. The guidance path prioritizes areas with reliable data.

[0039] refer to Figure 5 In one embodiment of the present invention, the step of calculating the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library for each target planning time based on a continuous penalty function to construct a spatiotemporal cost surface corresponding to multiple target planning times specifically includes: Step S210: Based on the sum of the basic terrain cost function, environmental constraint cost function, and planning conflict cost function, determine the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library under each target planning time, so as to construct a spatiotemporal cost surface corresponding to multiple target planning times.

[0040] In this embodiment, a constraint modeling method employing continuous penalty functions and tolerance thresholds transforms discrete pass / fail decisions into continuous cost increment functions, enabling the optimization algorithm to achieve a fine trade-off between feasibility and economy. The continuous penalty functions include basic terrain cost functions, environmental constraint cost functions, and planning conflict cost functions. By calculating the sum of these functions, the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library for each target planning time is determined. It is important to note that this embodiment also introduces tolerance thresholds in the actual calculation of the comprehensive cost. For example, no additional cost is incurred when the slope is less than the first target slope; when the slope is greater than the first preset slope, the cost increases quadratically; when the slope is greater than the second preset slope, the cost increases rapidly but passability is still maintained. This allows for the generation of feasible solutions even in extreme terrain conditions, while simultaneously avoiding extreme areas through high-cost natural guidance paths. By calculating the sum of the basic terrain cost function, environmental constraint cost function, and planning conflict cost function, and introducing a tolerance threshold, the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library under each target planning time is accurately determined, thereby constructing a spatiotemporal cost surface corresponding to multiple target planning times.

[0041] Optionally, the overall cost is ; Wherein, the basic terrain cost function is The environmental constraint cost function is: The planning conflict cost function is: The For the slope, the For the degree of terrain roughness, the The normalization coefficient; For the first The time-varying weights of environmental constraints in year t The distance decay function is defined as the distance between the core area, buffer zone, and outer perimeter. as well as, ,and Each target planning time Monotonically increasing, For grid cells.

[0042] Understandably, the environmental constraint cost function employs a distance decay function between the core area, buffer zone, and outer area, thus providing room for fine-tuning optimization while adhering to the legal bottom line of ecological protection. Furthermore, the cost of each grid cell is not only a function of spatial coordinates but also a function of the target planning time. The time-varying weight function reflects the changing importance of various constraints across different eras. For example, as carbon neutrality policies advance, the ecological weight monotonically increases over time.

[0043] Optionally, the cost of the core area is set to a maximum value. The buffer is based on distance. exponential decay function Calculate the cost, the The attenuation constant is used; the cost of the outer area is set to 1.5 times the preset base cost.

[0044] In this embodiment, the cost of the core area is set to the maximum value, which is the area where construction is prohibited. The value is set to 500 meters. The preset base cost can be set according to actual needs. For example, the preset base cost can be a specific preset cost within the base terrain cost function.

[0045] refer to Figure 3 In one embodiment of the present invention, the step of searching the spatiotemporal cost surface of multiple target planning times based on the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to the multiple target planning times specifically includes: Step S310: Based on the comprehensive cost of each grid cell in the spatiotemporal cost surface of multiple target planning times, generate multiple planning paths whose planning path costs are within the target cost range; the planning path cost is the sum of the comprehensive costs of all grid cells from the start point to the end point; Step S320: Based on the generated multiple planned paths, minimize the overall path cost, minimize the total path length, and maximize the smoothness of path turns to obtain multiple optimized planned paths; Step S330: Based on the continuous penalty function, perform target filtering on multiple optimization planning paths to obtain multiple constrained planning paths; Step S340: Based on the NSGA-II algorithm, filter multiple constrained planning paths to generate Pareto optimal paths for target planning locations corresponding to multiple target planning times.

[0046] In this embodiment, the planned path is a sequence of ordered grid nodes. , Starting from, The endpoint is defined as follows: adjacent nodes are connected within an 8-neighborhood. First, multiple planned paths with costs within the target cost range are generated based on the comprehensive cost of each grid cell in the spatiotemporal cost surface. These planned paths are then ordered for subsequent filtering. The target cost range can be set according to the actual budget. Based on the multiple planned paths generated from the comprehensive cost, the comprehensive cost of the paths, the total path length, and the smoothness of path turns are minimized to obtain multiple optimized planned paths. The comprehensive cost of the paths is minimized as follows: The total path length is minimized to The path corner smoothness is maximized as follows: (Maximizing the negative value of the angle change). Based on obtaining multiple optimized planning paths, a continuous penalty function is used again to filter the multiple optimized planning paths to avoid the problem of rigid constraints in the previous processing method causing the inability to generate results. Finally, the NSGA-II algorithm is used to filter the multiple constrained planning paths to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times.

[0047] refer to Figure 4 Optionally, the step of filtering multiple constrained planning paths based on the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times specifically includes: Step S341: Based on the path topology, the cross operator and adaptive variable asynchronous length pair are used to cross multiple constrained planning paths at the common nodes of the two parent paths to obtain the Pareto optimal path set for the target planning location at multiple target planning times. Step S342: Based on the inflection point automatic screening mechanism, by calculating the marginal substitution rate change between adjacent path solutions in the Pareto optimal path set, Pareto optimal paths for target planning locations corresponding to multiple target planning times are generated.

[0048] In this embodiment, when dealing with problems with complex topological constraints such as path planning, the traditional NSGA-II algorithm is prone to disrupting the connectivity of solutions and generating a large number of invalid solutions due to random crossovers. By performing crossovers at common nodes, the engineering feasibility of offspring is fundamentally guaranteed, significantly reducing the generation rate of infeasible offspring from approximately 67% to below 12%. This reduces the computational resource waste on invalid solutions and effectively avoids the low search efficiency caused by over-reliance on penalty functions in traditional algorithms. Furthermore, by combining adaptive variable asynchronous length and employing an exponential decay function... In the early stages of the algorithm, a larger step size grants the population a strong global exploration capability, preventing it from getting trapped in local optima. As the number of generations increases, the step size gradually decreases, allowing the algorithm to focus on the neighborhood of high-quality solutions for refined local development in later stages. This dynamic adjustment mechanism effectively overcomes the "pseudo-convergence" or "premature convergence collapse" phenomena caused by fixed mutation parameters, ensuring that the search intensity of the algorithm remains optimal at different evolutionary stages. By using the path topology crossover operator and adaptive variable step size, multiple constrained planning paths are cross-processed at the common nodes of the two parent paths, thereby obtaining the Pareto optimal path set for the target planning locations at multiple target planning times. After obtaining the Pareto optimal path set, an inflection point automatic screening mechanism is used to calculate the curvature or marginal rate of substitution changes between adjacent path solutions in the Pareto optimal path set, accurately locating the optimal balance point among multiple objectives. It is understandable that near the inflection point, any small improvement in a single objective will lead to a sharp deterioration in other objectives, resulting in any further optimization of a single objective requiring a disproportionately large cost to other objectives. Therefore, by using the inflection point automatic screening mechanism, the adaptability of transmission line path planning can be effectively improved, thereby obtaining the Pareto optimal path for the target planning location corresponding to multiple target planning times, so as to facilitate the subsequent selection of the optimal planning path of the transmission line to the target planning location based on multiple target planning times.

[0049] In this embodiment, the path topology crossover operator ensures the feasibility of the solution at the operator level, the adaptive variable asynchronous length improves the search efficiency and convergence accuracy at the evolutionary strategy level, and the inflection point automatic screening mechanism provides the most engineering-valued recommended solution at the decision level, thereby generating the Pareto optimal path for the target planning location corresponding to multiple target planning times.

[0050] Among them, the For the initial variable asynchronous length, the For the current algebra, It is the largest algebra.

[0051] The present invention also proposes a control device comprising a memory, a processor, and a transmission line path planning program stored in the memory and executable on the processor, the transmission line path planning program being configured to implement the steps of the transmission line path planning method as described in any of the preceding claims.

[0052] It is worth noting that since the control device of the present invention is based on the above-mentioned transmission line path planning method, the embodiments of the control device of the present invention include all the technical solutions of all embodiments of the above-mentioned transmission line path planning method, and the technical effects achieved are exactly the same, so they will not be repeated here.

[0053] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for planning transmission line routes, characterized in that, The method includes: The target planning location is obtained by acquiring multiple target planning times and multiple spatial parameters, and the time base of multiple spatial parameters is unified based on multiple target planning times. The target planning location is also gridded to construct a multi-source spatiotemporal parameter library that corresponds to multiple target planning times and includes multiple grid cells. The comprehensive cost calculation of each grid cell in the multi-source spatiotemporal parameter library under each target planning time is based on the continuous penalty function to construct the spatiotemporal cost surface corresponding to multiple target planning times; The spatiotemporal cost surface of multiple target planning times is searched based on the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times. Based on the Pareto optimal path of the target planning location for multiple target planning times, the optimal planning path of the transmission line to the target planning location is obtained through path migration analysis, cost sensitivity analysis, and robust path recommendation.

2. The method for planning transmission line routes as described in claim 1, characterized in that, The steps of obtaining multiple target planning times and multiple spatial parameters corresponding to the target planning location, and unifying the time base of the multiple spatial parameters based on the multiple target planning times to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells specifically include: Obtain multiple target planning times corresponding to the target planning location; Acquire terrain data, environmental constraint data, environmental planning data, and power grid data corresponding to multiple target planning times in the target planning area, and transform the terrain data, environmental constraint data, environmental planning data, and power grid data to a preset projection coordinate system based on multiple target planning times to construct a multi-source spatiotemporal parameter library corresponding to multiple target planning times and including multiple grid cells; Among them, terrain data, environmental constraint data, environmental planning data and power grid data between multiple target planning times are obtained through spatiotemporal kriging interpolation and then converted to a preset projection coordinate system based on a unified time reference for multiple target planning times.

3. The method for planning transmission line routes as described in claim 2, characterized in that, The terrain data includes digital elevation models, digital surface models, and slope and aspect derived data; the environmental constraint data includes ecological protection red line vector data and geological disaster risk time-series raster; the environmental planning data includes urban master planning map patches, territorial spatial planning data, and transportation network planning alignments; the power grid data includes the location and capacity of existing substations, coordinates of planned load centers, and predicted load values.

4. The method for planning transmission line routes as described in claim 1, characterized in that, The specific steps for calculating the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library for each target planning time based on the continuous penalty function, in order to construct the spatiotemporal cost surface corresponding to multiple target planning times, are as follows: Based on the sum of the basic terrain cost function, environmental constraint cost function, and planning conflict cost function, the comprehensive cost of each grid cell in the multi-source spatiotemporal parameter library under each target planning time is determined, so as to construct a spatiotemporal cost surface corresponding to multiple target planning times.

5. The method for planning transmission line routes as described in claim 4, characterized in that, The comprehensive cost is ; Wherein, the basic terrain cost function is The environmental constraint cost function is: The planning conflict cost function is: The For the slope, the For the degree of terrain roughness, the The normalization coefficient; For the first The time-varying weights of environmental constraints in year t The distance decay function is defined as the distance between the core area, buffer zone, and outer perimeter. as well as, ,and Each target planning time Monotonically increasing, For grid cells.

6. The method for planning transmission line routes as described in claim 5, characterized in that, The cost of the core area is set to a maximum value. The buffer is based on distance. exponential decay function Calculate the cost, the The attenuation constant is used; the cost of the outer area is set to 1.5 times the preset base cost.

7. The method for planning transmission line routes as described in claim 1, characterized in that, The specific steps for searching the spatiotemporal cost surface for multiple target planning times using the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times are as follows: Based on the comprehensive cost of each grid cell in the spatiotemporal cost surface with multiple target planning times, multiple planning paths with planning path costs within the target cost range are generated; the planning path is a set of ordered grid node sequences. , Starting from, The endpoint is defined as the grid cell with adjacent nodes connected within 8 neighborhoods; the planned path cost is the sum of the total costs of all grid cells from the starting point to the endpoint. Based on the generated multiple planning paths, the overall path cost, total path length, and corner smoothness are minimized to obtain multiple optimized planning paths. Multiple constraint planning paths are obtained by selecting objectives from multiple optimization planning paths based on a continuous penalty function; The NSGA-II algorithm is used to filter multiple constrained planning paths to generate Pareto optimal paths for target planning locations corresponding to multiple target planning times.

8. The method for planning transmission line routes as described in claim 7, characterized in that, The specific steps for filtering multiple constrained planning paths based on the NSGA-II algorithm to generate the Pareto optimal path for the target planning location corresponding to multiple target planning times are as follows: Based on path topology, the crossover operator and adaptive variable asynchronous length pair are used to cross multiple constrained planning paths at the common nodes of the two parent paths to obtain the Pareto optimal path set for the target planning location at multiple target planning times. Based on the inflection point automatic screening mechanism, Pareto optimal paths for target planning locations corresponding to multiple target planning times are generated by calculating the marginal substitution rate change between adjacent path solutions in the Pareto optimal path set.

9. The method for planning transmission line routes as described in claim 8, characterized in that, The adaptive variable asynchronous length includes an exponential decay function. ; Among them, the For the initial variable asynchronous length, the For the current algebra, It is the largest algebra.

10. A control device, characterized in that, The control device includes a memory, a processor, and a transmission line path planning program stored in the memory and executable on the processor, the transmission line path planning program being configured to implement the steps of the transmission line path planning method as described in any one of claims 1 to 9.

Images