Intelligent optimization design method and device for internal road of wind power plant, medium and product
Through the intelligent optimization design method combining A* and whale school algorithm, the problem of difficulty in designing wind farm roads in complex terrain and mountainous areas is solved, and the scientific and reasonable layout of wind farm roads is realized, which reduces construction costs and improves operational efficiency. .
Patent Information
- Application Number
- CN202411183343.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-03
Smart Images

Figure CN119066971A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of wind farm road design, and in particular to an intelligent optimization design method, equipment, medium and product for internal roads of a wind farm. Background Art
[0002] As the global demand for renewable energy continues to grow, wind power has gained widespread attention as a clean and sustainable form of energy.
[0003] In the development and utilization of wind power, the road line selection inside the wind farm is a very important link, especially in mountainous areas with complex terrain.
[0004] Wind farms in this type of area have large terrain variations and the distribution of wind energy within the wind farm is affected by many factors, which increases the difficulty of designing wind farm roads in mountainous areas with complex terrain. Summary of the invention
[0005] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a method, equipment, medium and product for intelligent optimization design of internal roads in a wind farm, which integrates the A* algorithm and the whale swarm algorithm, which not only reduces the difficulty of designing wind farm roads in mountainous areas with complex terrain, but also improves the scientificity and systematicness of wind farm road design, and is particularly suitable for applications under complex terrain conditions, effectively reducing road construction costs, and improving the feasibility of construction and the operation and maintenance efficiency of wind farms.
[0006] To achieve the above objectives, the present invention provides a method for intelligent optimization design of internal roads in a wind farm, comprising: The invention relates to a method for preparing a wind farm using digital elevation model (DEM) data, and constructing a plurality of slope grids on a map of the wind farm; configuring a corresponding slope cost for the slope grid according to the slope of the slope grid; constructing a wind farm facility road line selection model based on an improved A* algorithm and the slope cost; inputting the location information of each wind farm facility in the wind farm into the wind farm facility road line selection model to obtain a path optimization result between wind farm facilities; determining an initial whale group of a whale group algorithm according to the path optimization result, wherein each individual whale in the initial whale group represents a potential road layout plan; obtaining the edit distance between the individual whales and the fitness of each individual whale; judging whether there is a target whale with better fitness and the shortest edit distance around the individual whale according to the edit distance and the fitness; if not, performing a field search on the individual whale to obtain a field whale; determining an optimized whale based on the fitness of the field whale and the individual whale; and determining an internal road optimization plan of the wind farm according to the optimized whale.
[0007] The method of the present invention can comprehensively consider multiple factors such as terrain, slope, construction cost, etc., to achieve a scientific, reasonable and economical layout of the internal roads of the wind farm. This embodiment uses DEM data to construct a slope grid, and configures a corresponding slope cost for each grid, and then uses an improved A* algorithm to perform intelligent line selection for paths between wind turbines, ensuring the efficiency and economy of path planning. After that, the overall road layout is globally optimized through an improved whale swarm algorithm. This embodiment cleverly combines the A* algorithm and the whale swarm algorithm, which not only improves the scientificity and systematicity of the wind farm road design, but is also particularly suitable for applications under complex terrain conditions, effectively reducing road construction costs, and improving the feasibility of construction and the operation and maintenance efficiency of the wind farm. This embodiment can maximize the economic benefits and environmental adaptability of the wind farm while ensuring the rationality of road connections.
[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining whether there is a target whale with better fitness and the closest edit distance around the individual whale based on the edit distance and the fitness, the method further includes: if the target whale exists, determining the position of the next generation whale based on the individual whale and the target whale; after moving the individual whale to the position of the next generation whale, performing a field search to obtain a field whale.
[0009] By adopting the technical solution of the above embodiment, the search capability of the algorithm and the diversity of solutions are enhanced by exchanging positions and searching areas between individual whales and target whales, which helps to find better road layout solutions and improve the optimization effect of internal road design in wind farms.
[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the position of the next generation of whales based on the individual whale and the target whale includes: initializing a path list and setting a loop termination condition; randomly selecting one or more elements from the individual whale or the target whale as target elements for multiple times, and adding the target elements to the path list; stopping selecting elements when the loop termination condition is met to obtain an adjusted path list; and determining the position of the next generation of whales based on the adjusted path list.
[0011] By adopting the technical solution of the above embodiment, the present invention optimizes the path selection process of individual whales by initializing the path list and setting the loop termination condition, so that the determination of the position of the next generation of whales is more scientific and systematic, thereby improving the efficiency of the algorithm and the quality of the solution.
[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of performing a domain search on the whale individual to obtain a domain whale includes: splitting each of the whale individuals into a multidimensional list; determining a first sublist and a second sublist from the multidimensional list, the first sublist containing a selected random element, and the second sublist not containing the random element; adjusting the first sublist and the second sublist according to index values of the first sublist and the second sublist, and the position of the random element in the first sublist to obtain an adjusted multidimensional list; and determining the domain whale based on the adjusted multidimensional list.
[0013] By adopting the technical solution of the above embodiment, the present invention increases the local changes of the solution by splitting the whale individuals into multidimensional lists and adjusting them, making the generation of domain whales more flexible and helping the algorithm to find a more reasonable road layout in a complex wind farm environment.
[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining a better element from the first sublist or the second sublist according to the index values of the first sublist and the second sublist, and the position of the random element in the first sublist includes: If the random element is at the first position in the first sublist, the first index value of the first sublist is less than the second index value of the second sublist, and the last element in the sublist with an index value between the first index value and the second index value is not the random element, then select an element from the second sublist that is not the last element as a better element, and replace the better element in the first sublist, and replace the random element in the second sublist; If the random element is between the first and last element in the first sublist, and the last element in the sublist with an index value between the first index value and the second index value is not the random element, then delete the random element from the first sublist and insert the random element into the second sublist; If the random element is at the last position in the first sublist, the first sublist and the second sublist are replaced with each other.
[0015] By adopting the technical solution of the above embodiment and concretizing the element selection and replacement rules, the present invention refines the adjustment method of the multidimensional list, ensures the continuity and effectiveness of the solution, and further improves the adaptability and accuracy of the whale group algorithm in solving the wind farm road optimization problem.
[0016] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the initial whale group of the whale group algorithm based on the path optimization result includes: adding multiple distance values between each wind power facility in the path optimization result to obtain a total spacing value; determining multiple probability values based on the multiple distance values and the total spacing value; generating a probability value sequence based on the multiple probability values; comparing each element in the probability value sequence with a randomly generated numerical value to determine the initial wind power facility; connecting the initial wind power facilities to form an initial whale; and forming a plurality of the initial whales into an initial whale group.
[0017] By adopting the technical solution of the above embodiment, by converting the path optimization result into a probability value sequence, the method of generating the initial whale group is innovated, so that the initial solution is closer to the actual road layout, and the initial search capability of the algorithm and the reliability of the final optimization result are enhanced.
[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the slope calculation formula of the slope grid includes: Among them, Slope is the slope of the slope grid; Slope we Slope is the horizontal slope. sn is the vertical slope; e is the center point of the slope grid; e i (i=1,2,…,7,8) is the elevation value of the center point of the grid around the center point e; Cellsize is the grid size.
[0019] By adopting the technical solution of the above embodiment and clarifying the calculation formula of the slope grid, the present invention provides an accurate terrain analysis tool for the wind farm road line selection model, making road planning more scientific and reasonable, and effectively reducing the construction difficulty and cost caused by terrain factors.
[0020] In a second aspect, an embodiment of the present invention provides an electronic device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method described in the first aspect and any possible implementation method of the first aspect.
[0021] In a third aspect, the present invention provides a computer-readable storage medium comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the method described in the first aspect and any possible implementation of the first aspect.
[0022] In a fourth aspect, the present invention provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the method described in the first aspect and any possible implementation of the first aspect.
[0023] It is understandable that the electronic device provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in the present invention. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.
[0024] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: 1. The present invention realizes the intelligent optimization design of internal roads of wind farms by combining DEM data analysis and improved A* algorithm. This method not only improves the economy and practicality of road selection, but also ensures the feasibility and safety of road construction by accurately considering the terrain slope, significantly improving the construction and operation efficiency of wind farms.
[0025] 2. Through the application of the whale group algorithm, the present invention enhances the global optimization capability of the wind farm road design. The edit distance and fitness evaluation mechanism in the algorithm enable the algorithm to identify and select a better road layout solution. At the same time, the domain search strategy further refines the solution and ensures the optimization of the road network design, thereby reducing the overall construction cost and improving the operational efficiency of the wind farm.
[0026] 3. The probability value sequence generation and initial whale group construction method in the present invention provide an innovative initialization strategy for wind farm road design. This method generates an initial solution that better meets actual needs based on the actual road optimization results, thereby providing a more reasonable starting point for the global search of the algorithm, accelerating the optimization process and improving the quality of the final solution. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 It is an intelligent optimization design method for internal roads of a wind farm according to an embodiment of the present invention; Figure 2 is a schematic diagram of the distribution of grid points in an embodiment of the present invention; Figure 3is a flow chart of a whale movement rule in an embodiment of the present invention; Figure 4 is a flow chart of a whale neighborhood search in an embodiment of the present invention; Figure 5 It is a schematic diagram of the architecture of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION
[0028] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to be limiting of the present invention. As used in the specification of the present invention, the singular expressions "a", "a", "above", "the" and "this" are intended to also include plural expressions, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations comprising one or more of the listed items.
[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.
[0030] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, the terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.
[0031] In the development and utilization of wind power, the selection of roads within wind farms is a very important link, especially in mountainous areas with complex terrain. Wind farms in such areas have large terrain changes and many factors that affect the distribution of wind energy within the wind farms, which increases the difficulty of designing wind farm roads in mountainous areas with complex terrain.
[0032] In view of this, an embodiment of the present invention provides an intelligent optimization design method for internal roads in a wind farm, which can comprehensively consider multiple factors such as terrain, slope, construction cost, etc., and realize the scientific, reasonable and economical layout of internal roads in the wind farm. This embodiment uses DEM data to construct a slope grid, and configures a corresponding slope cost for each grid, and then uses an improved A* algorithm to perform intelligent line selection for paths between wind turbines, ensuring the efficiency and economy of path planning. After that, the overall road layout is globally optimized through an improved whale swarm algorithm. This embodiment cleverly combines the A* algorithm and the whale swarm algorithm, which not only improves the scientificity and systematicness of the wind farm road design, but is also particularly suitable for applications under complex terrain conditions, effectively reducing the cost of road construction, and improving the feasibility of construction and the operation and maintenance efficiency of the wind farm. This embodiment can maximize the economic benefits and environmental adaptability of the wind farm while ensuring the rationality of road connections.
[0033] Based on the above technical effects, Figure 1 The following is an introduction to the intelligent optimization design method for internal roads in a wind farm according to this embodiment, which specifically includes the following steps: Step 101 : constructing a plurality of slope grids on a map of the wind farm based on DEM data of the wind farm.
[0034] Specifically, the DEM data is first parsed. The DEM data provides elevation information for each point in the wind farm area. This information exists in the form of a grid, and each grid point contains an elevation value. Next, a slope grid is constructed at the corresponding position on the wind farm map based on the elevation value in the DEM data. This process involves comparing the elevation values of the neighboring points around each grid point to calculate the slope of each grid point. The slope calculation usually uses the differential method, that is, it is determined by using the elevation difference between the grid point and its surrounding points. For example, the slope can be estimated by comparing the elevation difference between the center point and the adjacent points, and then the slope can be obtained.
[0035] Subsequently, the calculated slope values are assigned to the corresponding grid points to form a continuously changing slope surface map. This slope surface map can reflect the degree of inclination of different areas within the wind farm, providing detailed information on the terrain undulations for the subsequent road selection model. The slope grid constructed in this way not only takes into account the microscopic changes in the terrain, but also provides an important decision-making basis for the design of roads within the wind farm, ensuring the scientificity and rationality of road planning. Ultimately, these slope grids will be combined with the road selection algorithm to automatically generate a wind farm internal road layout plan that meets the terrain requirements and is economical and efficient.
[0036] In some embodiments, the slope calculation formula of the slope grid includes the following: (1) (2) (3) Among them, Slope is the slope of the slope grid; Slope we Slope is the horizontal slope. sn is the vertical slope; the distribution positions of e1 to e8 are as follows Figure 2 As shown, e is the center point of the slope grid; e i (i=1,2,…,7,8) is the elevation value of the center point of the grid around the center point e; Cellsize is the grid size.
[0037] In this embodiment, formula (1) defines the calculation method of the grid comprehensive slope, which is estimated by considering the difference in elevation values in the eight directions around the center point; formula (2) specifically calculates the slope in the horizontal direction, focusing on the change in elevation values in the east-west direction; formula (3) calculates the slope in the vertical direction, that is, evaluating the elevation difference in the north-south direction. These formulas provide key terrain information for the wind farm road selection model by quantifying the inclination of the terrain, ensuring that the selected path can adapt to terrain changes while minimizing construction costs and construction difficulties.
[0038] Step 102: configuring a corresponding slope cost for the slope grid according to the slope of the slope grid.
[0039] Specifically, it first involves analyzing the slope value of each cell in the slope grid. The slope value reflects the degree of inclination of the terrain and directly affects the difficulty and cost of road construction. When configuring the slope cost, a cost function is usually set, which takes the slope value as input and outputs the corresponding cost value based on the economic and technical feasibility of road construction.
[0040] The design of the cost function needs to consider multiple factors. For example, a large slope may increase the difficulty of transporting construction materials and increase construction costs. It may also affect later maintenance and operational safety. Therefore, the cost function usually assigns higher costs to larger slope values. Specifically, the impact of slope on cost can be quantified by setting a nonlinear cost model, such as exponential growth or polynomial form. For example, a cost factor that increases with the increase in slope can be used. This factor can be a linear, quadratic, or higher-order polynomial to reflect the nonlinear impact of different slope values on construction costs.
[0041] In actual operation, a cost value is assigned to each slope grid unit according to the slope value and the preset cost function, and these cost values will be used in the subsequent road selection algorithm. In this way, when searching for the optimal path, the algorithm will tend to choose those paths with lower slope costs, thereby maximizing cost-effectiveness while meeting technical requirements. Ultimately, this slope cost-based optimization method can ensure that the internal road design of the wind farm is both scientific and reasonable, and economical and efficient, laying a solid foundation for the smooth construction and long-term operation of the wind farm.
[0042] Step 103: construct a wind power facility road line selection model based on the improved A* algorithm and the slope cost.
[0043] Specifically, firstly, the wind farm terrain is analyzed using DEM data to generate slope grids, and the corresponding slope cost is calculated based on the slope of each grid. These slope costs reflect the difficulty and cost of road construction under different terrain conditions, providing an important decision-making basis for road line selection.
[0044] These slope costs are then integrated into the improved A* algorithm as part of the heuristic function to evaluate the potential path costs from the starting point to the target point. The A* algorithm is an effective path search algorithm that estimates the total cost F = G + H by evaluating the actual path cost G and the estimated cost H to the target point.
[0045] In addition, the improved A* algorithm may also include adaptive adjustments to terrain characteristics, such as adding additional cost factors in areas with larger slopes, or reducing costs in areas with flat terrain to optimize path selection. In this way, the algorithm can quickly and efficiently search for the best path from one facility to another in a wind farm while taking into account the impact of terrain.
[0046] Finally, by applying the improved A* algorithm to the wind farm map and combining the slope cost of each grid point, this embodiment constructs an intelligent road line selection model. This model not only improves the accuracy and efficiency of path planning, but is also particularly suitable for wind farms under complex terrain conditions, providing a scientific, reasonable and cost-effective solution for the layout of roads between wind power facilities.
[0047] In this embodiment, the estimated cost H in the A* algorithm uses Manhattan distance as a heuristic function and combines the slope cost, so that the algorithm can more intelligently avoid high-cost areas.
[0048] Among them, the calculation of Manhattan distance is simple and fast, which can significantly improve the execution speed of the A* algorithm, allowing the algorithm to quickly evaluate potential paths and accelerate convergence to the optimal solution. Secondly, the linear characteristics of Manhattan distance make the heuristic function more stable, reduce random fluctuations in the search process, and improve the reliability of the algorithm. In addition, Manhattan distance can provide more accurate distance estimates in regular terrain, which helps the algorithm avoid falling into local optimality and more effectively guide the search process to the global optimal solution.
[0049] In the design of wind farm roads, the A* algorithm using Manhattan distance as the heuristic function can better adapt to the regularity of the terrain, and at the same time, combined with the slope cost, intelligently avoid high-slope areas, reducing road construction costs and construction difficulties. This method not only improves the scientificity and systematicity of path planning, but is also particularly suitable for the automated and intelligent road design of large-scale wind farms, providing strong technical support for the construction and operation of wind farms.
[0050] Step 104: input the location information of each wind power facility in the wind farm into the wind power facility road line selection model to obtain the path optimization result between the wind power facilities.
[0051] Among them, wind power facilities include but are not limited to wind turbines, substations and other wind power generation related facilities.
[0052] Specifically, the coordinates of each wind power facility in the wind farm are first accurately obtained through the Geographic Information System (GIS) or other related technical means. These coordinates are then imported as location information into the road selection model based on the improved A* algorithm, which has integrated the slope cost obtained from the DEM data analysis.
[0053] The model uses this input location information, combined with the terrain slope and the preset slope cost, to calculate the optimal connection path between wind power facilities through an algorithm. During the calculation process, the A* algorithm evaluates the actual cost G and estimated cost H of each potential path, and combines the Manhattan distance as a heuristic function to estimate the total cost F = G + H from the starting point to the target point. In this way, the algorithm can intelligently avoid high-slope and high-cost areas and select the most cost-effective path.
[0054] Ultimately, the path optimization results output by the model will show the best way to connect wind farms. These paths not only take into account the slope of the terrain and the feasibility of construction, but also take into account economy and efficiency. This method provides a scientific, systematic and automated solution for wind farm road planning, ensuring the optimization of road layout between wind farms, thereby improving the construction and operation efficiency of the entire wind farm.
[0055] In some embodiments, the specific process of the A* algorithm is as follows: Step 1.1, put the starting point into close_set (closed list). If the neighboring point of the starting point is neither in the open list nor in the closed list, calculate the cost function F=G+H of the neighboring point, add it to open_set (open list), and record its parent node.
[0056] This step means that the starting point has been selected as part of the path and no longer needs to be re-evaluated. Next, the algorithm will consider the neighboring points near the starting point. The starting point is a wind turbine in the wind farm.
[0057] Step 1.2, determine whether open_set is empty.
[0058] If it is empty, it means that all possible path points have been found before reaching the end point, the path finding fails, and the algorithm ends; if it is not empty, continue with Step 1.3.
[0059] Step 1.3, visit the node with the lowest cost in open_set and move it from open_set to close_set.
[0060] This step is to select the current best candidate node for expansion. Minimum cost usually means that the sum of the actual path cost G from the node to the starting point plus the estimated cost H to the target point is the smallest among all candidate nodes.
[0061] Step 1.4: Determine whether this point is the end point.
[0062] If the point is the end point, then the pathfinding is successful and the path from the start point to the end point is found. If it is not the end point, the algorithm will continue to evaluate the neighboring points of the newly added close_set node, repeating the process from Step 1.1 to Step 1.4 until the end point is found or the open_set is empty.
[0063] The above process is an iterative step in the A* algorithm to gradually explore and evaluate the path, searching from the starting point to the target point. Each step aims to select the current optimal path and gradually approach the target point until the target point is found or it is determined that the target point cannot be reached.
[0064] Step 105: determine the initial whale group of the whale group algorithm according to the path optimization result.
[0065] Among them, the Whale Swarm Algorithm with Iterative Counter (WSA-IC) is designed to solve multimodal optimization problems. The algorithm improves search efficiency and the ability to locate the global optimal solution by introducing an iterative counting mechanism and new parameters. Each individual whale in the initial whale group represents a potential road layout solution.
[0066] In this embodiment, each individual whale in the initial whale group is generated based on the optimization results obtained in the previous steps, and they represent potential road layout plans within the wind farm. These plans take into account factors such as wind turbine location, terrain slope, road connectivity and construction cost.
[0067] Specifically, the generation process of the initial whale group is as follows: First, the optimized path between wind power facilities calculated by the A* algorithm is used as the initial position of the individual whales to ensure that each individual whale has a cost-effective road layout at the beginning. Then, according to the specific conditions of the wind farm, such as the number, distribution, and terrain characteristics of wind power facilities, a sufficient number of individual whales are generated to ensure the diversity of the initial solution. These individual whales may have subtle differences in the initial stage, such as path selection, road layout, etc. These differences provide rich exploration space for subsequent group intelligence optimization.
[0068] Next, in the iterative process of the whale group algorithm, each individual whale will update its position according to its own fitness and group information, and continuously explore better road layout solutions by simulating the social behaviors of whale groups, such as following, crossing and mutation. In this process, the whale group algorithm takes advantage of group intelligence and gradually guides the entire group to evolve towards a better solution through information exchange and collaboration between individuals.
[0069] Finally, through the optimization of the whale group algorithm, the individuals in the initial whale group will continue to improve, forming a series of optimized road layout schemes. These schemes not only have advantages in local paths, but also achieve cost minimization and efficiency maximization in global layout, providing an innovative solution for the road design of wind farms. Through this method, the present invention achieves a leap from local optimization to global optimization, greatly improving the scientificity and practicality of wind farm road design.
[0070] In some embodiments, step 105 specifically includes the following: Step 2.1, add up the multiple distance values between the wind power facilities in the path optimization result to obtain the total distance value.
[0071] For example, the distance between fans and the distance between fans and booster stations. Add up all these distances.
[0072] Step 2.2, determine multiple probability values according to multiple distance values and the total value of the interval.
[0073] Specifically, for each distance value, the probability value formula is used to calculate its proportion of the total distance value to obtain a series of probability values. The probability value formula is as follows: Among them, p[i] is the i-th probability value, s[i] is the i-th distance value, s t is the total value of the spacing.
[0074] Step 2.3, generate a probability value sequence based on the multiple probability values.
[0075] Specifically, the above probability values are used to perform cumulative summation to obtain a cumulative probability sequence, and this cumulative probability sequence is used as a probability value sequence. The elements in this probability value sequence are always between 0 and 1.
[0076] Step 2.4, compare each element in the probability value sequence with the randomly generated value to determine the initial wind power facility.
[0077] Specifically, a number a is randomly generated, and the range of a is between 0 and 1; each element in the cumulative probability sequence is checked, and if the randomly generated number a is less than or equal to the value of the current element, the selection is stopped.
[0078] After finding the cumulative probability that meets the conditions, the corresponding original value is regarded as the selected initial wind power facility.
[0079] Then use the formula Select subsequent wind power facilities. Where L[i] represents the last selected element in the i-th whale, L represents the set of all wind power facilities, max represents the maximum value, and p[i] represents the probability of the i-th whale being selected.
[0080] Through probability and random selection, it is ensured that each whale can choose a wind turbine that has not been selected by other whales, thus avoiding repeated selection, ensuring the diversity of the whale group, and helping to improve the algorithm's optimization ability.
[0081] Through Step 2.1-Step 2.5, the whale can be initialized.
[0082] Step 2.5, connect the initial wind power facilities to form the initial whale.
[0083] Connecting these initial wind farms through preset connection rules or paths actually builds an initial solution for road connections in the algorithm, called the "initial whale". This process involves determining the connection sequence between wind turbines, the layout of roads, and the connection points with key facilities to form an initial model representing the internal road network of the wind farm. The construction of the initial whale is based on the existing wind turbine location information and preliminary considerations of road design, providing a starting point for subsequent optimization algorithms.
[0084] Step 2.6, organize multiple initial whales into an initial whale group.
[0085] Once there are several initial whales, each representing a potential wind farm road layout solution, the next step is to "form" these initial whales into a group, namely the initial whale group. This group is formed in order to apply the whale group algorithm for optimization. Among them, group diversity is the key to searching for the global optimal solution, so each individual in the initial whale group should have unique road layout characteristics. By setting the algorithm initialization parameters, such as group size, location distribution, etc., it is ensured that the individuals in the initial whale group are both diverse and can cover the possible solution space of the wind farm road layout. The construction of the initial whale group provides a basis for the iterative optimization of the algorithm, enabling the algorithm to explore better road layout solutions by simulating the social behavior of whales in subsequent steps.
[0086] Step 106, obtaining the edit distance between the individual whales and the fitness of each individual whale.
[0087] Among them, the edit distance refers to the degree of difference between two strings (representing different road layout plans in this embodiment), and the fitness is an indicator for evaluating the quality of individual whales (i.e., road layout plans).
[0088] First, encode the solution of each whale individual into a string form. For example, the road layout solution can be converted into a character sequence through a specific encoding rule. Then, use the edit distance algorithm, such as the Levenshtein distance, to calculate the string difference between any two whale individuals. This difference reflects the similarity or variation of their solutions. Whale individuals with a smaller edit distance mean that their road layout solutions are more similar, while a larger distance means that they have more different features.
[0089] In some embodiments, the specific algorithm for calculating the edit distance between individual whales is as follows: Let editDist(i,j) represent the edit distance required to convert a substring of length i of the first string to a substring of length j of the second string. The formula is as follows: When i=0 and j=0, editDist(i,j)=0; When i=0 and j>0, editDist(i,j)=j; When i=0 and j>0, editDist(i,j)=i; When i≥1 and j≥1, Among them, when the i-th character of the first string is not equal to the j-th character of the second string, cost(i,j)=1, otherwise, cost(i,j)=0.
[0090] In this step, a fitness function is also defined for each individual whale, which calculates the fitness value based on multiple evaluation indicators of the road layout solution, which may include the total length of the road, construction cost, maintenance difficulty, connection efficiency with wind turbines, etc. The fitness function is designed to quantify the pros and cons of the solution to guide the optimization direction of the algorithm.
[0091] In each iteration of the whale group algorithm, by calculating the edit distance between individual whales and evaluating their fitness, the algorithm can identify the better solutions in the group and guide the group to evolve in the direction of these excellent solutions. The edit distance helps the algorithm maintain the diversity of the group and avoid premature convergence, while the fitness evaluation ensures that the optimization process always moves in the direction of improving the quality of the solution.
[0092] In this way, the whale swarm algorithm can effectively search and explore in the neighborhood of candidate solutions while maintaining the diversity and optimization direction of the solution, and finally achieve the global optimization of the wind farm road layout. This process not only improves the efficiency and economy of wind farm road design, but also enhances the algorithm's adaptability to complex terrain and engineering conditions.
[0093] Step 107: According to the edit distance and the fitness, it is determined whether there is a target whale with better fitness and the shortest edit distance around the individual whale.
[0094] Specifically, the edit distance between the current whale individual and all other individuals in the group is first calculated to determine the similarity or difference between them. Then, the fitness of these neighboring individuals is evaluated to determine the quality of their solutions.
[0095] Next, we look for whales with higher fitness (i.e., better solutions) and closer edit distances (i.e., solutions similar to the current whale but with improvements). If such whales exist, they may provide potential ways to improve the current solution. In this way, the algorithm is able to guide the search process towards higher quality solutions while maintaining the diversity of the population.
[0096] The key to this process is to balance the relationship between exploration (finding new solutions) and utilization (improving existing solutions). By considering the edit distance, the algorithm avoids premature convergence to the local optimal solution, while ensuring the correctness of the search direction through fitness evaluation. This strategy enables the whale group algorithm to effectively search in the solution space, gradually approaching the global optimal solution or at least obtaining a high-quality approximate solution.
[0097] If the target whale exists, the position of the next generation whale is determined based on the individual whale and the target whale; after the individual whale is moved to the position of the next generation whale, a field search is performed to obtain the field whale.
[0098] Specifically, the location information of the current individual whale and the location information of the target whale are used first to determine the location of the next generation of whales through predefined movement rules. This process involves evaluating the fitness of the two individual whales and the relationship between them, as well as possible random factors, to simulate the social behavior and migration patterns of whale groups in nature. In this way, the algorithm hopes to produce a new offspring that inherits the advantages of both, thereby driving the evolution of the entire group towards a better solution.
[0099] Once the whale individuals move to a new location according to the above method and form the so-called next generation of whales, the algorithm will then perform a field search in the neighborhood of the new location. The purpose of the field search is to find possible better or equivalent solutions in the local area of the new location. This process may include small changes or mutations to the new location to explore the neighboring solution space and evaluate the impact of these changes on fitness. If a whale individual with better fitness is found in the field search, the individual will be identified as a field whale and may become a new target whale in subsequent iterations. In this way, the algorithm is able to not only perform global exploration in the entire search space, but also make fine adjustments and optimizations in local areas, thereby gradually improving the quality of the solution.
[0100] In some embodiments, the location of the next generation of whales can be determined based on the individual whale and the target whale according to the preset whale movement rules. The specific steps are as follows: (1) Initialize the path list and set the loop termination condition.
[0101] In the whale group algorithm, initializing the path list is to create an empty container for the process of gradually building and optimizing the solution. At the same time, setting the loop termination condition is to control the number of iterations of the algorithm or to achieve a specific goal. These conditions may be based on the improvement of fitness, the limit of the number of iterations, the constraint of computing resources, or the set goal. In this embodiment, the loop termination condition is: among all whales, the last element of the route is selected as a booster station.
[0102] (2) Randomly select one or more elements from the whale individual or the target whale as target elements multiple times, and add the target elements to the path list.
[0103] By randomly selecting elements from the solutions of individual whales or target whales, the algorithm simulates random exploration during the search process. The selected elements, representing key points or road connections in the wind farm, are added to the path list, gradually forming a candidate road layout solution.
[0104] (3) When the loop termination condition is met, stop selecting elements and obtain the adjusted path list.
[0105] As the algorithm progresses, when the preset termination condition is met, the algorithm stops selecting new elements from the whale individual. At this point, the elements that have been added to the path list constitute an adjusted candidate solution.
[0106] (4) Determine the location of the next generation of whales based on the adjusted path list.
[0107] Using the adjusted path list, the algorithm evaluates and determines the next generation of whale positions, which represents an updated solution for the road layout within the wind farm. This process involves evaluating and selecting the current candidate solutions, as well as making decisions based on fitness and algorithmic rules to ensure that the newly generated whale positions reflect the optimized solution characteristics.
[0108] In some embodiments, suppose whale X moves toward whale Y, such as Figure 3 As shown, the moving rules are as follows: Step 3.1. Generate an empty list X'.
[0109] Step 3.2, set the termination condition: the selected element is the booster station.
[0110] Step 3.3, generate a random number R; 0 <R<1。
[0111] Step 3.4, set λ; the value is 0.5.
[0112] Step 3.5, determine whether R is less than λ. If yes, proceed to Step 3.6; if no, proceed to Step 3.7.
[0113] Step 3.6. Select element X0 from whale X for the first time.
[0114] Step 3.7. Select element Y0 from whale Y for the first time.
[0115] Step 3.8, determine whether X0 or Y0 is a booster station. If yes, go to Step 3.9; if not, go back to Step 3.3.
[0116] Step 3.9. Add the booster station element to the list X'.
[0117] Step 3.10. Add the separator X' and the first route is selected.
[0118] Among them, the significance of the separator is to identify and distinguish the different sections or nodes selected by individual whales during their movement. Specifically, the separator is used to clearly distinguish the key nodes in the generated road layout plan, such as wind turbine locations or booster stations, to ensure that the connection relationship from one node to another can be clearly expressed during the path construction process. When the algorithm selects elements between whale X and whale Y and builds a path, the addition of the separator marks the end of one section and the beginning of another, thereby helping the algorithm maintain and track the structure of the entire road network. This approach not only helps to keep the solution clear and organized during the execution of the algorithm, but is also crucial for the reconstruction and verification of the final output path.
[0119] Step 3.11. Set the termination condition and whale X continues to move.
[0120] Step 3.12: Determine whether R is less than λ. If yes, proceed to Step 3.13; if no, proceed to Step 3.14.
[0121] Step 3.13. Select element X from whale X i ; i=1,2,…,n.
[0122] Step 3.14. Select element Y from whale Y i ; i=1,2,…,n.
[0123] Step 3.15, determine X i or Y i Is it a booster station, or does it already exist in X'? If yes, go to Step 3.16, if not, return to Step 3.12.
[0124] Step 3.16. Add the delimiter to X' to terminate the loop.
[0125] Step 3.17, eliminate the paths in X' that do not meet the conditions and sort out the unselected fans.
[0126] Step 3.18. Integrate into X' using the roulette initialization method.
[0127] Step 3.19. Return to X'.
[0128] Step 108: If the target whale does not exist, a domain search is performed on the individual whale to obtain a domain whale.
[0129] Among them, domain search is a local search strategy that aims to improve the solution of the current whale individual. This process involves exploring possible solutions in the neighborhood of the current whale individual, looking for better or equivalent solutions through minor adjustments or changes while maintaining a certain degree of similarity with the original solution.
[0130] Specifically, a domain search may consider the local path choices, connectivity, or layout configurations of individual whales and attempt to generate new candidate solutions by replacing, inserting, or deleting certain elements. These candidate solutions are then evaluated according to a fitness function to determine whether they provide an improvement over the original solution.
[0131] If the domain search finds a solution with a better fitness value, then this new solution will be accepted and replace the original solution, becoming a new domain whale. This process helps to refine and optimize the individuals in the whale group, driving the entire group towards the global optimal solution or a higher quality solution space.
[0132] This step generates and determines a better domain whale through local exploration and improvement, thereby promoting the overall performance improvement of the entire whale group algorithm in solving the wind farm road optimization problem.
[0133] In order to avoid the domain search algorithm from looping infinitely, ensure that the algorithm can run efficiently with limited resources, and find a feasible solution or optimal solution to the problem within a reasonable time, it is necessary to set termination conditions for the algorithm, which usually include reaching a preset number of iterations, the fitness improvement is lower than a certain threshold, the quality of the solution meets the predetermined requirements, computing resources are exhausted, the algorithm shows convergence, no better solution is found in the neighborhood, or specific user-defined conditions are met.
[0134] In some embodiments, the step of performing a domain search on the whale individual to obtain a domain whale may specifically include: (1) Split each individual whale into a multidimensional list.
[0135] In the whale group algorithm, each whale individual represents a potential solution. Splitting the whale individuals into a multidimensional list is to decompose the components of the solution (such as individual road sections or nodes in the road layout) into units that can be processed and optimized independently, which helps the algorithm to explore and improve the solution more carefully.
[0136] (2) Determine a first sub-list and a second sub-list from the multi-dimensional list, wherein the first sub-list contains the selected random element, and the second sub-list does not contain the random element.
[0137] By identifying specific sublists from the multidimensional list, the algorithm can focus on optimizing specific parts of the solution. The first sublist contains selected random elements, which are randomly picked from the current solution and represent possible improvements, while the second sublist does not contain these random elements and usually contains the rest of the solution.
[0138] (3) According to the index values of the first sublist and the second sublist and the position of the random element in the first sublist, the first sublist and the second sublist are adjusted to obtain an adjusted multidimensional list.
[0139] This step involves adjusting the structure of the multidimensional list based on the indices of the sublists and the specific positions of the random elements. This adjustment may include reordering, replacing, or moving elements, with the goal of exploring new combinations or configurations to find a better solution while maintaining the coherence of the solution.
[0140] In some embodiments, this step may specifically include: (31) If the random element is at the first position in the first sublist, the first index value of the first sublist is less than the second index value of the second sublist, and the last element in the sublist with an index value between the first index value and the second index value is not the random element, then a non-last element is selected from the second sublist as a better element, and the better element is replaced in the first sublist, and the random element is replaced in the second sublist.
[0141] This optimizes the solutions of individual whales in the group and explores new solution spaces by exchanging elements between the two sublists. Specifically, when a random element is at the top of the first sublist and meets a specific index value condition, a non-last element in the second sublist is selected for replacement, aiming to introduce new path connections, which may improve the continuity and efficiency of the road layout while maintaining the diversity of solutions.
[0142] (32) If the random element is located between the first and last position in the first sublist, and the index value is in the sublist between the first index value and the second index value, and the last element is not the random element, then delete the random element from the first sublist and insert the random element into the second sublist.
[0143] In this way, when the random element is in the middle of the first sublist, by deleting the element and inserting it into the second sublist, the order of elements in the solution can be adjusted and reorganized to seek a more reasonable road layout. This operation helps to avoid local optimal solutions and promotes the algorithm to search in a wider solution space, increasing the possibility of finding the global optimal or approximate optimal solution.
[0144] (33) If the random element is at the last position in the first sublist, the first sublist and the second sublist are replaced with each other.
[0145] If the random element is at the end of the first sublist, the step of replacing the entire list means completely reconstructing the solution. The purpose of this strategy is to completely change the solution of the current whale individual and explore the solution space from a new perspective. This is especially important when the algorithm is trapped in a local optimum or needs to make a large jump to an unknown area. It helps the algorithm to break out of the existing mode and explore better solutions that may be overlooked.
[0146] (4) Determine domain whales based on the adjusted multidimensional list.
[0147] After the multidimensional list is adjusted, an updated solution is formed, which is called a domain whale. The domain whale represents the optimal or nearly optimal solution obtained through local search in the current search domain. It may become a reference or target for other whale individuals in subsequent iterations, thereby promoting the evolution of the entire whale group towards the global optimal solution.
[0148] In some embodiments, Figure 4 As shown, the specific execution steps of whale neighborhood search are as follows: Step 4.1. Split the whale into multidimensional lists by separators.
[0149] Step 4.2. Randomly select a list S from lists.
[0150] Among them, list S is the first sublist.
[0151] Step 4.3. Determine whether S is the first list in lists; if so, proceed to Step 4.4; if not, proceed to Step 4.5.
[0152] Step 4.4. Remove the last element in S.
[0153] Step 4.5, randomly select a coordinate S from S i .
[0154] Step 4.6, if S i is the first element.
[0155] Step 4.7. Select a list S' in lists that does not contain the element.
[0156] Among them, list S' is the second sublist.
[0157] Step 4.8. Determine whether the index value of S is less than the index value of S'; if so, proceed to Step 4.9; if not, terminate the loop.
[0158] Step 4.9. Determine whether the last element of the list between two indexes is S i ; If yes, terminate the loop, if no, go to Step 4.10.
[0159] Step 4.10, randomly select an element S from S' except the last element i '.
[0160] Step 4.11, S i and S i 'The two replace each other in the list.
[0161] Step 4.12, if S i The middle element.
[0162] Step 4.13. Select a list S' in lists that does not contain the element.
[0163] Step 4.14. Determine whether the last element of the list between two indexes is S i ; If yes, terminate the loop; if no, go to Step 4.15.
[0164] Step 4.15. Randomly select an element S from S' except the last element i '.
[0165] Step 4.16, put S i Delete from S, and put S i Insert into S'.
[0166] Step 4.17, if S i is the last element.
[0167] Step 4.18. Select a list S' in lists that does not contain the element.
[0168] Step 4.19. Replace S and S' with each other.
[0169] Step 4.20. Reorganize the multidimensional list into a list X'.
[0170] Step 4.21. Return to X'.
[0171] Step 109, determining the optimized whale based on the fitness of the whales in the field and the individual whale.
[0172] In the whale group algorithm, once the domain whales are obtained through domain search, the next task is to use these domain whales and their fitness information to optimize the current individual whales. This process involves evaluating the fitness of individual domain whales. Fitness reflects the quality of individual solutions, which is usually based on a comprehensive assessment of multiple factors such as road length, cost, and construction difficulty.
[0173] The optimization process may include comparing the fitness of the domain whale with the current individual whale, selecting the individual with higher fitness as a reference, or integrating some excellent characteristics of the domain whale (such as shorter paths, lower costs) into the current individual to produce a new, improved individual whale. This process helps to improve the overall fitness level of the whale group and promotes the algorithm to develop in the direction of finding a better road layout solution.
[0174] Step 110: determining an internal road optimization scheme for the wind farm according to the optimized whale.
[0175] After completing the optimization of individual whales, the algorithm will determine the internal road optimization plan of the wind farm based on these optimized whales. This step is the decision-making process of converting the search results of the algorithm into practical applications. Specifically, the algorithm will select the individual with the highest fitness from all optimized whale individuals, which represents the best road layout plan found in the current search stage. Then, based on the path information of this best individual, a specific road construction plan inside the wind farm is generated, including detailed planning of the starting point, end point, turning point, slope change, etc. of the road. This plan takes into account the terrain characteristics, construction cost and operational efficiency, and provides a scientific and reasonable road network design for the wind farm, thereby ensuring the efficient construction and smooth operation of the wind farm.
[0176] The method of this embodiment firstly aims at the problem of selecting the road between wind turbines in mountainous wind farms, and proposes an improved A* algorithm suitable for intelligent road selection in mountainous wind farms. The improved A* algorithm uses Manhattan distance as the heuristic function; uses DEM data to establish a slope grid, uses slope data to assign different costs to different slopes, and constructs an intelligent model for selecting the road for wind power facilities.
[0177] Secondly, in response to the problem of generating roads throughout the wind farm, this embodiment proposes a new algorithm based on wind farm road generation, namely the WSA-ROADOPT (Whale Swarm Algorithm for Road Optimization, WSA-ROADOPT) algorithm. Based on the whale swarm algorithm, a new objective function is designed, which is specifically aimed at the optimization requirements of the wind farm road layout. On this basis, four key aspects of the whale swarm algorithm are customized and improved: first, the individual encoding is adjusted to more accurately represent the complexity and diversity of the road layout in the wind farm; second, the individual initialization process is improved to generate an initial road layout plan that is closer to practical applications. Then, the calculation method of the distance between individuals is optimized to more reasonably evaluate the differences between different road layout plans. Finally, the individual movement rules are adjusted so that the algorithm can more effectively explore the solution space when simulating the social behavior of whale groups, thereby finding a better solution to the problem of wind farm road generation. Together, these improvements improve the algorithm’s performance and efficiency in solving specific wind farm road optimization problems, ensuring that the generated road layout achieves the best balance between economy, practicality, and adaptability.
[0178] The method provided in the above embodiment can be executed by an electronic device, and the electronic device is an electronic device. The electronic device in the embodiment of the present invention is described below from the perspective of hardware processing. Figure 5 , is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.
[0179] It should be noted that Figure 5 The structure of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0180] like Figure 5 As shown, the electronic device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.
[0181] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.
[0182] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the present invention are performed.
[0183] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0184] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.
[0185] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.
[0186] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the electronic device, the electronic device implements the method provided in the above embodiment.
[0187] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.
[0188] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.
[0189] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.
Claims
1. A method for intelligent optimization design of internal roads in a wind farm, characterized in that: include: Based on the DEM data of the wind farm, construct a plurality of slope grids on a map of the wind farm; According to the slope of the slope grid, a corresponding slope cost is configured for the slope grid; Constructing a wind power facility road line selection model based on the improved A* algorithm and the slope cost; Inputting the location information of each wind power facility in the wind farm into the wind power facility road line selection model to obtain the path optimization result between the wind power facilities; Determining an initial whale group of a whale group algorithm according to the path optimization result, wherein the whale individuals in the initial whale group represent a potential road layout solution; Obtaining the edit distance between the individual whales and the fitness of each individual whale; According to the edit distance and the fitness, determining whether there is a target whale with better fitness and the shortest edit distance around the individual whale; If not, a domain search is performed on the individual whale to obtain a domain whale; Determining an optimized whale based on the fitness of the field whale and the individual whale; An internal road optimization scheme of the wind farm is determined according to the optimized whale.
2. The method according to claim 1, characterized in that After the step of judging whether there is a target whale with better fitness and the closest edit distance around the individual whale according to the edit distance and the fitness, the method further includes: if the target whale exists, determining the position of the next generation whale according to the individual whale and the target whale; After the individual whale is moved to the position of the next generation whale, a field search is performed to obtain a field whale.
3. The method according to claim 2, characterized in that The step of determining the position of the next generation of whales according to the individual whales and the target whales comprises: Initialize the path list and set the loop termination condition; randomly selecting one or more elements from the individual whales or the target whales as target elements for multiple times, and adding the target elements to the path list; When the loop termination condition is met, stop selecting elements and obtain an adjusted path list; The next generation whale position is determined based on the adjusted path list.
4. The method according to claim 1, characterized in that The step of performing a domain search on the individual whales to obtain domain whales comprises: Splitting each of the individual whales into a multidimensional list; Determine a first sub-list and a second sub-list from the multi-dimensional list, the first sub-list containing the selected random element, and the second sub-list excluding the random element; According to the index values of the first sublist and the second sublist, and the position of the random element in the first sublist, the first sublist and the second sublist are adjusted to obtain an adjusted multidimensional list; Domain whales are determined based on the adjusted multidimensional list.
5. The method according to claim 4, characterized in that The step of determining a better element from the first sublist or the second sublist according to the index values of the first sublist and the second sublist and the position of the random element in the first sublist comprises: If the random element is at the first position in the first sublist, the first index value of the first sublist is less than the second index value of the second sublist, and the index value is in the sublist between the first index value and the second index value, and the last element is not the random element, then select an element that is not the last element from the second sublist as a better element, and replace the better element in the first sublist, and replace the random element in the second sublist; If the random element is located between the first and last position in the first sublist, and the index value is in the sublist between the first index value and the second index value, and the last element is not the random element, then delete the random element from the first sublist and insert the random element into the second sublist; If the random element is at the last position in the first sublist, the first sublist and the second sublist are completely replaced with each other.
6. The method according to claim 1, characterized in that The step of determining the initial whale group of the whale group algorithm according to the path optimization result includes: Adding multiple distance values between wind power facilities in the path optimization result to obtain a total distance value; Determine a plurality of probability values according to the plurality of distance values and the total distance value; generating a probability value sequence based on the plurality of probability values; Comparing each element in the probability value sequence with a randomly generated value to determine an initial wind power facility; connecting the initial wind power facilities to form an initial whale; A plurality of the initial whales are formed into an initial whale group.
7. The method according to any one of claims 1 to 6, characterized in that: The slope calculation formula of the slope grid includes: Wherein, Slope is the slope of the slope grid; Slope we Slope is the horizontal slope. sn is the vertical slope; e is the center point of the slope grid; e i (i=1,2,…,7,8) is the elevation value of the center point of the grid around the center point e; Cellsize is the grid size.
8. An electronic device, characterized in that: include: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method according to any one of claims 1 to 7.
9. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on an electronic device, the electronic device is caused to execute the method as claimed in any one of claims 1 to 7.
10. A computer program product, characterized in that When the computer program product is executed on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.
