Improved genetic algorithm-based method and system for topology design of wind farm power collection system

Abstract

The application discloses a kind of wind farm power collection system topology design method and system based on improved genetic algorithm, it is related to system topology design technical field, to solve the core problem of wind turbine grouping and submarine cable connection collaborative optimization under high-dimensional constraint, accurate matching of load flow and cost.The method determines the maximum number of wind turbines and the number range of feeder by parameter calculation module simultaneous equations, grouping connection module constructs initial scheme by polar grouping combined with minimum spanning tree algorithm, cost modeling module calculates cost by exclusive function, iteration optimization module dynamically adjusts grouping and the number of wind turbines based on improved genetic algorithm, constraint screening module excludes illegal scheme by penalty formula, and finally generates optimal and suboptimal topology graph containing core parameters.The application divides high-dimensional optimization problem into layers, considers constraint satisfaction degree and economy, significantly reduces submarine cable investment cost, improves design efficiency and engineering feasibility, and is suitable for various offshore wind farm power collection system topology design.

Description

Technical Field

[0001] This invention relates to the field of system topology design technology, specifically to a method and system for topology design of wind farm power collection systems based on an improved genetic algorithm. Background Technology

[0002] As the core network for collecting and transmitting electrical energy within an offshore wind farm, the power collection system's topology directly determines the cost, construction difficulty, and operation and maintenance efficiency of submarine cables, thus having a crucial impact on the economics and reliability of offshore wind power projects. With the development of offshore wind power towards large-scale and deep-sea applications, achieving optimal cost for power collection systems while meeting electrical constraints, marine environmental constraints, and reliability requirements has become a core technological focus for the industry.

[0003] Currently, the topology design of offshore wind farm collection systems largely relies on engineers' experience or simple grouping methods. Some studies have attempted to use intelligent optimization algorithms for solution search, but most have not fully considered the complexity of high-dimensional optimization problems. Existing technologies often integrate wind turbine grouping with intra-group connection design, resulting in a large optimization space, low computational efficiency, and difficulty in balancing economy and constraint satisfaction. Furthermore, traditional methods do not comprehensively consider key constraints such as submarine cable current carrying capacity limits and path non-intersection, making it difficult to generate globally optimal topology solutions.

[0004] Existing technologies have significant drawbacks: Firstly, empirical design methods cannot handle high-dimensional optimization requirements under complex constraints, easily leading to excessively high submarine cable investment costs or insufficient system reliability. Secondly, most existing algorithm optimization schemes lack hierarchical design, failing to dynamically adjust the number of wind turbine groups and the configuration of turbines within groups during the optimization process, thus limiting the exploration space and making it difficult to balance computational efficiency and optimization effectiveness. Furthermore, some methods lack accurate cost calculation models and do not fully consider the impact of downstream wind turbine power superposition on submarine cable selection, further affecting the economic viability and engineering feasibility of the topology scheme. Summary of the Invention

[0005] To address the aforementioned problems, this invention proposes a wind farm power collection system topology design method and system based on an improved genetic algorithm. This addresses the core contradiction of failing to accurately match current carrying capacity and cost in the collaborative optimization of wind turbine grouping and submarine cable connections under high-dimensional constraints. To achieve the above objective, the wind farm power collection system topology design method based on an improved genetic algorithm includes:

[0006] Step 1: Obtain the rated power of the offshore wind farm substation, the rated power of the wind turbine, and the maximum current carrying capacity, rated voltage, and power factor of the submarine cable. Calculate the maximum number of wind turbines that can be connected to each feeder and the range of feeder quantities.

[0007] Step 2: Based on the maximum number of wind turbines that can be connected to each feeder and the range of the number of feeders, establish polar coordinates with the offshore wind farm substation as the center, perform initial grouping of all wind turbines, and then complete the initial connection of each group of wind turbines through the minimum spanning tree algorithm to obtain the initial grouping scheme.

[0008] Step 3: Construct a submarine cable cost calculation function. Substitute the submarine cable selection parameters corresponding to the connection directed graph of each group of wind turbines in the initial grouping scheme, the unit price of submarine cable, the distance between adjacent wind turbines, and the number of downstream wind turbines into the function to calculate the initial total cost of submarine cable corresponding to the initial grouping scheme.

[0009] Step 4: Based on the initial grouping scheme and the initial total cost of the submarine cable, an improved genetic algorithm is used for iterative optimization. First, two adjacent wind turbine groups are randomly selected, and one wind turbine is selected from each group for exchange. Then, the number of wind turbines in each group is adjusted by random parameters to generate multiple candidate grouping schemes.

[0010] Step 5: Perform cable cross-constraint judgment on each candidate grouping scheme. For candidate grouping schemes that violate the constraints, trigger a cost penalty mechanism to make the computational cost of the candidate grouping scheme increase sharply and exceed the initial total cost of the submarine cable, and screen out feasible candidate schemes that meet the constraints.

[0011] Step 6: Sort all the feasible candidate solutions according to the total cost of the submarine cable, extract the cost-optimal solution and the second-best solution, and generate the corresponding offshore wind farm power collection system topology diagram.

[0012] Preferably, the maximum number of wind turbines that can be connected to each feeder and the range of the number of feeders are calculated using the following formula:

[0013] (1)

[0014] In the formula, This is the maximum power of the feeder. This refers to the rated power of the offshore wind farm substation. This refers to the maximum number of wind turbines that can be connected to each feeder. Number of feeders This refers to the rated power of the wind turbines in an offshore wind farm. The rated voltage of the current collection system, This is the maximum current carrying capacity of the submarine cable. This is the power coefficient.

[0015] Preferably, the polar coordinates are established with the center of the offshore wind farm substation as the origin, and the grouping of wind turbines corresponds to the angular partitioning of the polar coordinates. The number of wind turbines in each group does not exceed the formula.

[0016] (1) The maximum number of wind turbines that can be connected to each feeder. .

[0017] Preferably, the number of feeders The range of values ​​is ,in , , The minimum number of wind turbines that can be connected to each feeder. Indicates rounding up. This indicates rounding down to the nearest integer.

[0018] Preferably, the specific expression of the submarine cable cost calculation function is as follows:

[0019] (2)

[0020] In the formula, This represents the total cost of the submarine cable. This is a function for calculating the connection cost based on the minimum spanning tree algorithm. For the first Directed graph of fan unit connections. This is the unit price of the submarine cable. For the first The distance between two connected wind turbines in the group; this function is achieved through... Determine the number of downstream wind turbines, match the current carrying capacity of the submarine cable with the total power of the downstream wind turbines, and then calculate the corresponding cost of the submarine cable.

[0021] Preferably, the extraction of adjacent fan groups and the selection of fans within each group are both generated using random parameters. The range of values ​​for the random parameters is consistent with the number of fans in the corresponding group. Group and No. The combined expression after the fan group is swapped is:

[0022] (3)

[0023] In the formula, For the first Fan assembly, For the first Fan assembly, to For the first The fan before the group was replaced to For the first The fan before the group was replaced For the first The fan serial number selected for exchange within the group. For the first The fan serial number selected for exchange within the group. and All are random numbers.

[0024] Preferably, the random parameter The range of values ​​is to random parameters The range of values ​​is to ;when At that time, the first The group only accepts the first The group's fans do not supply the first Group output fan, number Increase in the number of fans , No. The number of fans has been reduced. ;when At that time, the first The group only accepts the first The group's fans do not supply the first Group output fan, number Increase in the number of fans , No. The number of fans has been reduced. .

[0025] Preferably, the core of the submarine cable cross constraint judgment is to detect whether there is a cross between the submarine cable connection paths of wind turbines in different groups, and the computational cost of candidate grouping schemes that violate this constraint. satisfy ,in This represents the initial total cost of the submarine cable. It is the penalty coefficient, and This ensures that solutions that violate the constraints are excluded from subsequent screening.

[0026] Preferably, the generated offshore wind farm power collection system topology diagram includes: the wind turbine grouping of the optimal and suboptimal schemes, the submarine cable connection path, the submarine cable type, and key calculation parameters for the total cost of the submarine cable.

[0027] A topology design system for offshore wind farm power collection systems based on an improved genetic algorithm, comprising:

[0028] The parameter calculation module is used to obtain the rated power of the offshore wind farm substation, the rated power of the wind turbine, and the maximum current carrying capacity, rated voltage, and power factor of the submarine cable, and to calculate the maximum number of wind turbines that can be connected to each feeder and the range of feeder numbers.

[0029] The group connection module is used to establish polar coordinates with the offshore wind farm substation as the center based on the maximum number of wind turbines that can be connected to each feeder and the range of the number of feeders, to initially group all wind turbines, and then complete the initial connection of each group of wind turbines through the minimum spanning tree algorithm to obtain the initial grouping scheme.

[0030] The cost modeling module is used to construct a submarine cable cost calculation function. Substitute the submarine cable selection parameters corresponding to the connection directed graph of each group of wind turbines in the initial grouping scheme, the unit price of submarine cable, the distance between adjacent wind turbines, and the number of downstream wind turbines into the function to calculate the initial total cost of submarine cable corresponding to the initial grouping scheme.

[0031] The iterative optimization module is used to perform iterative optimization based on the initial grouping scheme and the initial total cost of the submarine cable using an improved genetic algorithm. First, two adjacent wind turbine groups are randomly selected, and one wind turbine is selected from each group for exchange. Then, the number of wind turbines in each group is adjusted by random parameters to generate multiple candidate grouping schemes.

[0032] The constraint screening module is used to judge the submarine cable cross-constraints for each candidate grouping scheme. For candidate grouping schemes that violate the constraints, a cost penalty mechanism is triggered, which causes the computational cost of the candidate grouping scheme to increase sharply and exceed the initial total cost of the submarine cable, thereby screening out feasible candidate schemes that meet the constraints.

[0033] The topology generation module is used to sort all the feasible candidate schemes according to the total cost of the submarine cable, extract the cost-optimal scheme and the second-best scheme, and generate the corresponding offshore wind farm collection system topology map.

[0034] Compared with the prior art, the beneficial effects of the present invention are:

[0035] This invention addresses the core challenges of collaborative optimization of wind turbine grouping and submarine cable connections under high-dimensional constraints, as well as precise matching of current carrying capacity and cost, through a hierarchical collaborative optimization and precise quantitative design approach. The invention determines the maximum number and range of wind turbines in the feeder by using simultaneous formulas, clearly defining the value boundaries. It also ensures the compliance and efficiency of the initial scheme by combining polar coordinate grouping with a minimum spanning tree algorithm. Furthermore, it accurately calculates the cost of the submarine cable, including downstream power superposition, using a specific function. An improved genetic algorithm enables the exchange of adjacent wind turbine groups and dynamic adjustment of the number within groups, expanding the optimization dimension. A quantitative penalty mechanism eliminates cross-violation schemes, ultimately outputting the optimal and second-best topology diagrams containing key parameters. The progressive and collaborative approach of each scheme overcomes the shortcomings of traditional methods, such as low optimization efficiency and incomplete constraint considerations, while significantly reducing submarine cable costs. Simultaneously, it ensures that the scheme strictly meets electrical and marine environmental constraints, balancing computational accuracy, engineering feasibility, and selection flexibility. Attached Figure Description

[0036] Figure 1 A flowchart of the design method of the present invention is shown.

[0037] Figure 2 The overall algorithm architecture diagram of the present invention is shown.

[0038] Figure 3 This illustrates the grouping algorithm portion of the overall algorithm architecture of the present invention.

[0039] Figure 4 This illustrates the optimization algorithm portion of the overall computing architecture of the present invention.

[0040] Figure 5 The algorithm portion of the submarine cable cost calculation function in the overall calculation architecture of the present invention is shown.

[0041] Figure 6 The system architecture diagram of the present invention is shown.

[0042] Figure 7 A block diagram of an exemplary electronic device capable of implementing this embodiment is shown. Detailed Implementation

[0043] 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 some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of this invention, it should be noted that unless otherwise explicitly specified and limited, the terms "installed," "connected," "linked," and "set up" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The following describes embodiments of the invention based on its overall structure.

[0045] Figure 1 This is the overall algorithm architecture diagram of the present invention; Figure 2 This is a schematic diagram of the grouping algorithm, showing the polar coordinate grouping logic with the substation as the center. Each group forms a path without cross connections through the minimum spanning tree algorithm. Figure 3 This is a schematic diagram of the underlying optimization algorithm. Figure 4 This is a schematic diagram of the cost assessment algorithm.

[0046] Example 1:

[0047] Please see Figures 1-5 This invention discloses a topology design method for wind farm power collection systems based on an improved genetic algorithm. The core process is "parameter calculation - initial grouping - cost modeling - iterative optimization - constraint screening - topology generation". Each step / module is connected sequentially and data is interconnected to form a fully automated optimization system. This ensures a closed-loop logic from basic parameter input to topology scheme output, and achieves precise collaborative optimization of wind turbine grouping and submarine cable connection under high-dimensional constraints.

[0048] The parameter calculation process is based on the rated power of the offshore wind farm substation. Rated power of the fan Maximum current carrying capacity of submarine cable Rated voltage of the current collection system Power coefficient Based on the basic input, the key parameters are solved by simultaneously solving three core formulas. The specific simultaneous formulas are as follows:

[0049] (1)

[0050] in, This is the maximum power of the feeder. This refers to the maximum number of wind turbines that can be connected to each feeder. Let be the number of feeders. The solution can be obtained precisely using this simultaneous formula. and This ensures that the parameters simultaneously meet the current carrying capacity constraints of the submarine cable and the capacity requirements of the substation. The number of feeders needs to be further clarified. The range of values ​​for is determined by the formula. Calculate the minimum number of feeders ( (This indicates rounding up), using the formula Calculate the maximum number of feeders ( Indicates rounding down. (Minimum number of wind turbines that can be connected to each feeder), providing a flexible and compliant parameter space for subsequent grouping.

[0051] Feeder quantity range calculated based on parameters A polar coordinate system was established with the substation center as the origin. All wind turbines were initially grouped according to their polar coordinate angles, with the grouping results corresponding to the angle zones. This ensured that each group of wind turbines was geographically concentrated, reducing the risk of submarine cable crossings. The number of wind turbines in each group was strictly controlled. Within the specified range, the capacity constraints are met. After grouping, the minimum spanning tree algorithm is applied to initially connect each group of wind turbines. The algorithm aims to minimize the total length of the submarine cable connection paths within each group, while strictly adhering to the non-crossing constraint of submarine cables and the formula... A defined maximum capacity constraint for the feeder ensures that the initial design is both compliant and economical.

[0052] A function for calculating submarine cable costs based on the minimum spanning tree algorithm is constructed, with the specific expression as follows:

[0053] (2)

[0054] in, This represents the total cost of the submarine cable. This is a function for calculating the connection cost based on the minimum spanning tree algorithm. For the first Directed graph of fan unit connections. This is the unit price of the submarine cable. For the first The distance between two connected wind turbines in the group. This function is achieved through... By determining the number of downstream wind turbines and matching the total power of the downstream wind turbines with the current carrying capacity of the submarine cable, the corresponding cost of the submarine cable can be accurately calculated, providing a clear and reliable evaluation benchmark for subsequent iterative optimization.

[0055] Based on the initial grouping scheme and the initial total cost of the submarine cable Based on this, an improved genetic algorithm is used for iterative optimization. The optimization process includes two core actions, and the execution logic is defined by clear formulaic rules. The first is the exchange of adjacent grouped wind turbines, extracting the first... Group and No. The group performs a fan swap, and the combined expression after the swap is:

[0056] (3)

[0057] in, For the first Fan assembly, For the first Fan assembly, to For the first The fan before the group was replaced to For the first The fan before the group was replaced For the first The fan serial number selected for exchange within the group. For the first The fan serial number selected for exchange within the group. and All are random numbers. Secondly, the number of fans within the group is adjusted, using random parameters. The range of values ​​is to random parameters The range of values ​​is to ;when or At this time, the corresponding group only receives wind turbines and does not output wind turbines, realizing dynamic adjustment of the number. The two actions are carried out in tandem, which not only avoids violating the constraints of submarine cable crossings, but also greatly expands the optimization space.

[0058] Constraint screening: Ensuring project feasibility using penalty formulas

[0059] The focus is on rigorously judging submarine cable crossing constraints. By detecting whether there are crossings in the connection paths of submarine cables in different groups, a cost penalty mechanism is triggered for candidate grouping schemes that violate the constraints. The penalty rules are defined by a formula:

[0060] (4)

[0061] in, The computational cost of violating the constraints, This represents the initial total cost of the submarine cable. The penalty coefficient and This ensures that the computational cost of non-compliant solutions far exceeds the initial cost, effectively eliminating them. The combination of constraint judgments and penalty formulas not only guarantees the engineering feasibility of the final solution but also improves overall optimization efficiency.

[0062] For all feasible candidate solutions after constraint screening, based on the total cost of the submarine cable The optimal and second-best cost solutions are sorted, and corresponding offshore wind farm power collection system topology diagrams are generated. These topology diagrams contain complete key information, specifically covering wind turbine grouping, submarine cable connection paths, submarine cable types, and total submarine cable cost. And the maximum power of the feeder obtained from the parameter calculation process. Maximum number of wind turbines that can be connected to each feeder Number of feeders These core parameters provide comprehensive and accurate technical support for project implementation.

[0063] This invention, through a hierarchical optimization design approach and the quantitative support of multiple key formulas, decomposes high-dimensional optimization problems into several quantifiable and executable sub-problems. This effectively addresses the technical shortcomings of traditional empirical design methods, such as their inability to handle complex constraints, the limited depth of existing algorithms, and the constraints on optimization space. The simultaneous formulas for parameter calculation ensure the accuracy of key parameters; the combination of polar coordinate grouping and the minimum spanning tree algorithm ensures the compliance and efficiency of the initial solution; improved genetic algorithms and formulaic rules achieve deep optimization; the penalty formula for constraint selection ensures the feasibility of the solution; the cost calculation function ensures accurate accounting; and the final generated topology graph information is complete.

[0064] The entire technical solution strictly revolves around the core objective of "meeting constraints and reducing costs." All technical features and formula applications serve this objective. Under the premise of meeting electrical constraints, marine environmental constraints, and reliability requirements, it significantly reduces the investment cost of submarine cables, while taking into account computational efficiency, engineering feasibility, and selection flexibility, providing a systematic and innovative solution for the topology design of offshore wind farm power collection systems.

[0065] Example 2:

[0066] This embodiment is applied to a deep-sea wind farm project. The wind farm is planned to install 144 wind turbines with a rated power of 6MW, and the substation has a rated power of... Rated voltage of the current collection system The selected submarine cable is an XLPE insulated three-core submarine cable with a maximum current carrying capacity. Power coefficient The specific implementation steps are as follows:

[0067] 1. Parameter Calculation: The parameter calculation module performs the following operations: Based on the known parameters, it calculates the maximum number of wind turbines that can be connected to each feeder by solving simultaneous formulas. and number of feeders .

[0068] The simultaneous formulas are:

[0069]

[0070] in, , , , Substitute into the third equation to calculate the maximum power of the feeder. :

[0071]

[0072] Then according to , can be obtained Take the integer part (That is, the maximum number of wind turbines that can be connected to each feeder is 7).

[0073] Combination , can be obtained Therefore, the number of feeders tower.

[0074] 2. Initial grouping and connection: The grouping connection module and the parameter calculation module are connected by signal, and the following operations are performed:

[0075] Establish a polar coordinate system with the center of the substation as the origin. Divide the 144 wind turbines into 21 groups according to the polar coordinate angles. The first 18 groups each contain 7 wind turbines (not exceeding...). The last three groups each have six fans, ensuring that the number of fans in each group does not exceed the maximum number of fans that can be connected to each feeder.

[0076] Subsequently, a minimum spanning tree algorithm (using Kruskal's algorithm) is applied to each group of wind turbines for initial connection, with the goal of minimizing the total length of the submarine cable connection paths between the turbines within each group. For example, the coordinates of the 7 wind turbines in the first group are as follows: , , , , , , The connection order is determined using Kruskal's algorithm as follows: During the connection process, the constraints of no crossing of submarine cables and maximum capacity of feeder lines must be strictly followed (the total power of each group shall not exceed the limit). ).

[0077] 3. Cost Modeling: The cost modeling module is connected to the group connection module via signal, and the following operations are performed:

[0078] Construct a submarine cable cost calculation function ,in:

[0079] For the first The directed graph connecting the wind turbine groups is determined based on the connection order of the minimum spanning tree in step 2. For example, the directed graph of the first group is "substation". The number of downstream wind turbines is determined using this directed graph, such as... The downstream wind turbines number 6, and their total capacity is [missing information]. ;

[0080] The unit price of the selected XLPE insulated three-core submarine cable is 28,000 yuan / meter.

[0081] For the first The distance between two connected wind turbines in the group, for example and The distance between them was calculated as follows: That is, 210 meters.

[0082] Based on the above parameters, the cost of the submarine cable in Group 1 is calculated as: the sum of the length of each cable segment multiplied by the unit price of the corresponding cable model. The downstream wind turbines (6 units) require a cable current carrying capacity of 36MW, so a cable with a current carrying capacity of 800A is selected. The total cost of this group is 1.862 million yuan. Similarly, the initial total cost of all 21 groups is calculated. Ten thousand yuan.

[0083] 4. Iterative optimization: The iterative optimization module is connected to the group connection module and the cost modeling module via signals, and performs the following operations:

[0084] Based on the initial grouping scheme in step 2 and step 3 Using 10,000 yuan as a benchmark, an improved genetic algorithm is used for 100 generations of iterative optimization. The specific process is as follows:

[0085] In each iteration, two adjacent groups of wind turbines are randomly selected (e.g., group 5 and group 6). The wind turbines in group 5 before the swap are... ( The fan before the exchange in group 6 was ( );

[0086] Generate random numbers (The fan serial numbers selected for exchange in group 6) (The fan numbers selected for exchange in group 5), the two fan combinations after the exchange are:

[0087]

[0088]

[0089] In subsequent iterations, random numbers are generated. , At this point, group 6 only receives data from group 5. The fan will not output power to group 5, and the number of fans in group 6 will increase to 8 (exceeding the limit). (Subsequent constraint screening will be processed), the number of wind turbines in group 5 becomes 6.

[0090] 5. Constraint filtering: The constraint filtering module is signal-connected to the iterative optimization module and performs the following operations:

[0091] For each iteration of the candidate grouping scheme, submarine cable cross-constraint judgment is performed using a coordinate cross-detection method: the submarine cable connection path of each wind turbine group is converted into coordinate line segments, and the intersection of line segments from different groups is detected. If an intersection exists (such as the intersection of the submarine cable paths of group 12 and group 13), a cost penalty mechanism is triggered, and the computational cost is calculated accordingly. ,Pick ,Right now Ten thousand yuan 10,000 yuan, far exceeding This option was therefore eliminated. After screening, a total of 32 feasible candidate options that met the constraints were obtained.

[0092] 6. Topology generation: The topology generation module is signal-connected to the constraint filtering module and performs the following operations:

[0093] The 32 feasible candidate schemes were ranked according to the total cost of the submarine cable. The optimal scheme (total cost of RMB 35.283 million) and the second-best scheme (total cost of RMB 35.648 million) were extracted, and the corresponding offshore wind farm collection system topology diagram was generated. The topology diagram includes: wind turbine grouping (7 turbines per group in the first 18 groups and 6 turbines per group in the last 3 groups in the optimal scheme), submarine cable connection path, submarine cable type (XLPE insulated three-core submarine cable), total cost of submarine cable, and maximum power of feeder. Maximum number of wind turbines that can be connected to each feeder and number of feeders .

[0094] This embodiment solves the problems of low optimization efficiency and incomplete constraint consideration in traditional methods through the above technical solution. The iterative optimization process expands the optimization space, and the constraint screening ensures the compliance of the solution. The final topology solution reduces the submarine cable investment cost by about 8.9% compared with the initial solution, taking into account both economic efficiency and engineering feasibility.

[0095] Example 3

[0096] This embodiment applies to an offshore wind farm project. The wind farm is planned to install 120 wind turbines with a rated power of 5MW each, and the substation has a rated power of... Rated voltage of the current collection system The selected submarine cable is an XLPE insulated three-core submarine cable with a maximum current carrying capacity. Power coefficient Minimum number of wind turbines that can be connected to each feeder The specific implementation steps of this embodiment are as follows:

[0097] The parameter calculation module performs the following operations: Based on the known parameters, it calculates the key parameters and the range of feeder quantity using simultaneous formulas:

[0098] The simultaneous formulas are:

[0099]

[0100] Substitute parameters , , , ,calculate ;

[0101] Take the integer part ;

[0102] Calculate the number of feeders The range of values ​​for:

[0103]

[0104]

[0105] Therefore, the number of feeders The range of values ​​is Choose based on the actual project .

[0106] The group connection module and the parameter calculation module are connected by signal, and the following operations are performed:

[0107] Establish a polar coordinate system with the substation center as the origin, and divide the 120 wind turbines into 18 groups according to the polar coordinate angles, with each group containing 6-7 wind turbines (all within...). to (between), including 12 groups with 7 fans each and 6 groups with 6 fans each.

[0108] For each group of wind turbines, the Kruskal algorithm is applied for initial connection. For example, the coordinates of the 7 wind turbines in the 10th group are... , , , , , , The connection order is determined by an algorithm to ensure that the submarine cable paths within a group do not intersect and that the total power of each group does not exceed [a certain limit]. .

[0109] The cost modeling module and the group connection module are connected by signal to construct the submarine cable cost calculation function. ,in:

[0110] The directed graph connecting each group of wind turbines is determined based on the minimum spanning tree connection order. For example, the directed graph for the 10th group is "substation". ”;

[0111] The unit price of the selected XLPE insulated three-core submarine cable is 26,000 yuan / meter;

[0112] The distance between connected fans, such as and The distance between them is That is, 140 meters.

[0113] The cost of the submarine cable in group 10 is calculated to be 1.587 million yuan. The total initial cost of all 18 groups of submarine cables is... Ten thousand yuan.

[0114] The iterative optimization module performs 80 iterations. In each iteration:

[0115] Randomly select adjacent groups (e.g., group 11 and group 12), group 11 ( Group 12 Generate random numbers , After the exchange, the two sets of fans are combined as follows:

[0116]

[0117]

[0118] Generating random numbers in partial iterations , Group 12 only accepts applications from Group 11. The number of fans has increased to 8 (exceeding the limit). (Subsequently filtered out); generated , Group 11 only accepts Group 12. The number of fans has increased to 7 (in compliance with regulations). ).

[0119] The coordinate cross-detection method is used to determine whether submarine cable paths intersect, and a penalty coefficient is set for non-compliant schemes. Its computational cost Ten thousand yuan 10,000 yuan, higher than After eliminating these, 28 feasible candidate solutions were finally obtained.

[0120] The 28 feasible candidate solutions were ranked, and the optimal solution (total cost 26.897 million yuan) and the second-best solution (total cost 27.235 million yuan) were extracted. The generated topology map includes wind turbine grouping, submarine cable connection paths, submarine cable types, and total submarine cable cost. , , Key parameters, etc.

[0121] This embodiment further optimizes the rationality of grouping by clarifying the range of values ​​for the number of feeders. Compared with the initial scheme, it reduces the investment cost of submarine cables by about 9.2%, solves the problem of limited optimization space in traditional methods, and meets the actual engineering needs of near-shore wind farms, taking into account both calculation accuracy and selection flexibility.

[0122] The above three embodiments do not introduce any unnecessary technical features. Those skilled in the art can adjust the relevant parameters according to the actual project requirements to achieve the technical effects of the present invention. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described modules can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0123] Example 4:

[0124] See below Figure 6 A topology design system for offshore wind farm power collection system based on an improved genetic algorithm includes: a parameter calculation module, used to obtain the rated power of the offshore wind farm substation, the rated power of the wind turbine, and the maximum current carrying capacity, rated voltage, and power factor of the submarine cable, and to calculate the maximum number of wind turbines that can be connected to each feeder and the range of the number of feeders;

[0125] The group connection module is used to establish polar coordinates with the offshore wind farm substation as the center based on the maximum number of wind turbines that can be connected to each feeder and the range of the number of feeders, to initially group all wind turbines, and then complete the initial connection of each group of wind turbines through the minimum spanning tree algorithm to obtain the initial grouping scheme.

[0126] The cost modeling module is used to construct a submarine cable cost calculation function. Substitute the submarine cable selection parameters corresponding to the connection directed graph of each group of wind turbines in the initial grouping scheme, the unit price of submarine cable, the distance between adjacent wind turbines, and the number of downstream wind turbines into the function to calculate the initial total cost of submarine cable corresponding to the initial grouping scheme.

[0127] The iterative optimization module is used to perform iterative optimization based on the initial grouping scheme and the initial total cost of the submarine cable using an improved genetic algorithm. First, two adjacent wind turbine groups are randomly selected, and one wind turbine is selected from each group for exchange. Then, the number of wind turbines in each group is adjusted by random parameters to generate multiple candidate grouping schemes.

[0128] The constraint screening module is used to judge the submarine cable cross-constraints for each candidate grouping scheme. For candidate grouping schemes that violate the constraints, a cost penalty mechanism is triggered, which causes the computational cost of the candidate grouping scheme to increase sharply and exceed the initial total cost of the submarine cable, thereby screening out feasible candidate schemes that meet the constraints.

[0129] The topology generation module is used to sort all the feasible candidate schemes according to the total cost of the submarine cable, extract the cost-optimal scheme and the second-best scheme, and generate the corresponding offshore wind farm collection system topology map.

[0130] Example 5:

[0131] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product. Figure 7 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0132] Device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 302 or a computer program loaded from storage unit 308 into random access memory (RAM) 303. RAM 303 may also store various programs and data required for the operation of device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0133] Multiple components in device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of monitors, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0134] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of method 100 described above may be performed.

[0135] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0137] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0139] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0140] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0141] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0142] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A wind farm power collection system topology design method based on an improved genetic algorithm, characterized in that, Includes the following steps: Step 1: Obtain the rated power of the offshore wind farm substation, the rated power of the wind turbines, and the maximum current carrying capacity, rated voltage, and power factor of the submarine cables. Calculate the maximum number of wind turbines that can be connected to each feeder and the range of feeder numbers. The maximum number of wind turbines that can be connected to each feeder and the range of feeder numbers are calculated using the following formula: （1） In the formula, This is the maximum power of the feeder. This refers to the rated power of the offshore wind farm substation. This refers to the maximum number of wind turbines that can be connected to each feeder. Number of feeders This refers to the rated power of the wind turbines in an offshore wind farm. The rated voltage of the current collection system, This is the maximum current carrying capacity of the submarine cable. Power coefficient; Step 2: Based on the maximum number of wind turbines that can be connected to each feeder and the range of the number of feeders, establish polar coordinates with the offshore wind farm substation as the center, perform initial grouping of all wind turbines, and then complete the initial connection of each group of wind turbines through the minimum spanning tree algorithm to obtain the initial grouping scheme. Step 3: Construct a submarine cable cost calculation function. Substitute the submarine cable selection parameters corresponding to the connection directed graph of each group of wind turbines in the initial grouping scheme, the unit price of submarine cable, the distance between adjacent wind turbines, and the number of downstream wind turbines into the function to calculate the initial total cost of submarine cable corresponding to the initial grouping scheme. Step 4: Based on the initial grouping scheme and the initial total cost of the submarine cable, an improved genetic algorithm is used for iterative optimization. First, two adjacent wind turbine groups are randomly selected, and one wind turbine is selected from each group for exchange. Then, the number of wind turbines in each group is adjusted by random parameters to generate multiple candidate grouping schemes. The selection of adjacent fan groups and the selection of fans within each group are both generated using random parameters. The range of values ​​for the random parameters is consistent with the number of fans in the corresponding group. Group and No. The combined expression after the fan group is swapped is: （3） In the formula, For the first Fan assembly, For the first Fan assembly, to For the first The fan before the group was replaced to For the first The fan before the group was replaced For the first The fan serial number selected for exchange within the group. For the first The fan serial number selected for exchange within the group. and All are random numbers; The random parameter The range of values ​​is to random parameters The range of values ​​is to ;when At that time, the first The group only accepts the first The group's fans do not direct to the first Group output fan, number Increase in the number of fans , No. The number of fans has been reduced. ;when At that time, the first The group only accepts the first The group's fans do not direct to the first Group output fan, number Increase in the number of fans , No. The number of fans has been reduced. ; Step 5: Perform cable cross-constraint judgment on each candidate grouping scheme. For candidate grouping schemes that violate the constraints, trigger a cost penalty mechanism to make the computational cost of the candidate grouping scheme increase sharply and exceed the initial total cost of the submarine cable, and screen out feasible candidate schemes that meet the constraints. Step 6: Sort all the feasible candidate solutions according to the total cost of the submarine cable, extract the cost-optimal solution and the second-best solution, and generate the corresponding offshore wind farm power collection system topology diagram.

2. The method of claim 1, wherein, The polar coordinates are established with the center of the offshore wind farm substation as the origin. The grouping of wind turbines corresponds to the angular partitioning of the polar coordinates. The number of wind turbines in each group does not exceed the maximum number of wind turbines that can be connected to each feeder as calculated by formula (1). .

3. The method of claim 1, wherein, The number of feeders The range of values ​​is ,in , , The minimum number of wind turbines that can be connected to each feeder. Indicates rounding up. This indicates rounding down to the nearest integer.

4. The method of claim 1, wherein, The specific expression for the submarine cable cost calculation function is as follows: （2） In the formula, This represents the total cost of the submarine cable. This is a function for calculating the connection cost based on the minimum spanning tree algorithm. For the first Directed graph of fan unit connections. This is the unit price of the submarine cable. For the first The distance between two connected wind turbines in the group; this function is achieved through... Determine the number of downstream wind turbines, match the current carrying capacity of the submarine cable with the total power of the downstream wind turbines, and then calculate the corresponding cost of the submarine cable.

5. The method of claim 1, wherein, The core of the submarine cable cross constraint judgment is to detect whether there is a cross between the submarine cable connection paths of wind turbines in different groups, and the computational cost of candidate grouping schemes that violate this constraint. satisfy ,in This represents the initial total cost of the submarine cable. The penalty coefficient is, and This ensures that solutions that violate the constraints are excluded from subsequent screening.

6. The method of claim 1, wherein, The generated offshore wind farm power collection system topology diagram includes: the wind turbine grouping of the optimal and suboptimal schemes, the submarine cable connection path, the submarine cable type, and key calculation parameters for the total cost of the submarine cable.

7. A system for topology design of a wind farm power collection system based on improved genetic algorithm, the system being configured to perform the steps of the method according to any one of claims 1-6, characterized in that, include: The parameter calculation module is used to obtain the rated power of the offshore wind farm substation, the rated power of the wind turbine, and the maximum current carrying capacity, rated voltage, and power factor of the submarine cable, and to calculate the maximum number of wind turbines that can be connected to each feeder and the range of feeder numbers. The group connection module is used to establish polar coordinates with the offshore wind farm substation as the center based on the maximum number of wind turbines that can be connected to each feeder and the range of the number of feeders, to initially group all wind turbines, and then complete the initial connection of each group of wind turbines through the minimum spanning tree algorithm to obtain the initial grouping scheme. The cost modeling module is used to construct a submarine cable cost calculation function. Substitute the submarine cable selection parameters corresponding to the connection directed graph of each group of wind turbines in the initial grouping scheme, the unit price of submarine cable, the distance between adjacent wind turbines, and the number of downstream wind turbines into the function to calculate the initial total cost of submarine cable corresponding to the initial grouping scheme. The iterative optimization module is used to perform iterative optimization based on the initial grouping scheme and the initial total cost of the submarine cable using an improved genetic algorithm. First, two adjacent wind turbine groups are randomly selected, and one wind turbine is selected from each group for exchange. Then, the number of wind turbines in each group is adjusted by random parameters to generate multiple candidate grouping schemes. The constraint screening module is used to judge the submarine cable cross-constraints for each candidate grouping scheme. For candidate grouping schemes that violate the constraints, a cost penalty mechanism is triggered, which causes the computational cost of the candidate grouping scheme to increase sharply and exceed the initial total cost of the submarine cable, thereby screening out feasible candidate schemes that meet the constraints. A topology generation module is configured to sort all the feasible candidate schemes according to the total cable cost, extract the optimal scheme and the suboptimal scheme, and generate a corresponding offshore wind farm power collection system topology graph.

Images