Double-layer multi-target planning method and system for bilateral looped network current collection system of offshore wind plant

Abstract

The invention discloses a double-layer multi-target planning method and system for a bilateral looped network current collection system of an offshore wind plant, and the method comprises the steps: inputting the data of the offshore wind plant into a double-layer planning model of the bilateral looped network current collection system, and enabling an outer-layer model to be used for constructing a plurality of two-dimensional populations composed of weights and the number of clusters, and inputting the two-dimensional populations into an inner-layer model; the inner-layer model is used for grouping the wind turbine generators under different two-dimensional populations by adopting a clustering algorithm, taking minimum cable investment cost and minimum network loss as objective functions and adding constraint conditions to construct a path optimization model so as to carry out path planning on the wind turbine generator groups, solving total cost and outputting the total cost to the outer-layer model; and ending iteration of the outer layer model when the total cost is converged, if not, continuing to output an optimal solution result, and otherwise, continuing to update the two-dimensional population. The invention aims to spontaneously cluster wind turbine generators through a heuristic algorithm and find the optimal path of the bilateral looped network of the wind turbine generators so as to realize accurate planning of the bilateral looped network current collection system of the offshore wind power plant.

Description

Technical Field

[0001] The present invention relates to the field of wind power technology, and in particular to a double-layer multi-objective planning method and system for a bilateral ring network collection system of an offshore wind farm. Background Art

[0002] In the context of the strong support and development of the wind power industry, offshore wind farms are receiving widespread attention and active exploration around the world due to their significant advantages. Compared with onshore wind farms, offshore wind farms have more abundant wind resources and vast space resources, showing great development potential. The topological planning of the offshore wind farm collection system can optimize the cable layout, reduce construction costs, improve system reliability, adapt to the development needs of deep sea areas, and help large-scale wind power to operate efficiently. It is an important guarantee for the development of offshore wind power. Among them, the bilateral ring network collection system design of offshore wind farms has the advantages of high reliability, low power loss, and strong redundancy, which can effectively improve the operational stability of wind farms. Therefore, how to minimize the investment cost and operating loss of the designed collection system while ensuring the high reliability of the offshore wind farm collection system has become a key technical problem that needs to be solved urgently. Summary of the invention

[0003] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a double-layer multi-objective planning method and system for a bilateral ring network collection system of an offshore wind farm are provided. The present invention aims to prevent cable crossing between bilateral ring networks, avoid crossing of cables between offshore transformers and onshore transformers with bilateral ring network cables, spontaneously cluster wind turbines through heuristic algorithms and find the optimal path of their bilateral ring networks, so as to achieve accurate planning of the bilateral ring network collection system of the offshore wind farm.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: A double-layer multi-objective planning method for a bilateral ring network collection system of an offshore wind farm comprises the following steps: obtaining wind farm data of an offshore wind farm; inputting the wind farm data into a double-layer planning model of a bilateral ring network collection system, wherein the double-layer planning model of the bilateral ring network collection system comprises an outer model and an inner model, wherein the outer model is used to initially construct a weighted ω and the number of clusters k The multiple two-dimensional populations formed are input into the inner layer model, and the inner layer model is used to use the direction angle and distance of the wind farm as clustering indicators and adopt a clustering algorithm to perform different weights ω and the number of clusters kThe wind turbine groups are grouped under the condition of minimum cable investment cost and minimum network loss as the objective function and constraints are added to build a path optimization model to plan the path for the wind turbine groups. The solver is used to solve the topological structure of the bilateral ring network collection system and the total cost composed of the value of its objective function, which is output to the outer model. When the total cost converges, the outer model outputs the optimal topological structure of the bilateral ring network collection system and its corresponding total cost. Otherwise, the current two-dimensional population is selected, crossed and mutated based on the genetic algorithm to update the two-dimensional population and input it into the inner model to continue iterating until the total cost converges.

[0005] Optionally, when initially constructing multiple two-dimensional populations consisting of weights and cluster numbers, the weights ω is a random value in the interval [0,1], the number of clusters k The value is in the interval [ K , K +2], where K is the minimum number of bilateral ring networks contained in the collection system. The calculation function expression of the minimum number of bilateral ring networks contained in the collection system is: , , Among them, ceil is the upward rounding function, and fix is ​​the downward rounding function. N is the total number of wind turbines in the wind farm, nwt To accurately consider the maximum number of wind turbines that can be included in a single bilateral ring network when cable redundancy is taken into account, cable is the cable capacity between wind turbines connected to the offshore substation in a single bilateral ring network, swt The capacity of a single fan.

[0006] Optionally, the wind farm direction angle and distance are used as clustering indicators and clustering algorithms are used to perform different weightings. ω and the number of clusters k The clustering algorithm used when grouping wind turbine groups under the condition is an improved fuzzy clustering algorithm. The clustering objective of the improved fuzzy clustering algorithm is to find the value of the clustering objective function shown in the following formula to be minimized: , , in, is the clustering objective function, N is the total number of wind turbines in the wind farm, is the number of clusters, For fans Cluster Center The membership degree of m is the index of the membership matrix formed by the membership degree, For fans To cluster center The comprehensive distance considering the direction angle and distance, is the coordinate of the i-th wind turbine, is the jth cluster center, and: , , , in, is the comprehensive distance coefficient, ω is the weight, is the azimuth angle of the wind turbine and cluster center azimuth The difference, is the absolute distance between the i-th wind turbine and the j-th cluster center, r is the distance constant, ε is the length factor, For fans To cluster center The comprehensive distance considering the direction angle and distance, For the p Cluster centers.

[0007] Optionally, the calculation function expression of the distance constant is: ; The wind turbine azimuth and cluster center azimuth The calculation function expression of the difference is: , The calculation function expression of the absolute distance between the i-th wind turbine and the j-th cluster center is:

[0008] The calculation function expression of the comprehensive distance coefficient is:

[0009] in, and are the comprehensive distance coefficients at time t and time t-1, is the sum of the capacities of all fans in the jth ring network, is the maximum allowed capacity of the jth ring network.

[0010] Optionally, when the objective function is to minimize the cable investment cost and the network loss and to add constraints to construct a path optimization model to plan the path for the wind turbine group, the function expression of the constructed objective function is: , , , , In the above formula, is the objective function, is the cost of medium voltage submarine cable, The power loss cost of medium voltage submarine cable transmission; is a binary decision variable A set of binary decision variables Indicates whether node i and node j are connected by A The level cable is connected, the value is 1 when connected, otherwise it is 0; For medium voltage cable assembly, is the set of wind turbine nodes, A collection of time nodes for a year. for A Grade cable unit price, is the cable length between nodes ij, Indicates the total service life of the cable in years, is the cable power loss cost for one year, is the annual inflation rate of energy prices, ep For energy prices, Indicates that A The power loss cost between nodes i and j connected by the level cable in time period h.

[0011] Optionally, when the objective function is to minimize the cable investment cost and the network loss and to add constraints to construct a path optimization model to plan the path for the wind turbine group, the function expression of the constraints added is: , , , , , , , in, and is a binary decision variable, Indicates whether node i is connected to node j by a cable, Indicates whether node j is connected to node i through a cable. If so, the value is 1, otherwise, it is 0. is the set of wind turbine nodes, , and are the active power, reactive power and voltage at node i respectively, is the voltage at node j, , are the conductance and susceptance values ​​between nodes i and j, respectively. is the azimuth difference between nodes i and j, , , , are the minimum voltage, maximum voltage, minimum azimuth angle and maximum azimuth angle at node i respectively. , are the flows between nodes i and j respectively. A The current of the graded cable and its maximum value.

[0012] Optionally, the total cost convergence means that the total cost is less than a preset value or the number of iterations is equal to a preset maximum number of iterations.

[0013] In addition, the present invention also provides a double-layer multi-objective planning system for a bilateral ring network collection system of an offshore wind farm, comprising an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm.

[0014] In addition, the present invention also provides a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is programmed or configured to execute the double-layer multi-objective planning method of the bilateral ring network collection system of the offshore wind farm through a processor.

[0015] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the double-layer multi-objective planning method of the bilateral ring network collection system of the offshore wind farm through a processor.

[0016] Compared with the prior art, the present invention mainly has the following advantages: the method of the present invention comprises inputting the offshore wind farm into the double-layer programming model of the bilateral ring network power collection system, wherein the outer model is used to construct a plurality of two-dimensional populations consisting of weights and cluster numbers and input them into the inner model, the inner model is used to adopt a clustering algorithm to group wind turbines under different two-dimensional populations, take the minimum cable investment cost and the minimum network loss as the objective function and add constraints to construct a path optimization model to plan the path of the wind turbine group and solve the total cost and output it to the outer model, the outer model ends the iteration when the total cost converges, otherwise continues to output the optimal solution result, otherwise continues to update the two-dimensional population, the double-layer programming model of the bilateral ring network power collection system of the offshore wind farm designed by the present invention can not only prevent the crossing of cables between the bilateral ring networks, but also avoid the crossing of the cables between the offshore transformer and the onshore transformer and the bilateral ring network cables, and at the same time spontaneously clusters the wind turbines through a heuristic algorithm and finds the optimal path of its bilateral ring network, so as to realize the accurate planning of the bilateral ring network power collection system of the offshore wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0018] Figure 2 Schematic diagram of the optimal topology structure obtained by using the improved scanning method of the genetic algorithm for comparison in the embodiments of the present invention, wherein (a) is the optimal topology structure of an offshore wind farm with 20 wind turbines, (b) is the optimal topology structure of an offshore wind farm with 30 wind turbines, and (c) is the optimal topology structure of an offshore wind farm with 42 wind turbines.

[0019] Figure 3 Schematic diagram of the topological structure obtained by the wind turbine scanning method used as a comparison in the embodiments of the present invention, wherein (a) is the optimal topological structure of an offshore wind farm with 20 wind turbines, (b) is the optimal topological structure of an offshore wind farm with 30 wind turbines, and (c) is the optimal topological structure of an offshore wind farm with 42 wind turbines.

[0020] Figure 4 Schematic diagram of the topological structure obtained by the genetic algorithm used as a comparison in the embodiments of the present invention, wherein (a) is the optimal topological structure of an offshore wind farm with 20 wind turbines, (b) is the optimal topological structure of an offshore wind farm with 30 wind turbines, and (c) is the optimal topological structure of an offshore wind farm with 42 wind turbines.

[0021] Figure 5 Schematic diagram of the topological structure obtained by the method of this embodiment of the present invention, wherein (a) is the optimal topological structure of an offshore wind farm with 20 wind turbines, (b) is the optimal topological structure of an offshore wind farm with 30 wind turbines, and (c) is the optimal topological structure of an offshore wind farm with 42 wind turbines.

[0022] Figure 6 Schematic diagram of the topological structure obtained by the mathematical programming method for comparison in the embodiments of the present invention, wherein (a) is the optimal topological structure of an offshore wind farm with 20 wind turbines, (b) is the optimal topological structure of an offshore wind farm with 30 wind turbines, and (c) is the optimal topological structure of an offshore wind farm with 42 wind turbines. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0024] like Figure 1 As shown, the double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm in this embodiment includes the following steps: obtaining wind farm data of the offshore wind farm; inputting the wind farm data into a double-layer planning model of the bilateral ring network collection system, wherein the double-layer planning model of the bilateral ring network collection system includes an outer model and an inner model, wherein the outer model is used to initially construct a weighted ω and the number of clusters k The multiple two-dimensional populations formed are input into the inner layer model, and the inner layer model is used to use the direction angle and distance of the wind farm as clustering indicators and adopt a clustering algorithm to perform different weights ω and the number of clusters k The wind turbine groups are grouped under the condition of minimum cable investment cost and minimum network loss as the objective function and constraints are added to build a path optimization model to plan the path for the wind turbine groups. The solver is used to solve the topological structure of the bilateral ring network collection system and the total cost composed of the value of its objective function, which is output to the outer model. The outer model outputs the optimal topological structure of the bilateral ring network collection system and its corresponding total cost when the total cost converges (the total cost is less than the preset value or the number of iterations is equal to the preset maximum number of iterations). Otherwise, the current two-dimensional population is selected, crossed and mutated based on the genetic algorithm to update the two-dimensional population and input it into the inner model to continue iterating until the total cost converges. Figure 1 As shown, the two-layer planning model of the bilateral ring network collection system in this embodiment includes an outer model and an inner model. The outer model is a genetic algorithm model, which is used to iterate weights and cluster number variables to obtain the topological structure and the optimal total cost of the bilateral ring network collection system of the offshore wind farm. The inner model is an improved fuzzy clustering model and a path optimization model, which is used to group wind turbines with different weights and cluster number variables, and perform path planning to obtain the topological structure and the total cost of the bilateral ring network collection system of the offshore wind farm under the current conditions.

[0025] In this embodiment, when initially constructing multiple two-dimensional populations consisting of weights and cluster numbers, the number of two-dimensional populations can be selected as needed. For example, as an optional implementation, the number of two-dimensional populations in this embodiment is 30. ω is a random value in the interval [0,1], the number of clusters k The value is in the interval [ K , K +2], where K is the minimum number of bilateral ring networks contained in the collection system. The calculation function expression of the minimum number of bilateral ring networks contained in the collection system is: , , Among them, ceil is the upward rounding function, and fix is ​​the downward rounding function. N is the total number of wind turbines in the wind farm, nwt To accurately consider the maximum number of wind turbines that can be included in a single bilateral ring network when cable redundancy is taken into account, cable is the cable capacity between wind turbines connected to the offshore substation in a single bilateral ring network, swt The capacity of a single fan.

[0026] In this embodiment, based on the weight and cluster number data input by the outer model, the inner model uses the direction angle and distance as clustering indicators, and the improved clustering model based on the comprehensive direction angle and distance factors is constructed to group wind turbines. ω and the number of clusters k The clustering algorithm used when grouping wind turbine groups under the condition is an improved fuzzy clustering algorithm. The clustering objective of the improved fuzzy clustering algorithm is to find the value of the clustering objective function shown in the following formula to be minimized: , , in, is the clustering objective function, N is the total number of wind turbines in the wind farm, is the number of clusters, For fans Cluster Center The membership degree of m is the exponent of the membership matrix composed of membership degrees (the value can be taken according to the actual situation, for example, the value is 2), For fans To cluster center The comprehensive distance considering the direction angle and distance, is the coordinate of the i-th wind turbine, is the jth cluster center, and: , , , in, is the comprehensive distance coefficient, ω is the weight, is the azimuth angle of the wind turbine and cluster center azimuth The difference, is the absolute distance between the i-th wind turbine and the j-th cluster center, r is the distance constant, ε is the length coefficient (the value can be determined according to the actual situation, for example, in this embodiment, the value is 1×10 -5 ), For fans To cluster center The comprehensive distance considering the direction angle and distance, For the p Cluster centers.

[0027] Among them, the calculation function expression of the distance constant is: ; The wind turbine azimuth and cluster center azimuth The calculation function expression of the difference is: , The calculation function expression of the absolute distance between the i-th wind turbine and the j-th cluster center is:

[0028] The calculation function expression of the comprehensive distance coefficient is:

[0029] in, and are the comprehensive distance coefficients at time t and time t-1, is the sum of the capacities of all fans in the jth ring network, is the maximum allowed capacity of the jth ring network.

[0030] In this embodiment, based on the divided wind turbine groups, the path optimization model constructed in the inner layer is used to plan the path of the wind turbine group, find the optimal path of the wind turbine group in each bilateral ring network, and consider the cable investment cost and network loss. When the path optimization model is constructed with the minimum cable investment cost and the minimum network loss as the objective function and the constraint conditions are added to plan the path of the wind turbine group, the function expression of the constructed objective function is: , , , , In the above formula, is the objective function, is the cost of medium voltage submarine cable, The power loss cost of medium voltage submarine cable transmission; is a binary decision variable A set of binary decision variables Indicates whether node i and node j are connected by A The level cable is connected, the value is 1 when connected, otherwise it is 0; For medium voltage cable assembly, is the set of wind turbine nodes, A collection of time nodes for a year. for A Grade cable unit price, is the cable length between nodes ij, Indicates the total service life of the cable in years, is the cable power loss cost for one year, is the annual inflation rate of energy prices (in this embodiment, the annual inflation rate of energy prices is is 0.08), ep For energy prices, Indicates that A The power loss cost between nodes i and j connected by the level cable in time period h.

[0031] The path optimization model is essentially a vehicle path problem, which must satisfy the constraint that each node is visited and only visited once. At the same time, each node must also satisfy the active power and reactive power balance equations, voltage amplitude, voltage angle, and maximum current transmission constraints. In this embodiment, when the path optimization model is constructed with the minimum cable investment cost and the minimum network loss as the objective function and constraints are added to plan the path for the wind turbine group, the function expression of the constraints added is: , , , , , , , in, and is a binary decision variable, Indicates whether node i is connected to node j by a cable, Indicates whether node j is connected to node i through a cable. If so, the value is 1, otherwise, it is 0. is the set of wind turbine nodes, , and are the active power, reactive power and voltage at node i respectively, is the voltage at node j, , are the conductance and susceptance values ​​between nodes i and j, respectively. is the azimuth difference between nodes i and j, , , , are the minimum voltage, maximum voltage, minimum azimuth angle and maximum azimuth angle at node i respectively. , are the flows between nodes i and j respectively. A The current of the graded cable and its maximum value.

[0032] After taking the minimum cable investment cost and the minimum network loss as the objective function and adding constraints to construct a path optimization model, based on the inner path planning model, a solver is used to solve the objective function, and the optimal path corresponding to the bilateral ring network is found for all wind turbine groups, and the topological structure of the bilateral ring network collection system and the value of its objective function are obtained to form the minimum total cost, which is output to the outer model. After the genetic algorithm model corresponding to the outer model obtains the total cost of the bilateral ring network collection system under different populations, multiple populations are selected, crossed, mutated, and other operations are performed. In this embodiment, the crossover rate and mutation rate of the population are 0.7. The weights and the number of clusters input to the inner layer are continuously changed to obtain the corresponding total cost and topological structure of the inner layer output, with the goal of obtaining the minimum total cost, and repeated iterations are performed until the optimal solution for the planning of the bilateral ring network collection system of the offshore wind farm is obtained. Population selection, crossover, mutation, and other operations are well-known genetic algorithm calculation operations, so their implementation details are not described in detail here.

[0033] In order to verify the double-layer multi-objective planning method of the bilateral ring network collection system of the offshore wind farm in this embodiment, a simulation verification is carried out in this embodiment. In this embodiment, an offshore wind farm with 20 / 30 / 42 wind turbines is used for verification. Table 1 shows the specifications of the 33kV aluminum cross-linked polyethylene cable used in the offshore wind farm, including the cross-sectional area and the corresponding rated capacity, resistance per unit length, inductance and cost.

[0034] Table 1: Specifications of three (single) core aluminum XLPE cables

[0035] In Table 1, MVA refers to the capacity of the cable in megavolt-amperes (million volt-amperes).

[0036] Figure 2 to Figure 6 The topological design methods of bilateral ring network collection systems of the present embodiment and other methods are compared in the planning results of offshore wind farms with 20 / 30 / 42 wind turbines. All methods take into account the precise cable rating and network loss requirements. Other methods include: genetic algorithm improved scanning method, scanning method, genetic algorithm, and global optimal solution obtained by mathematical programming method. Figure 2 This is a schematic diagram of the optimal topological structure obtained by using the genetic algorithm to improve the scanning method in this embodiment for comparison. Figure 3 Schematic diagram of the topological structure obtained by the fan scanning method used as a comparison in this embodiment, Figure 4 Schematic diagram of the topological structure obtained by the genetic algorithm used as a comparison in this embodiment, Figure 5 Schematic diagram of the topological structure obtained by the method of this embodiment, Figure 6The schematic diagram of the topological structure obtained by the mathematical programming method used as a comparison in this embodiment. Among them, the genetic algorithm improved scanning method randomly determines the number of wind turbines in each group through a genetic algorithm, uses a scanning algorithm to divide the wind turbines contained in each group counterclockwise from the direction of the high-voltage cable, uses a genetic algorithm to plan the path, and continuously updates the population to obtain the optimal solution with the goal of minimizing the total cost. In the genetic algorithm improved scanning method, the population size is set to 30, and the crossover rate and mutation rate are 0.7. The scanning method uses a scanning algorithm to divide all wind turbines into several clusters counterclockwise from the direction of the high-voltage cable, and then uses a genetic algorithm to plan the wind farm collection system. The genetic algorithm randomly sorts and segments the wind turbines, uses a genetic algorithm to plan the path for each group of wind turbines, and continuously updates the population to find the optimal solution. In the genetic algorithm, the population size is set to 500, and the population update uses random operations such as flipping, exchanging, sliding, and modifying breakpoints on the population fragments. The mathematical programming method uses a mixed integer quadratic programming model to minimize the cable cost and total power loss, and obtains the global minimum value of the total cable investment cost and total power loss over the entire life cycle of the offshore wind farm. The solver used to implement the mathematical programming method is gurobi. The solution gaps for the 20 / 30 / 42 wind turbine systems are 0%, 4.72%, and 7.21%, respectively. The solution gap refers to the relative gap between the upper bound (the target value of the current best feasible solution) and the lower bound (the target value of the relaxed problem) at the end of the solution process. Therefore, the 20-wind turbine system has reached the global optimal solution, while the 30 and 42 wind turbines may not have reached the global optimal solution after spending a lot of solution time.

[0037] The simulation and optimization of all methods in this embodiment are carried out in MATLAB software R2021b version on a PC with a 2.8-GHz CPU and 32-GB RAM environment. The economic results of the design of the bilateral ring network collection system for an offshore wind farm using 20 / 30 / 42 wind turbines are shown in Table 2.

[0038] Table 2: Comparison of economics of offshore wind farms using 20 / 30 / 42 turbines

[0039] As can be seen from Table 2, compared with the improved scanning method of the genetic algorithm, in the offshore wind farm systems of 20, 30 and 42 wind turbines, the investment cost of the method of this embodiment is saved by 3.39%, 0.64% and 2.29%, respectively, and the total cost of the method of this embodiment is saved by 3.37%, 0.71% and 1.82%, respectively. Compared with the scanning method, in the offshore wind farm systems of 20, 30 and 42 wind turbines, the investment cost of the method of this embodiment is saved by 9.18%, 8.67% and 2.29%, respectively, and the total cost of the method of this embodiment is saved by 8.87%, 8.21% and 1.82%, respectively. The above two methods only use the azimuth angle between the wind turbine and the substation as the basis for division, while the method of this embodiment comprehensively considers the azimuth angle and distance between the wind turbine and the substation, making the division result more comprehensive, flexible and accurate. Compared with the genetic algorithm, in the offshore wind farm systems of 20, 30 and 42 wind turbines, the investment cost of the method of this embodiment saved 4.77%, 3.56% and 0.73% respectively, and the total cost of the method of this embodiment saved 4.56%, 3.50% and 0.69% respectively. Compared with the above-mentioned genetic algorithm, the method of this embodiment not only considers that the connecting cables between substations and the bilateral ring network cables will not cross, but also the path design planning is more stable and the calculation time is shorter. It can be seen that the planning cost of the method of this embodiment is close to the global optimal solution obtained by the mathematical programming method, and the planning calculation time of the method of this embodiment is much lower than that of the mathematical programming method, which can be regarded as an obvious advantage of the method of this embodiment. It is worth mentioning that in an offshore wind farm system with 30 wind turbines, the operating cost of the method of this embodiment saves 3.25% compared with the global optimal solution obtained by the mathematical programming method. In an offshore wind farm system with 42 wind turbines, the operating cost of the method of this embodiment saves 1.18% compared with the global optimal solution obtained by the mathematical programming method. The total cost of the method of this embodiment saves 0.06% compared with the global optimal solution obtained by the mathematical programming method. At this time, the method of this embodiment is close to the global optimal solution obtained by the mathematical programming method, and some indicators are better than the results of the mathematical programming method.

[0040] In summary, due to the high reliability of the bilateral ring network topology, it is widely used in the collection system of offshore wind farms. The current study considers how to ensure the high reliability of the collection system of offshore wind farms while minimizing the investment cost and operating loss of the designed collection system, which has become a key technical problem that needs to be solved urgently. Therefore, the method of this embodiment discloses a two-layer multi-objective planning scheme for the bilateral ring network collection system of an offshore wind farm. The method of this embodiment designs a two-layer planning model for the bilateral ring network collection system of an offshore wind farm. In the outer genetic algorithm model, different weights and cluster numbers are input into the inner layer to obtain the corresponding bilateral ring network design situation, and the population is iterated to obtain the final optimal solution. In the inner improved clustering model, the line connecting the offshore transformer and the onshore transformer is used as the 0-degree dividing line, and the direction angle and distance are used as clustering indicators. Fuzzy clustering models under different target weights and cluster numbers are constructed to group wind turbines. In the inner path planning model, the objective function is to minimize the cable investment cost and the network loss, and constraints are added. The solver is used to perform path planning for each wind turbine group, and the wind farm topology and total cost are output to the outer model. After the outer model obtains the total cost of the bilateral ring network collection system under different populations, it repeats the above steps through operations such as population selection, crossover, and mutation until the optimal solution for the planning of the bilateral ring network collection system of the offshore wind farm is obtained. The method of this embodiment can not only prevent the crossing of cables between bilateral ring networks, but also avoid the crossing of cables between offshore transformers and onshore transformers with bilateral ring network cables. At the same time, it spontaneously clusters wind turbines through a heuristic algorithm and finds the optimal path for its bilateral ring network, thereby realizing accurate planning of the bilateral ring network collection system of the offshore wind farm.

[0041] In addition, this embodiment also provides a double-layer multi-objective planning system for a bilateral ring network collection system of an offshore wind farm, comprising an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm.

[0042] In addition, this embodiment also provides a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is programmed or configured to execute the double-layer multi-objective planning method of the bilateral ring network collection system of the offshore wind farm through a processor.

[0043] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the double-layer multi-objective planning method for the bilateral ring network collection system of the offshore wind farm through a processor.

[0044] Those skilled in the art should understand that the technical solutions provided by the embodiments of the present invention may be in the form of methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that instructions executed by the processor of a computer or other programmable data processing device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0045] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A double-layer multi-objective planning method for a bilateral ring network collection system of an offshore wind farm, characterized in that: The method comprises the following steps: obtaining wind farm data of an offshore wind farm; inputting the wind farm data into a double-layer planning model of a bilateral ring network power collection system, wherein the double-layer planning model of the bilateral ring network power collection system comprises an outer model and an inner model, wherein the outer model is used to initially construct a weighted ω and the number of clusters k The multiple two-dimensional populations formed are input into the inner layer model, and the inner layer model is used to use the direction angle and distance of the wind farm as clustering indicators and adopt a clustering algorithm to perform different weights ω and the number of clusters k The wind turbine groups are grouped under the condition of minimum cable investment cost and minimum network loss as the objective function and constraints are added to build a path optimization model to plan the path for the wind turbine groups. The solver is used to solve the topological structure of the bilateral ring network collection system and the total cost composed of the value of its objective function, which is output to the outer model. When the total cost converges, the outer model outputs the optimal topological structure of the bilateral ring network collection system and its corresponding total cost. Otherwise, the current two-dimensional population is selected, crossed and mutated based on the genetic algorithm to update the two-dimensional population and input it into the inner model to continue iterating until the total cost converges.

2. The double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm according to claim 1 is characterized in that: When the initial construction consists of multiple two-dimensional populations consisting of weights and cluster numbers, the weights ω is a random value in the interval [0,1], the number of clusters k The value is in the interval [ K , K +2], where K is the minimum number of bilateral ring networks contained in the collection system. The calculation function expression of the minimum number of bilateral ring networks contained in the collection system is: ， ， Among them, ceil is the upward rounding function, and fix is ​​the downward rounding function. N is the total number of wind turbines in the wind farm, nwt To accurately consider the maximum number of wind turbines that can be included in a single bilateral ring network when cable redundancy is taken into account, cable is the cable capacity between wind turbines connected to the offshore substation in a single bilateral ring network, swt The capacity of a single fan.

3. The double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm according to claim 1 is characterized in that: The wind farm direction angle and distance are used as clustering indicators and clustering algorithms are used to perform different weightings. ω and the number of clusters k The clustering algorithm used when grouping wind turbine groups under the condition is an improved fuzzy clustering algorithm. The clustering objective of the improved fuzzy clustering algorithm is to find the value of the clustering objective function shown in the following formula to be minimized: ， ， in, is the clustering objective function, N is the total number of wind turbines in the wind farm, is the number of clusters, For fans Cluster Center The membership degree of m is the index of the membership matrix formed by the membership degree, For fans To cluster center The comprehensive distance considering the direction angle and distance, is the coordinate of the i-th wind turbine, is the jth cluster center, and: ， ， ， in, is the comprehensive distance coefficient, ω is the weight, is the azimuth angle of the wind turbine and cluster center azimuth The difference, is the absolute distance between the i-th wind turbine and the j-th cluster center, r is the distance constant, ε is the length factor, For fans To cluster center The comprehensive distance considering the direction angle and distance, For the p Cluster centers.

4. The double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm according to claim 3 is characterized in that: The calculation function expression of the distance constant is: ； The wind turbine azimuth and cluster center azimuth The calculation function expression of the difference is: ， The calculation function expression of the absolute distance between the i-th wind turbine and the j-th cluster center is: The calculation function expression of the comprehensive distance coefficient is: in, and are the comprehensive distance coefficients at time t and time t-1, is the sum of the capacities of all fans in the jth ring network, is the maximum allowed capacity of the jth ring network.

5. The double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm according to claim 1 is characterized in that: When the objective function is to minimize the cable investment cost and the network loss and to add constraints to construct a path optimization model to plan the path for the wind turbine group, the function expression of the constructed objective function is: ， ， ， ， In the above formula, is the objective function, is the cost of medium voltage submarine cable, The power loss cost of medium voltage submarine cable transmission; is a binary decision variable A set of binary decision variables Indicates whether node i and node j are connected by A The level cable is connected, the value is 1 when connected, otherwise it is 0; For medium voltage cable assembly, is the set of wind turbine nodes, A collection of time nodes for a year. for A Unit price of grade cable, is the cable length between nodes ij, Indicates the total service life of the cable in years, is the cable power loss cost for one year, is the annual inflation rate of energy prices, ep For energy prices, Indicates that A The power loss cost between nodes i and j connected by the level cable in time period h.

6. The double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm according to claim 4 is characterized in that: When the objective function is to minimize the cable investment cost and the network loss and to add constraints to construct a path optimization model to plan the path for the wind turbine group, the function expression of the constraints added is: ， ， ， ， ， ， ， in, and is a binary decision variable, Indicates whether node i is connected to node j by a cable, Indicates whether node j is connected to node i through a cable. If so, the value is 1, otherwise, it is 0. is the set of wind turbine nodes, , and are the active power, reactive power and voltage at node i respectively, is the voltage at node j, , are the conductance and susceptance values ​​between nodes i and j, respectively. is the azimuth difference between nodes i and j, , , , are the minimum voltage, maximum voltage, minimum azimuth angle and maximum azimuth angle at node i respectively. , The flow between nodes i and j is A The current of the graded cable and its maximum value.

7. The double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm according to claim 1 is characterized in that: The total cost convergence means that the total cost is less than a preset value or the number of iterations is equal to a preset maximum number of iterations.

8. A double-layer multi-objective planning system for a bilateral ring network collection system of an offshore wind farm, comprising an interconnected microprocessor and a memory, characterized in that: The microprocessor is programmed or configured to execute the double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm as described in any one of claims 1 to 7 through a processor.

10. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the double-layer multi-objective planning method for the bilateral ring network collection system of an offshore wind farm as described in any one of claims 1 to 7 through a processor.

Images