Current collection system topology optimization method and system based on particle swarm genetic hybrid algorithm

Abstract

The invention relates to the technical field of new energy power generation, and particularly discloses a power collection system topology optimization method and system based on a particle swarm genetic hybrid algorithm, and the method comprises the steps: building a target function of power collection system topology optimization with the minimum life cycle cost as a target, taking submarine cable current-carrying capacity constraint, the number of fans connected with submarine cables and submarine cable overlapping as constraint conditions, and obtaining a mathematical model of the topological structure of the current collection system of the offshore wind plant; solving the mathematical model by using a self-adaptive particle swarm genetic hybrid algorithm to obtain an optimal topological structure of the current collection system; according to the method, an adaptive particle swarm genetic hybrid algorithm is adopted during model solving, a hybrid coding mode is adopted for coding, the reciprocal of the square of the whole life cycle cost is selected as a fitness function to highlight the difference between individuals, and obtained result decoding is not only an economically optimal topological scheme, but also can visually and clearly represent a topological structure.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy power generation, and in particular to a method and system for optimizing the topology of a power collection system based on a particle swarm genetic hybrid algorithm. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Wind power generation is a way to convert wind energy into electrical energy. Compared with land-based wind power, offshore wind power has more abundant and stable wind resources, low carbon and environmental protection, and saves land occupation area. Offshore wind power has developed rapidly in recent years and is gradually becoming the future development direction of wind power. Offshore wind farms are mainly composed of three parts: wind turbines, power collection systems, and transmission systems. The power collection system is the connection between the wind turbines and the transmission system. The optimized design of this part has a vital impact on the economy and reliability of offshore wind farm operations. The electrical equipment of the power collection system is numerous and complex, and its economic construction cost accounts for a large proportion of the construction of offshore wind farms. Compared with land-based wind farms, the offshore environment is more severe and its operation and maintenance costs are higher.

[0004] Once a failure occurs in the power collection system, it may cause large-scale power loss in the entire wind farm, thus affecting economic benefits. For offshore wind farms that have been sited, once the model of wind turbines is selected, the investment cost of the wind turbines is relatively fixed. If you want to save economic costs, starting from the line topology of the power collection system will have more flexibility. Optimizing the line topology can reduce the economic cost of offshore wind farms and effectively improve the efficiency of system operation. The topology optimization problem of offshore wind power collection systems usually takes economy and reliability as objective functions.

[0005] The topology optimization problem of the collector system is a multidimensional nonlinear optimization problem. Existing methods mostly use intelligent optimization algorithms such as genetic algorithms, ant colony algorithms, fuzzy clustering algorithms, or graph theory-based algorithms such as DMST algorithms and Dijkstra algorithms to solve it. However, the above intelligent optimization algorithms are relatively lacking in optimization and convergence effects; for example: genetic algorithms are easily affected by the initial population and parameter settings, thus deviating from the optimal solution direction or converging prematurely; ant colony algorithms are easily trapped in local optimality and converge slowly due to the limitations of pheromone update strategies; fuzzy clustering algorithms are difficult to select cluster centers and determine membership functions; graph theory-based algorithms have limited assumptions on network structure, high complexity, single-source shortest paths, and poor dynamic adaptability, and their optimization and convergence effects are relatively lacking. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a collection system topology optimization method and system based on a particle swarm genetic hybrid algorithm, taking the full life cycle cost as the objective function, and introducing the current carrying capacity of the submarine cable, the number of wind turbine connections, and the intersection of the submarine cables as constraints. When solving the target, an adaptive particle swarm genetic hybrid algorithm is introduced to find the optimal parameters, and a hybrid coding is used to represent the connection status and position of the wind turbine. A suitable fitness function is selected, and its genetic operator design and dynamic update mechanism are used. The decoding result is not only the economically optimal topological solution, but also can intuitively and clearly represent the topological structure.

[0007] In some embodiments, the following technical solutions are adopted: A method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm, comprising: With the goal of minimizing the life cycle cost, the objective function of the topology optimization of the power collection system is established. At the same time, the current carrying capacity constraint of the submarine cable, the number of wind turbines connected to the submarine cable and the overlap of the submarine cable are considered as constraints, and the mathematical model of the topology structure of the power collection system of the offshore wind farm is obtained. The mathematical model is solved by using an adaptive particle swarm genetic hybrid algorithm to obtain the optimal topological structure of the power collection system; The process of solving the mathematical model using the adaptive particle swarm genetic hybrid algorithm is specifically as follows: The topological structure of the power collection system is encoded using a hybrid coding method, and the initial population is randomly generated to represent different topological structures, and each topological structure represents an individual; a fitness function is designed to evaluate the fitness of each individual, and the current optimal solution of the group is updated and recorded; Individuals in the current population are taken as particles, and the adaptive weighted particle swarm algorithm is used to iteratively update the particles. During the search process, the particles record the optimal position they have experienced and then obtain the current individual optimal solution of each particle. All the updated individual optimal solutions are taken as the new population, and genetic operations are performed to generate a new generation of individuals. The fitness values ​​of the new generation of individuals are calculated and ranked together with the fitness values ​​of the current group optimal solution to obtain a new group optimal solution. The process is repeated until the termination condition is met, and the global group optimal solution is obtained and decoded, thereby obtaining the optimal topological structure of the collector system.

[0008] As a further solution, the objective function of the topology optimization of the power collection system is established with the goal of minimizing the life cycle cost. Specifically, it is: ; in, is the total life cycle cost, For the equipment procurement and construction costs in the infrastructure phase, The operating cost of the operation phase , Maintenance cost and power outage loss costs The sum of Cost of equipment disposal for the recovery phase; is the discount factor.

[0009] As a further solution, the current carrying capacity constraint of the submarine cable is specifically: ; in, is the maximum continuous load current flowing through a certain section of submarine cable, is the total correction factor for the allowable current carrying capacity of the submarine cable, The current carrying capacity of the submarine cable.

[0010] As a further solution, the number of wind turbines connected to the submarine cable is specifically constrained as follows: ; ; in, is the number of wind turbines connected to a single submarine cable, is the maximum number of wind turbines that can be connected to the submarine cable, is the floor function, is the maximum wind turbine capacity that the submarine cable can bear. is the rated capacity of a single fan.

[0011] As a further solution, the submarine cable overlap constraint is specifically: ; in, , They represent two sections of submarine cables between four wind turbines. For point , and The cross product of .

[0012] As a further solution, a hybrid coding method is used to encode the topological structure of the power collection system, specifically: The connection relationship between the collector cable and the wind turbine is represented by a binary bit, 1 represents connection, and 0 represents disconnection; the connection mode between each wind turbine and the cable corresponds to a binary bit as the connection code; The position of the wind turbine is represented by a real value, the position of each wind turbine is represented by a two-dimensional coordinate, and the real number code obtained by sequentially combining the positions of all wind turbines is used as the position code; The connection code and the position code are combined into one entity to represent a topological structure of the collector system.

[0013] As a further solution, a fitness function is designed to evaluate the fitness of each individual, and the fitness function is specifically: ; in, The total life cycle cost.

[0014] In other embodiments, the following technical solutions are adopted: A collector system topology optimization system based on a particle swarm genetic hybrid algorithm, comprising: The model building module is used to establish the objective function of the topology optimization of the power collection system with the goal of minimizing the whole life cycle cost, and to obtain the mathematical model of the topology structure of the power collection system of the offshore wind farm by considering the current carrying capacity constraint of the submarine cable, the number of wind turbines connected to the submarine cable and the overlap of the submarine cable as constraints; A model solving module, used for solving the mathematical model using an adaptive particle swarm genetic hybrid algorithm to obtain an optimal topological structure of the power collection system; The process of solving the mathematical model using the adaptive particle swarm genetic hybrid algorithm is specifically as follows: The topological structure of the power collection system is encoded using a hybrid coding method, and the initial population is randomly generated to represent different topological structures, and each topological structure represents an individual; a fitness function is designed to evaluate the fitness of each individual, and the current optimal solution of the group is updated and recorded; Individuals in the current population are taken as particles, and the adaptive weighted particle swarm algorithm is used to iteratively update the particles. During the search process, the particles record the optimal position they have experienced and then obtain the current individual optimal solution of each particle. All the updated individual optimal solutions are taken as the new population, and genetic operations are performed to generate a new generation of individuals. The fitness values ​​of the new generation of individuals are calculated and ranked together with the fitness values ​​of the current group optimal solution to obtain a new group optimal solution. The process is repeated until the termination condition is met, and the global group optimal solution is obtained and decoded, thereby obtaining the optimal topological structure of the collector system.

[0015] In other embodiments, the following technical solutions are adopted: A terminal device includes a processor and a memory, wherein the processor is used to implement instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the above-mentioned particle swarm genetic hybrid algorithm-based power collection system topology optimization method.

[0016] In other embodiments, the following technical solutions are adopted: A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned collector system topology optimization method based on a particle swarm genetic hybrid algorithm.

[0017] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention comprehensively considers the equipment procurement and construction cost, operation cost, maintenance cost, power outage loss cost and equipment handling cost of the power collection system during the entire life cycle of the offshore wind farm, and constructs an objective function with the goal of minimizing the entire life cycle cost. At the same time, the constraint condition of the intersection of submarine cables is specially considered. By introducing an intersection detection algorithm to detect and judge whether there is an intersection between submarine cables, the existence of intersections in the planned submarine cable topology can be avoided, the probability of failure caused by physical damage caused by the intersection of submarine cables can be reduced, the electromagnetic interference caused by the intersection of submarine cables can be reduced, the power loss can be reduced, the stability of power transmission can be ensured, and the system reliability can be improved; at the same time, the maintenance cost and repair complexity caused by the intersection of submarine cables can be reduced.

[0018] (2) The present invention adopts an adaptive particle swarm genetic hybrid algorithm when solving the model, and adopts a hybrid coding method for coding. The inverse of the square of the life cycle cost is selected as the fitness function to highlight the differences between individuals. The adaptive particle swarm algorithm is combined for dynamic optimization, and the genetic operator is designed to increase the population diversity until the algorithm terminates. The optimal solution obtained is the optimal topological structure of the power collection system. The algorithm combines the advantages of the genetic algorithm and the adaptive particle swarm algorithm, and the results obtained by the hybrid coding method can accurately represent the connection status and location information between each wind turbine, and can intuitively and clearly represent the topological structure under the economically optimal topological scheme.

[0019] Other features and advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm in an embodiment of the present invention; Figure 2 Schematic diagram of the solution process of the adaptive particle swarm genetic hybrid algorithm in an embodiment of the present invention; Figure 3 Schematic diagram of calculation of condition 1 in the design principle of genetic selection operator in an embodiment of the present invention; Figure 4 Schematic diagram of calculation of condition 2 in the design principle of genetic selection operator in an embodiment of the present invention; Figure 5 A wind turbine location distribution diagram of a wind farm in an embodiment of the present invention; Figure 6 This is the optimal topological structure diagram of a wind turbine in a wind farm in an example of the present invention. DETAILED DESCRIPTION

[0021] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0022] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0023] Embodiment 1 In one or more embodiments, a method for optimizing a power collection system topology based on a particle swarm genetic hybrid algorithm is disclosed, which specifically includes the following process: (1) With the goal of minimizing the life cycle cost, the objective function of the topology optimization of the power collection system is established. At the same time, the current carrying capacity constraint of the submarine cable, the number of wind turbines connected to the submarine cable, and the overlap of the submarine cable are considered as constraints, and the mathematical model of the topological structure of the power collection system of the offshore wind farm is obtained; (2) An adaptive particle swarm genetic hybrid algorithm is used to solve the mathematical model and obtain the optimal topological structure of the power collection system.

[0024] The process of solving the mathematical model using the adaptive particle swarm genetic hybrid algorithm is specifically as follows: The topological structure of the power collection system is encoded using a hybrid coding method, and the initial population is randomly generated to represent different topological structures, and each topological structure represents an individual; a fitness function is designed to evaluate the fitness of each individual, and the current optimal solution of the group is updated and recorded; Individuals in the current population are taken as particles, and the adaptive weighted particle swarm algorithm is used to iteratively update the particles. During the search process, the particles record the optimal position they have experienced and then obtain the current individual optimal solution of each particle. All the updated individual optimal solutions are taken as the new population, and genetic operations are performed to generate a new generation of individuals. The fitness values ​​of the new generation of individuals are calculated and ranked together with the fitness values ​​of the current group optimal solution to obtain a new group optimal solution. The process is repeated until the termination condition is met, and the global group optimal solution is obtained and decoded, thereby obtaining the optimal topological structure of the collector system.

[0025] As a specific implementation method, Figure 1 The method of this embodiment specifically includes the following process: S1: From the perspective of the whole life cycle cost, define the objective function of the collector system topology optimization: The life of an offshore wind farm is generally 25 years. , taking into account its 25-year operating life and various costs during the operating cycle, such as equipment procurement and construction costs in the infrastructure phase, operating costs, maintenance costs and power outage loss costs in the operation phase, and equipment processing costs in the recovery phase.

[0026] S11: Definition The calculation formula for equipment procurement and construction costs in the infrastructure phase is: ; in, is the total number of different types of submarine cables, For the i The total number of submarine cables of various types, For the i Model No. j Length of submarine cable, For the i The unit purchase cost of each type of submarine cable equipment, For the i Unit construction costs of various types of submarine cable equipment.

[0027] S12: Definition The operating cost of the operation phase , Maintenance cost and power outage loss costs The sum of is calculated as: ; The operating cost is ; For the i The working current of the submarine cable of this type, For the i The resistance per unit length of the submarine cable of the following types: The on-grid electricity price for offshore wind power is 0.75 yuan / , The annual unit sea area usage fee for the sea area where the offshore wind farm is located. The total sea area used for offshore wind farms.

[0028] Maintenance costs ; For the i Number of failures of different types of submarine cables in a year, For the i The cost of a single repair of a submarine cable of this type is different due to the different types of faults. Expressed as annual expected value.

[0029] The power outage loss cost is , 8760 per year h , For the i The probability of failure of the submarine cable of the type For the i Model No. The number of wind turbines connected to each submarine cable, is the average power of the fan, for The probability of a typhoon turbine outage.

[0030] S13: Definition The equipment processing cost in the recovery phase is calculated as follows: ; The main cost of the vessel and manpower loading and unloading is the recycling process. Since the material of the submarine cable conductor and other equipment is metal, it has a certain recycling value. The value of secondary use after recycling.

[0031] However, the value of the secondary use of the equipment after recycling is not high, and the infrastructure construction stage also requires ships and labor costs to lay submarine cables and other equipment. The equipment processing cost of the recycling stage in this embodiment is This can be offset by the cost of ships and manpower required during the infrastructure construction phase. .

[0032] S14: The objective function of the topology optimization of the power collection system is: ; in, is the life cycle cost, and the discount factor , r The discount rate is taken as 8%.

[0033] S2: Considering the implementation methods of cable connections in actual operation, defining the constraints of the topology optimization problem and establishing a mathematical model of the topology of the offshore wind farm: Considering the actual operation situation, the constraints for the topology optimization of the power collection system mainly include the current carrying capacity constraint of the submarine cable, the number of wind turbines connected to the submarine cable, and the submarine cable overlap constraint.

[0034] S21: Considering the current carrying capacity constraint of submarine cables, it can be expressed as: ; in, is the maximum continuous load current flowing through a certain section of submarine cable, is the total correction factor for the allowable current carrying capacity of the submarine cable, The current carrying capacity of the submarine cable.

[0035] S22: When designing the topology of the power collection system, the number of wind turbines connected to a single submarine cable is limited by the current carrying capacity of the submarine cable. When connecting the submarine cable, it should be ensured that the number of wind turbines connected to a single submarine cable does not exceed the maximum number of wind turbines that can be connected to the submarine cable, which can be expressed as: ; ; in, is the number of wind turbines connected to a single submarine cable, is the maximum number of wind turbines that can be connected to the submarine cable, is the floor function, is the maximum wind turbine capacity that the submarine cable can bear. is the rated capacity of a single fan.

[0036] S23: In order to avoid the situation where the submarine cables connecting the wind turbines intersect in the planned topological structure of the submarine cables, this embodiment detects and determines whether the submarine cables intersect based on the given wind turbine data. Specifically, the position of the wind turbine is regarded as the coordinate of the midpoint of the coordinate system, and the submarine cable connecting the two wind turbines is regarded as a line segment, and it is determined whether the two line segments intersect.

[0037] Assume that the coordinates of the four points corresponding to the four wind turbines are , , , , Indicated by point and is a line segment with endpoints, Indicated by point and The endpoints of a line segment.

[0038] Condition 1: Vector , Located in vector The left and right sides; Condition 2: Vector , Located in vector The left and right sides; When both conditions 1 and 2 are met, the line segment can be determined and line segments intersect.

[0039] To determine the position of a vector relative to another vector, the specific process is as follows: Vector and vector For example, point , , The cross product formula is: If the vector Cross product vector The result is greater than 0. , then the vector In vector on the left; if , then the vector In vector on the right side; if , then the vector With vector Parallel. The calculation diagram of condition 1 is as follows Figure 3 As shown, the calculation diagram of condition 2 is as follows Figure 4 shown.

[0040] The wind turbine coordinates are used to determine whether there is an intersection between submarine cables. The constraints are: ; in, , Indicates two sections of submarine cables between four wind turbines. For point , , The cross product of .

[0041] S23: The comprehensive offshore wind farm power collection system takes the lowest economic index LCC as the goal, and the current carrying capacity of the submarine cable and the number of wind turbines connected to the submarine cable as constraints. The topology optimization model of the power collection system is established as follows: ; .

[0042] S3: Combination Figure 2 , use a hybrid coding method to encode the collector system topology and randomly generate the initial population: The hybrid coding method used in this embodiment can improve the convergence speed of the algorithm, help find the optimal solution more quickly, and at the same time enhance the expression ability of the solution, capture more features and information, thereby enhancing the search effect.

[0043] S31: The process of encoding the topology of the collector system using the hybrid encoding method is as follows: S311: Use binary bits to represent the connection relationship between the collector cable and the wind turbine, 1 means connected, 0 means not connected. Typhoon and The connection mode between each wind turbine and the submarine cable corresponds to a binary bit as the connection code, that is, the connection status of each wind turbine is represented by a binary bit with a length of For example, if there are 5 wind turbines and 3 power collection cables, the connection mode of wind turbine 1 is 101 (a binary string of length 3), indicating that wind turbine 1 is connected to power collection cable 1 and power collection cable 3, but not to power collection cable 2.

[0044] S312: Use real values ​​to represent the position of wind turbines, and use coordinates to represent the position of each wind turbine, that is, use a two-dimensional coordinate system Indicates the position of each fan. After encoding, each fan position is represented by a real number array of length 2 as the position code; the first element represents the position of the fan on the x-axis, and the second element represents the position of the fan on the y-axis. For example: if there are 3 fan positions with coordinates of , , , the real number encoding obtained by combining the positions of all fans in sequence is This encoding method can intuitively represent the location distribution of the fans and flexibly adjust the locations during the optimization process.

[0045] S32: Combine the connection code and the position code into an individual, where an individual contains both the connection information and the position information, and randomly generate an initialized population to represent different topological structures.

[0046] S4: Design a fitness function to evaluate each individual and update the current optimal solution: The fitness function is a function that evaluates the quality of individuals in the algorithm iteration. The higher the function value of the individual, that is, the higher the fitness score, the higher the quality of the solution, the easier it is to be selected for reproduction and its traits will appear in the next generation, producing better offspring. As the algorithm iterates, the quality of the solution will improve and the fitness will increase until the optimal solution is found.

[0047] S41: This embodiment aims to find the topology optimization solution that minimizes the life cycle cost of the power collection system, that is, the most economically optimal solution. The lower the life cycle cost corresponding to the individual, the higher the fitness, and the higher the quality of the solution corresponding to the individual. The two are negatively correlated, so the reciprocal is selected and then squared. The square can make the fitness difference corresponding to different solutions more obvious, which is convenient for further screening. Therefore, the reciprocal of the square of the life cycle cost is selected as the fitness function, which can better show the differences between individuals and can be expressed as: ; S42: According to the defined fitness function, the fitness value of each individual is calculated, and the fitness value of each individual is sorted to obtain the current optimal solution.

[0048] S43: The algorithm termination condition can be set as: when the error of each individual fitness is within the 2% error band, the algorithm terminates.

[0049] S44: If the current optimal solution of the algorithm is the optimal solution among the group optimal solution and the individual optimal solution, determine whether the algorithm meets the termination condition. If not, proceed to the next step. If so, output the current optimal solution as the global optimal solution to step S7. Otherwise, collect the current optimal solution and proceed to the next step.

[0050] S5: Using the idea of ​​adaptive particle swarm algorithm, update the speed and position of each particle to find the optimal solution: The dynamic update mechanism of the particle swarm algorithm can be used to improve search efficiency. This embodiment adopts an adaptive particle swarm optimization algorithm. The position of each particle represents a potential solution, that is, a topological solution. The individuals in the population in the above steps can be replaced by the positions of particles in this step. The individual optimal solution mentioned in the above steps enables the particles to perform local fine search around their own former optimal positions. The group optimal solution attracts particles to move in the optimal direction of the entire group, avoiding particles from falling into local optimality excessively. The continuous update and optimization of the individual optimal solution may discover new and better topological structures, thereby promoting the update of the group optimal solution and finding the global optimal solution.

[0051] The specific process is as follows: S51: Adopting adaptive weighted particle swarm algorithm, the iteration formula of the algorithm is: ; ; in: is the velocity of the particle, is the position of the particle, The inertia weight is used for dynamic adjustment. and is the learning factor, and A random number is used to increase randomness. is the optimal position of the particle, i.e., the individual optimal solution, is the global optimal position of the particle, i.e. the global optimal solution.

[0052] S511: Initialize the speed and position of each particle; S512: Initialize parameters, including inertia weight , learning factor and , the number of algorithm iterations ; S513: In each iteration, the new velocity and new position of the particle are calculated; S514: Dynamically adjust the inertia weight according to the change of the particle objective function value , used to increase or decrease search capabilities.

[0053] S52: Repeat the current step and record the currently obtained individual optimal solution.

[0054] S6: Take the updated optimal solutions of all individuals as the new population and perform genetic operations to generate a new generation of individuals: The updated positions of all particles, i.e., all individual optimal solutions, are considered as a new population. Assume that the population size is , perform selection, crossover and mutation operations on the population.

[0055] S61: Initialize the crossover probability of the hybrid algorithm , , , mutation probability ; S62: Design a selection operator, the purpose of which is to directly pass on the optimized individuals to the next generation or to generate new individuals through crossover and pass them on to the next generation. Calculate the fitness values ​​corresponding to all individuals in the initial population and arrange all fitness values ​​in descending order; Specifically, the selection operator used in the present invention is an exponential sorting method, which sorts individuals from high to low according to their fitness values, and then distributes the selection probability through an exponential function, so that individuals with high fitness have a higher probability of being selected, while individuals with low fitness have a certain chance of survival. ( ) individuals used for reproduction and producing the next generation are called parent individuals.

[0056] S621: Calculate the fitness value of each individual in the new population, and sort all individuals in the population from high to low according to fitness. The sorted sequence is ,in It is the individual with the highest fitness in the population.

[0057] S622: Calculate the selection probability using the index ranking method. For individuals The fitness value of , To adjust the parameters used to control the selected pressure, The larger the value, the greater the selection pressure, and the greater the probability that individuals with high fitness will be selected. The corresponding selection probability The calculation formula is Obviously, the higher the individual's fitness, the higher its corresponding The larger the value, the The larger the proportion of the total, the greater the individual The corresponding selection probability The higher.

[0058] S623: Use roulette wheel selection method to perform selection operation. The corresponding cumulative selection probability is , initially . Generate a random number in the interval [0,1] ,when When, individual is selected and copied to the next generation population. Repeat the above steps until Each time an individual is selected and copied to the next generation population, a random number needs to be regenerated to ensure that each individual has the opportunity to be selected according to its selection probability in each selection round. Each time an individual is selected and copied to the new population, the final population contains The next generation of individuals.

[0059] S63: Design a crossover operator, the purpose of which is to preserve the characteristic information of the parent individuals and increase population diversity, thus promoting population evolution; The present invention selects an adaptive crossover probability formula and adjusts the crossover probability according to the relative size of individual fitness, so that individuals with high fitness can cross over with a lower probability to protect excellent genes, while individuals with low fitness can cross over with a higher probability to increase their chances of improvement. For individuals The fitness value of is the average fitness of the population, and the adjustment formula of the adaptive crossover probability is as follows: are all constants: ; This crossover operator can retain the relevant characteristics of the parent generation and optimize the genetic process.

[0060] S64: Design mutation operators to randomly change the genes of some individuals. The purpose is to introduce new genetic information, prevent premature convergence and help the algorithm escape from the local optimal solution. The present invention adopts a variation mode of basic bit variation, randomly selects two gene bits for the binary part of an individual, performs an inversion operation on them, and changes 0 in the binary code to 1, and 1 to 0.

[0061] S641: Randomly generate a random number in the interval [0,1] ,like , then proceed to the next mutation operation; if , no mutation operation is performed, and jump to step S65.

[0062] S642: The number of wind turbines in the wind farm is h , the length of the individual binary code is h, randomly select interval Integer d As a mutation bit, the coded value of the position is reversed. In the binary code, a gene bit is randomly selected for flipping, which increases the diversity of the population.

[0063] S65: Return to step S42 to sort the population obtained after the genetic operation, update and record the new group optimal solution, and determine whether the new group optimal solution is the global optimal solution. If so, continue to determine whether the termination condition is met. If the termination condition is met, output the current group optimal solution as the global optimal solution, and the algorithm ends; otherwise, return to step S5 and continue to execute the algorithm.

[0064] S7: Decode the obtained global optimal solution to obtain the optimal topological structure of the power collection system.

[0065] This embodiment takes a 1.5km square wind farm as an example, where 20 wind turbines are installed, one offshore booster station, and a 35KV submarine cable is selected to draw a wind turbine distribution diagram according to the wind turbine location distribution. Figure 5 As shown, the adaptive particle swarm genetic hybrid algorithm of the present invention is used for debugging, and the result of the fan connection is:

[0066] The decoding results in an optimal topology structure under the constraints of current carrying capacity, number of wind turbine connections, and intersection of submarine cables. Figure 6 shown.

[0067] The method of this embodiment considers the full life cycle cost as the objective function, the current carrying capacity of the submarine cable, the number of wind turbine connections, and the intersection constraints of the submarine cable, and then considers the topological structure of the power collection system and establishes the objective function of the optimization problem. When solving, an adaptive particle swarm genetic hybrid algorithm is introduced to find the optimal parameters, hybrid coding is used to represent the connection status and location of the wind turbine, and a suitable fitness function is selected. The design and dynamic update mechanism of its genetic operator are used to obtain the decoding result, which is not only the most economically optimal topological solution, but also can intuitively and clearly represent the topological structure.

[0068] Embodiment 2 In one or more embodiments, a system for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm is disclosed, comprising: The model building module is used to establish the objective function of the topology optimization of the power collection system with the goal of minimizing the whole life cycle cost, and to obtain the mathematical model of the topology structure of the power collection system of the offshore wind farm by considering the current carrying capacity constraint of the submarine cable, the number of wind turbines connected to the submarine cable and the overlap of the submarine cable as constraints; A model solving module, used for solving the mathematical model using an adaptive particle swarm genetic hybrid algorithm to obtain an optimal topological structure of the power collection system; The process of solving the mathematical model using the adaptive particle swarm genetic hybrid algorithm is specifically as follows: The topological structure of the power collection system is encoded using a hybrid coding method, and the initial population is randomly generated to represent different topological structures, and each topological structure represents an individual; a fitness function is designed to evaluate the fitness of each individual, and the current optimal solution of the group is updated and recorded; Individuals in the current population are taken as particles, and the adaptive weighted particle swarm algorithm is used to iteratively update the particles. During the search process, the particles record the optimal position they have experienced and then obtain the current individual optimal solution of each particle. All the updated individual optimal solutions are taken as the new population, and genetic operations are performed to generate a new generation of individuals. The fitness values ​​of the new generation of individuals are calculated and ranked together with the fitness values ​​of the current group optimal solution to obtain a new group optimal solution. The process is repeated until the termination condition is met, and the global group optimal solution is obtained and decoded, thereby obtaining the optimal topological structure of the collector system.

[0069] It should be noted that the specific implementation method of the above modules is the same as that in Example 1 and will not be described in detail.

[0070] Embodiment 3 In one or more embodiments, a terminal device is disclosed, which includes a processor and a memory, the processor is used to implement instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the collection system topology optimization method based on the particle swarm genetic hybrid algorithm described in Example 1.

[0071] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0072] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0073] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.

[0074] Embodiment 4 In one or more embodiments, a computer-readable storage medium is disclosed, in which a plurality of instructions are stored, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the collector system topology optimization method based on a particle swarm genetic hybrid algorithm described in Example 1.

[0075] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm, characterized in that: include: With the goal of minimizing the life cycle cost, the objective function of the topology optimization of the power collection system is established. At the same time, the current carrying capacity constraint of the submarine cable, the number of wind turbines connected to the submarine cable and the overlap of the submarine cable are considered as constraints, and the mathematical model of the topology structure of the power collection system of the offshore wind farm is obtained. The mathematical model is solved by using an adaptive particle swarm genetic hybrid algorithm to obtain the optimal topological structure of the power collection system; The process of solving the mathematical model using the adaptive particle swarm genetic hybrid algorithm is specifically as follows: The topological structure of the power collection system is encoded using a hybrid coding method, and the initial population is randomly generated to represent different topological structures, and each topological structure represents an individual; a fitness function is designed to evaluate the fitness of each individual, and the current optimal solution of the group is updated and recorded; The individuals in the current population are taken as particles, and the particles are iteratively updated using the adaptive weighted particle swarm algorithm. During the search process, the particles record the optimal position they have experienced, and then obtain the current individual optimal solution of each particle. The updated optimal solutions of all individuals are taken as the new population, and genetic operations are performed to generate a new generation of individuals. The fitness values ​​of the new generation of individuals are calculated and ranked together with the fitness values ​​of the current group optimal solution to obtain a new group optimal solution. The process is repeated until the termination condition is met, and the global group optimal solution is obtained and decoded, thereby obtaining the optimal topological structure of the power collection system.

2. A method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm as claimed in claim 1, characterized in that: With the goal of minimizing the life cycle cost, the objective function of the topology optimization of the power collection system is established, which is as follows: ； in, is the total life cycle cost, For the equipment procurement and construction costs in the infrastructure phase, The operating cost of the operation phase , Maintenance cost and power outage loss costs the sum of is the equipment processing cost in the recovery phase, R is the discount factor.

3. A method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm as claimed in claim 2, characterized in that: The current carrying capacity constraints of the submarine cable are specifically: ； in, is the maximum continuous load current flowing through a certain section of submarine cable, is the total correction factor for the allowable current carrying capacity of the submarine cable, The current carrying capacity of the submarine cable.

4. The method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm according to claim 2, characterized in that: The specific constraints on the number of wind turbines connected to the submarine cable are: ； ； in, is the number of wind turbines connected to a single submarine cable, is the maximum number of wind turbines that can be connected to the submarine cable, is the floor function, is the maximum wind turbine capacity that the submarine cable can bear. is the rated capacity of a single fan.

5. The method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm according to claim 2, characterized in that: The submarine cable overlap constraint is specifically: ； in, , They represent two sections of submarine cables between four wind turbines. For point , and The cross product of .

6. The method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm according to claim 1, characterized in that: The topological structure of the power collection system is encoded using a hybrid coding method, specifically: The connection relationship between the collector cable and the wind turbine is represented by a binary bit, 1 represents connection, 0 represents disconnection, and the connection mode between each wind turbine and the cable corresponds to a binary bit as the connection code; The position of the wind turbine is represented by a real value, the position of each wind turbine is represented by a two-dimensional coordinate, and the real number code obtained by sequentially combining the positions of all wind turbines is used as the position code; The connection code and the position code are combined into one entity to represent a topological structure of the collector system.

7. The method for topology optimization of a power collection system based on a particle swarm genetic hybrid algorithm according to claim 1, characterized in that: A fitness function is designed to evaluate the fitness of each individual, and the fitness function is specifically: ； in, The total life cycle cost.

8. A collector system topology optimization system based on a particle swarm genetic hybrid algorithm, characterized in that: include: The model building module is used to establish the objective function of the topology optimization of the power collection system with the goal of minimizing the whole life cycle cost, and to obtain the mathematical model of the topology structure of the power collection system of the offshore wind farm by considering the current carrying capacity constraint of the submarine cable, the number of wind turbines connected to the submarine cable and the overlap of the submarine cable as constraints; A model solving module, used for solving the mathematical model using an adaptive particle swarm genetic hybrid algorithm to obtain an optimal topological structure of the power collection system; The process of solving the mathematical model using the adaptive particle swarm genetic hybrid algorithm is specifically as follows: The topological structure of the power collection system is encoded using a hybrid coding method, and the initial population is randomly generated to represent different topological structures, and each topological structure represents an individual; a fitness function is designed to evaluate the fitness of each individual, and the current optimal solution of the group is updated and recorded; The individuals in the current population are taken as particles, and the particles are iteratively updated using the adaptive weighted particle swarm algorithm. During the search process, the particles record the optimal position they have experienced, and then obtain the current individual optimal solution of each particle. The updated optimal solutions of all individuals are taken as the new population, and genetic operations are performed to generate a new generation of individuals. The fitness values ​​of the new generation of individuals are calculated and ranked together with the fitness values ​​of the current group optimal solution to obtain a new group optimal solution. The process is repeated until the termination condition is met, and the global group optimal solution is obtained and decoded, thereby obtaining the optimal topological structure of the power collection system.

9. A terminal device, comprising a processor and a memory, wherein the processor is used to implement instructions; and the memory is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the collector system topology optimization method based on a particle swarm genetic hybrid algorithm as described in any one of claims 1-7.

10. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing the collector system topology optimization method based on a particle swarm genetic hybrid algorithm as described in any one of claims 1 to 7.

Images