Wind power plant wake flow optimization method based on particle swarm optimization algorithm

Abstract

The invention provides a wind power plant wake flow optimization method based on a particle swarm optimization algorithm, and belongs to the technical field of wind power plant wake flow optimization, and the method comprises the steps: obtaining the layout distribution data of fans in a wind field, the wind direction data in the wind field, and the wind speed data; based on the layout distribution data of the fans in the wind field, the wind direction data in the wind field and the wind speed data, the wake flow wind speed of the single fan in the wind field is calculated; modeling the wake flow effect of the whole wind power plant according to the wake flow wind speed of a single fan in the wind power plant to obtain a wake flow model of the wind power plant; based on the wind power plant wake flow model, obtaining a total active power optimization model of the wind power plant; and optimizing the total active power optimization model of the wind power plant through an improved particle swarm algorithm to obtain the total generating capacity of the optimized wind power plant. And optimizing the total active power optimization model of the wind power plant through an improved particle swarm algorithm, and maximizing the output power of the wind power plant.

Description

Technical Field

[0001] The invention belongs to the technical field of wind farm wake optimization, and in particular relates to a wind farm wake optimization method based on a particle swarm optimization algorithm. Background Art

[0002] As an important component of clean energy, wind power generation plays an indispensable role in global energy transformation and addressing climate change. With technological advances and cost reductions, wind power installed capacity has grown rapidly, which not only reflects the huge potential for the development and utilization of wind energy resources, but also highlights its important position in the power system. However, with the expansion of wind farms, the wake effect between wind turbines has become one of the main bottlenecks restricting the improvement of wind farm efficiency. The wake effect refers to the adverse effect of upstream wind turbines on downstream wind turbines. It will reduce the wind speed received by subsequent wind turbines and increase the turbulence intensity, thereby causing the output power of these wind turbines to decrease and mechanical fatigue to increase, ultimately affecting the economic benefits and service life of the entire wind farm.

[0003] In order to mitigate the impact of wake effect on wind farm performance, researchers have developed a series of optimization techniques and methods. Layout optimization adjusts the relative positions of wind turbines to minimize the negative impact of wake effect, which is suitable for new wind farms in the planning stage. Active wake control (AWC) is more suitable for wind farms that have been built and put into operation. It mainly improves the wake distribution by adjusting the operating status of wind turbines, such as yaw angle, pitch angle or speed, thereby increasing the overall output power of wind farms. Axial induction factor control (AIC) and wake redirection control (WRC) are two common AWC strategies. AIC adjusts the wake intensity by changing the axial induction factor of the wind turbine, while WRC changes the yaw angle of the wind turbine to deviate the wake from the downstream wind turbine, thereby increasing the output of the wind farm. However, traditional axial induction factor control (AIC) relies on specific model assumptions and parameter settings, and it is difficult to respond in time under actual conditions where wind speed and wind direction change frequently, resulting in limited optimization effect.

[0004] To this end, the present invention provides a wind farm wake optimization method based on a particle swarm optimization algorithm. Summary of the invention

[0005] The present invention provides a wind farm wake optimization method based on a particle swarm optimization algorithm, so as to at least solve the problem that the traditional axial induction factor control (AIC) in the prior art relies on specific model assumptions and parameter settings, and is difficult to respond in time under actual working conditions where wind speed and wind direction change frequently, resulting in limited optimization effect.

[0006] The wind farm wake optimization method comprises the following specific steps: S1: Obtaining the layout distribution data of wind turbines in the wind farm, the wind direction data in the wind farm, and the wind speed data; S2: Calculate the wake wind speed of a single wind turbine in the wind farm based on the layout distribution data of the wind turbines in the wind farm, the wind direction data in the wind farm, and the wind speed data; S3: Based on the wake wind speed of a single wind turbine in the wind farm, the wake effect of the entire wind farm is modeled to obtain the wind farm wake model; S4: Based on the wind farm wake model, the total active power optimization model of the wind farm is obtained; S5: The total active power optimization model of the wind farm is optimized by using an improved particle swarm algorithm to obtain the total power generation of the optimized wind farm.

[0007] Furthermore, the overall active power optimization model of the wind farm is optimized by using an improved particle swarm algorithm, including the following specific steps: S51: taking the fan state quantity as the particle position and randomly initializing it to generate a finite particle population; S52: Calculate the fitness of all particles and select attractors from them; S53: Update particle velocity, calculate the new position of each particle, and calculate the optimal fitness of each particle; S54: Determine whether the optimal fitness satisfies the termination condition. If so, execute step S55; if not, execute S56; S55: output result; S56: Return to continue executing step S53-step S54.

[0008] Furthermore, in S2, the Jensen wake model is used to study the wake of a single wind turbine, and its expression is:

[0009]

[0010] In the formula, is the effective input wind speed of the upstream fan; Downstream of the fan The wake wind speed at a distance of times the fan impeller diameter; is the thrust coefficient of the fan; is the wake attenuation constant; is the fan impeller diameter; Downstream of the fan The wake diameter at a distance of times the fan impeller.

[0011] Furthermore, in S3, it is assumed that in the wind farm, There are a total of The wake of the typhoon and the There is wake overlap between typhoon turbines, so the expression of the wind farm wake model is:

[0012]

[0013] In the formula, For the Wind speed of the typhoon; is the free wind speed in the wind farm; Upstream of the fan The input wind speed of the typhoon machine; Upstream of the fan The input wind speed of the typhoon is Wake wind speed at the typhoon head; For the Thrust coefficient of the typhoon turbine; For fans Impeller area; For the Typhoon and The distance of the typhoon turbine along the wind direction; is the wake overlap area, It represents an intermediate variable, which represents the difference between the input wind speed of the jth fan upstream and the downstream wind speed.

[0014] Furthermore, the expression of the wake overlap area is:

[0015] In the formula, is the radius of the wake area; is the radius of the downstream fan impeller; It is the distance between the center of the wake area and the center of the downstream fan impeller in the direction perpendicular to the wake.

[0016] Furthermore, based on the wind farm wake model, the overall active power optimization model of the wind farm is obtained, which includes the following specific steps: Calculate the wind farm The power of the typhoon is expressed as:

[0017] In the formula, For the wind farm The power of the typhoon; is the air density, For the Wind energy utilization factor of typhoon turbines; Based on the wind farm The power of the wind turbine is used to calculate the total output power of the wind farm. The expression is:

[0018] In the formula, is the total output power of the wind farm; is the number of wind turbines in the wind farm; Finally, the total active power optimization model of the wind farm is expressed as:

[0019] In the formula, is the axial induction factor; Indicates the wind farm The power of the fan, Represents the maximum value of the total output power of the wind farm in the total active power optimization model of the wind farm.

[0020] Furthermore, the wind energy utilization coefficient is related to the axial induction factor, and its expression is: ; The thrust coefficient is related to the axial induction factor, and its expression is: .

[0021] Furthermore, in S52, the fitness of all particles is calculated, and the expression of the attractor is selected from them:

[0022] In the formula, For the The attractor position generated by the update; For the The first attractor position after iterations; For the The second attractor position after iterations; For the After the iteration attractor positions; For particle The position at the iteration.

[0023] Furthermore, in S53, the expression for updating the particle velocity is:

[0024] In the formula, Representative The particle velocity at the iteration; Representative The particle velocity at the iteration; For the The weight of the iteration; is the individual learning factor; is the population learning factor; For particle The position at the iteration; is the optimal position of an individual, that is, all particles in the population are in the The particle position with the highest fitness after iterations.

[0025] Furthermore, in S53, the expression for calculating the new position of each particle is:

[0026] In the formula, For particle The position at the iteration.

[0027] It can be seen from the above technical solutions that the present invention has the following advantages: In the wind farm wake optimization method based on the particle swarm optimization algorithm provided in the present application, the total active power optimization model of the wind farm is optimized by the improved particle swarm algorithm to maximize the output power of the wind farm; The improved particle swarm algorithm can dynamically adjust the optimization strategy according to real-time wind data, ensuring continuous optimization of wind turbine operating parameters throughout the life cycle of the wind farm, maximizing the output power and economic benefits of the wind farm, and having greater adaptability and flexibility; Moreover, the algorithm enhances the global search capability and stability of the particle swarm by introducing multiple dynamic attractors and particle speed pause mechanism, and can maintain an efficient and stable optimization process even at a smaller population size, thereby improving the overall performance of the wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0029] Figure 1 It is a flow chart of the wind farm wake optimization method based on particle swarm optimization algorithm; Figure 2 Schematic diagram of three groups of ordinary particles moving toward the attractor position in the wind farm wake optimization method based on the particle swarm optimization algorithm, wherein (a) is a schematic diagram of the first group of ordinary particles moving toward the attractor position, (b) is a schematic diagram of the second group of ordinary particles moving toward the attractor position, and (c) is a schematic diagram of the third group of ordinary particles moving toward the attractor position; Figure 3 This is the flow chart of the improved particle swarm algorithm for the wind farm wake optimization method based on the particle swarm optimization algorithm. DETAILED DESCRIPTION

[0030] In the following detailed description of the wind farm wake optimization method based on the particle swarm optimization algorithm, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0031] Hereinafter, the terms "include" or "may include" used in various embodiments of the present disclosure indicate the presence of disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "include", "have", and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or a combination of the foregoing, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components, or a combination of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or a combination of the foregoing.

[0032] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0033] The expressions (such as "first", "second", etc.) used in the various embodiments of the present disclosure may modify the various constituent elements in the various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing one element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0034] It should be noted that if it is described that one component element is “connected” to another component element, the first component element may be directly connected to the second component element, and a third component element may be “connected” between the first component element and the second component element. Conversely, when one component element is “directly connected” to another component element, it can be understood that there is no third component element between the first component element and the second component element.

[0035] The term “user” used in various embodiments of the present disclosure may indicate a person who uses an electronic device, and may be a monitoring person, a test person, or an operator.

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] The embodiment of the present application provides a wind farm wake optimization method based on a particle swarm optimization algorithm, which solves the current urgent need for a technical problem of being able to dynamically adjust the optimization strategy according to real-time wind condition data.

[0038] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0039] Figure 1 The following is a flow chart of a wind farm wake optimization method based on a particle swarm optimization algorithm provided in an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a wind farm wake optimization method based on a particle swarm optimization algorithm, and the wind farm wake optimization method includes the following specific steps: S1: Obtaining the layout distribution data of wind turbines in the wind farm, the wind direction data in the wind farm, and the wind speed data; the layout distribution data of wind turbines in the wind farm includes the number of wind turbines and the coordinates of each wind turbine; S2: Calculate the wake wind speed of a single wind turbine in the wind farm based on the layout distribution data of the wind turbines in the wind farm, the wind direction data in the wind farm, and the wind speed data; S3: Based on the wake wind speed of a single wind turbine in the wind farm, the wake effect of the entire wind farm is modeled to obtain the wind farm wake model; S4: Based on the wind farm wake model, the total active power optimization model of the wind farm is obtained; S5: The total active power optimization model of the wind farm is optimized by using an improved particle swarm algorithm to obtain the total power generation of the optimized wind farm.

[0040] It should be noted that the wind farm wake model is used to calculate the input wind speed of each wind turbine in the wind farm.

[0041] The improved particle swarm algorithm can dynamically adjust the optimization strategy according to real-time wind condition data, ensuring that the operating parameters of the wind turbines are continuously optimized throughout the life cycle of the wind farm, maximizing the output power and economic benefits of the wind farm, and having greater adaptability and flexibility.

[0042] Furthermore, the overall active power optimization model of the wind farm is optimized by using an improved particle swarm algorithm, including the following specific steps: S51: taking the fan state quantity as the particle position and randomly initializing it to generate a finite particle population; S52: Calculate the fitness of all particles and select attractors from them; S53: Update particle velocity, calculate the new position of each particle, and calculate the optimal fitness of each particle; S54: Determine whether the optimal fitness satisfies the termination condition. If so, execute step S55; if not, execute S56; S55: output result; S56: Return to continue executing step S53-step S54.

[0043] It should be noted that the fan state quantity is the axial induction factor of each fan. The value range of the axial induction factor is between (0, 1 / 3), and the maximum value is 1 / 3.

[0044] The optimal fitness is the maximum active output of the wind field calculated by the wind turbine state quantity corresponding to each particle.

[0045] The present invention improves the particle swarm algorithm (PSO) by introducing multiple dynamic attractors and a particle speed pause mechanism, and optimizes the total active power optimization model of the wind farm through the improved particle swarm algorithm (NP-PSO) to maximize the output power of the wind farm. In addition, the algorithm enhances the global search capability and stability of the particle swarm by introducing multiple dynamic attractors and a particle speed pause mechanism, and can maintain an efficient and stable optimization process even at a smaller population size, thereby improving the overall performance of the wind farm.

[0046] It should be noted that multiple dynamic attractors refer to the particle velocity update. After each iteration, the particle with the highest fitness is selected from all particles. particles (attractors), where is a positive integer, and each particle will randomly approach the position of an attractor.

[0047] The speed pause mechanism also refers to the particle speed update expression. The speed is updated normally, but if Just set the particle speed to 0. Here Tp is a random number. .

[0048] In an exemplary embodiment, the wind farm wake optimization method includes: S1: Obtaining layout distribution data of wind turbines in a wind farm, wind direction data in the wind farm, and wind speed data; the layout distribution data of wind turbines in a wind farm includes the number of wind turbines and the coordinates of each wind turbine.

[0049] S2: Calculate the wake wind speed of a single wind turbine in the wind farm based on the layout distribution data of the wind turbines in the wind farm, the wind direction data in the wind farm, and the wind speed data in the wind farm.

[0050] In S2, the Jensen wake model is used to study the wake of a single wind turbine, and its expression is:

[0051]

[0052] In the formula, is the effective input wind speed of the upstream fan; Downstream of the fan The wake wind speed at a distance of times the fan impeller diameter; is the thrust coefficient of the fan; is the wake attenuation constant; is the fan impeller diameter; Downstream of the fan Wake diameter at times the distance from the fan impeller. Wake attenuation constant Usually based on experience; wake attenuation constant middle, In this embodiment, when hour, represents the wake attenuation constant of the onshore wind turbine, The value of is 0.075; when hour, represents the wake attenuation constant of the offshore wind turbine, The value of is 0.04.

[0053] S3: According to the wake wind speed of a single wind turbine in the wind farm, the wake effect of the entire wind farm is modeled to obtain the wind farm wake model.

[0054] In one embodiment, assuming that in the wind farm, There are a total of The wake of the typhoon and the There is wake overlap between typhoon turbines, so the expression of the wind farm wake model is:

[0055]

[0056] In the formula, For the Wind speed of the typhoon; is the free wind speed in the wind farm; For the Typhoon machine; ; Upstream of the fan The input wind speed of the typhoon machine; Upstream of the fan The input wind speed of the typhoon is Wake wind speed at the typhoon head; For the Thrust coefficient of the typhoon turbine; For fans Impeller area; For the Typhoon and The distance of the typhoon turbine along the wind direction; is the wake overlap area, It represents an intermediate variable, which represents the difference between the input wind speed of the jth fan upstream and the downstream wind speed.

[0057] According to an embodiment of the present application, the expression of the wake overlap area is:

[0058] In the formula, is the radius of the wake area; is the radius of the downstream fan impeller; It is the distance between the center of the wake area and the center of the downstream fan impeller in the direction perpendicular to the wake.

[0059] S4: Based on the wind farm wake model, the overall active power optimization model of the wind farm is obtained; the specific steps include: Calculate the wind farm The power of the typhoon is expressed as:

[0060] In the formula, For the wind farm The power of the typhoon; is the air density, For the The wind energy utilization coefficient of the typhoon turbine.

[0061] Based on the wind farm The power of the wind turbine is used to calculate the total output power of the wind farm. The expression is:

[0062] In the formula, is the total output power of the wind farm; is the number of wind turbines in the wind farm.

[0063] Finally, the total active power optimization model of the wind farm is expressed as:

[0064] In the formula, is the axial induction factor; Indicates the wind farm The power of the fan, Represents the maximum value of the total output power of the wind farm in the total active power optimization model of the wind farm.

[0065] It should be noted that the wind energy utilization coefficient is related to the axial induction factor, and its expression is: .

[0066] The thrust coefficient is related to the axial induction factor, and its expression is: .

[0067] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process in this embodiment, another wind farm wake optimization method is provided. In S52, the fitness of all particles is calculated, and the expression of the attractor is selected from them:

[0068] In the formula, For the The attractor position generated by the update; For particle The position at the iteration.

[0069] It should be noted that the definition of attractor is: After the update, among all particles, the one with the highest fitness Particles, The attractor that each particle tracks during each update is chosen randomly.

[0070] It should be further explained that in S53, the expression for updating the particle velocity is:

[0071] In the formula, Representative The particle velocity at the iteration; Representative The particle velocity at the iteration; For the The weight of the iteration; is the individual learning factor; is the population learning factor; set and The value of is 1.4932; , and are state variables, and are all random numbers between 0 and 1; if Then the next particle speed update inherits the previous particle speed, and simultaneously tracks two extreme values, namely: the individual historical optimal position and the attractor position; For particle The position at the iteration; is the optimal position of an individual, that is, all particles in the population are in the The particle position with the highest fitness after iterations.

[0072] As an example, in S53, the expression for calculating the new position of each particle is:

[0073] In the formula, For particle The position at the iteration.

[0074] In one embodiment, Figure 3 This is a flow chart of another wind farm wake optimization method based on a particle swarm optimization algorithm provided according to an embodiment of the present invention. Based on the above embodiments, this embodiment further optimizes and expands the wind farm wake optimization method based on a particle swarm optimization algorithm.

[0075] The NP-PSO algorithm improves the search and utilization capabilities of the PSO optimization algorithm by simulating the dynamic behavior of the brain's neuron population. Among them, the attractor strategy simulates the brain's neuron attractors and attracts other particles to explore the current multiple optimal solution areas to improve the algorithm's solution performance. In NP-PSO, each particle not only tracks individual extreme values, but also tracks an attractor position (one of the global optimal solution or the local optimal solution). This dual extreme value tracking mechanism helps particles jump out of the local optimum and avoids the premature convergence phenomenon common in traditional PSO algorithms. In addition, the NP-PSO algorithm introduces a speed pause mechanism. The speed pause mechanism simulates the movement of real particles, and its speed update can be inherited from the last particle's movement speed, and it can also be directly changed to zero. Through the speed pause mechanism, particles can inherit the speed to develop new areas, and the speed may also be directly zero and stay at the current position.

[0076] Combination Figure 2 In (a), (b), and (c), during the update process of the improved PSO algorithm, the speed update formula of each particle is as follows:

[0077] In the formula, Representative The particle velocity at the iteration; Representative The particle velocity at the iteration; For the The weight of the iteration; is the individual learning factor; is the population learning factor; set and The value of is 1.4932; , and are state variables, and are all random numbers between 0 and 1; if Then the next particle speed update inherits the previous particle speed, and simultaneously tracks two extreme values, namely: the individual historical optimal position and the attractor position; For particle The position at the iteration; is the optimal position of an individual, that is, all particles in the population are in the The particle position with the highest fitness after iterations.

[0078] The definition of attractor is: After the update, among all particles, the one with the highest fitness Particles, The attractor that each particle tracks during each update is chosen randomly.

[0079] The fitness of all particles is calculated and the expression for selecting attractors is:

[0080] In the formula, For the The attractor position generated by the update; For the The first attractor position after iterations; For the The second attractor position after iterations; For the After the iteration attractor positions; For particle The position at the iteration.

[0081] It should be noted that if , then the speed of the particle directly becomes 0. The present invention introduces a speed pause mechanism, and the speed of each particle in the population can inherit the speed of the previous iteration and can also be directly changed to zero. The NP-PSO algorithm not only improves the probability of finding the global optimal solution, but also reduces unnecessary computational overhead, making the active power optimization of large-scale wind farms more feasible.

[0082] The expression for the new position of each particle is:

[0083] In the formula, For particle The position at the iteration.

[0084] Combination Figure 3 The calculation process of the NP-PSO algorithm is as follows: First, randomly generate a specified number of particle populations and calculate their initial fitness values. Second, select the top particle with the highest fitness. The particles are used as attractors, which will guide other particles to explore the solution space in subsequent iterations. The speed update is determined based on the value of the particle's state variable. If the condition is met, the particle's speed is adjusted according to the defined speed update formula. Subsequently, the updated speed is used to adjust the positions of all particles and calculate the new fitness value. Finally, check whether the preset iteration termination conditions (such as reaching the maximum number of iterations or fitness convergence) are met. If so, the iteration is stopped and the optimal solution is output; otherwise, the particle with the highest fitness is re-selected from the updated particle swarm. The particles serve as new attractors, ready to enter the next round of iteration.

[0085] The present invention introduces a particle swarm optimization algorithm (NP-PSO) based on a multi-attractor mechanism. The algorithm enhances the global search capability and stability of the particle swarm by introducing multiple dynamic attraction points, and can maintain an efficient and stable optimization process even at a smaller population size. In addition, the present invention also introduces a speed pause mechanism, and the speed of each particle in the population can inherit the speed of the previous iteration and can also be directly changed to zero. Thanks to the two introduced mechanisms, the NP-PSO algorithm not only improves the probability of finding the global optimal solution, but also reduces unnecessary computational overhead, making the active optimization of large-scale wind farms more feasible. By applying the improved particle swarm algorithm, the present invention not only improves the overall performance of the wind farm, but also provides new ideas and technical means for the design and management of future wind farms. In summary, the present invention solves the limitations of the prior art through innovative optimization strategies, and has made significant progress in the optimization of wind turbine operation in built wind farms.

[0086] The wind farm wake optimization method based on particle swarm optimization algorithm provided in the embodiment of the present application can be applied to electronic devices. It can be understood by those skilled in the art that the electronic device structure involved in the embodiment of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or less components than shown in the figure, or combine certain components, or arrange different components. In an embodiment of the present invention, the electronic device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0087] The above-mentioned electronic device realizes the wind farm wake optimization method based on the particle swarm optimization algorithm of the present application, which obtains the layout distribution data of the wind turbines in the wind farm, the wind direction data in the wind farm and the wind speed data; calculates the wake wind speed of a single wind turbine in the wind farm based on the layout distribution data of the wind turbines in the wind farm, the wind direction data in the wind farm and the wind speed data; models the wake effect of the entire wind farm according to the wake wind speed of the single wind turbine in the wind farm to obtain a wind farm wake model; calculates the total power generation of the wind farm based on the wind farm wake model; uses the wind turbine state quantity as the particle position and randomly initializes it to generate a finite particle population; calculates the fitness of all particles and selects attractors from them; updates the particle velocity, calculates the new position of each particle, and calculates the optimal fitness of each particle; determines whether the optimal fitness meets the termination condition, and if so, outputs the result; if not, returns to continue executing the above steps until the optimal fitness meets the termination condition. The present invention introduces a particle swarm optimization algorithm (NP-PSO) based on a multi-attractor mechanism. The algorithm enhances the global search capability and stability of the particle swarm by introducing multiple dynamic attraction points, and can maintain an efficient and stable optimization process even at a smaller population size. In addition, the present invention also introduces a speed pause mechanism, and the speed of each particle in the population can inherit the speed of the previous iteration and can also be directly changed to zero. Thanks to the two introduced mechanisms, the NP-PSO algorithm not only improves the probability of finding the global optimal solution, but also reduces unnecessary computational overhead, making the active optimization of large-scale wind farms more feasible. By applying the improved particle swarm algorithm, the present invention not only improves the overall performance of the wind farm, but also provides new ideas and technical means for the design and management of future wind farms. In summary, the present invention solves the limitations of the prior art through innovative optimization strategies, and has made significant progress in the optimization of wind turbine operation in built wind farms.

[0088] The storage medium provided in the present application stores a program product capable of implementing a wind farm wake optimization method based on a particle swarm optimization algorithm.

[0089] The wind farm wake optimization method based on the particle swarm optimization algorithm includes: obtaining the layout distribution data of the wind turbines in the wind farm, the wind direction data and the wind speed data in the wind farm; calculating the wake wind speed of a single wind turbine in the wind farm based on the layout distribution data, the wind direction data and the wind speed data of the wind turbines in the wind farm; modeling the wake effect of the entire wind farm according to the wake wind speed of the single wind turbine in the wind farm to obtain the wind farm wake model; calculating the total power generation of the wind farm based on the wind farm wake model; taking the wind turbine state quantity as the particle position and randomly initializing it to generate a finite particle population; calculating the fitness of all particles and selecting attractors from them; updating the particle velocity, calculating the new position of each particle, and calculating the optimal fitness of each particle; judging whether the optimal fitness meets the termination condition, and if so, outputting the result; if not, returning to continue to execute the above steps until the optimal fitness meets the termination condition.

[0090] The present invention improves the particle swarm algorithm (PSO) by introducing multiple dynamic attractors and a particle speed pause mechanism, and optimizes the total active power optimization model of the wind farm through the improved particle swarm algorithm (NP-PSO) to maximize the output power of the wind farm. In addition, the algorithm enhances the global search capability and stability of the particle swarm by introducing multiple dynamic attractors and a particle speed pause mechanism, and can maintain an efficient and stable optimization process even at a smaller population size, thereby improving the overall performance of the wind farm.

[0091] In some possible embodiments, the wind farm wake optimization method based on the particle swarm optimization algorithm disclosed in the present invention can be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0092] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0093] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0094] For those skilled in the art, designing different forms of control circuits according to the teachings of the present invention does not require creative work. These changes, modifications, substitutions and variations of the embodiments without departing from the principles and spirit of the present invention still fall within the scope of protection of the present invention.

Claims

1. A wind farm wake optimization method based on particle swarm optimization algorithm, characterized in that: The wind farm wake optimization method comprises the following specific steps: S1: Obtaining the layout distribution data of wind turbines in the wind farm, the wind direction data in the wind farm, and the wind speed data; S2: Calculate the wake wind speed of a single wind turbine in the wind farm based on the layout distribution data of the wind turbines in the wind farm, the wind direction data in the wind farm, and the wind speed data; S3: Based on the wake wind speed of a single wind turbine in the wind farm, the wake effect of the entire wind farm is modeled to obtain the wind farm wake model; S4: Based on the wind farm wake model, the total active power optimization model of the wind farm is obtained; S5: The total active power optimization model of the wind farm is optimized by using an improved particle swarm algorithm to obtain the total power generation of the optimized wind farm.

2. The wind farm wake optimization method according to claim 1, characterized in that: The overall active power optimization model of the wind farm is optimized by using the improved particle swarm algorithm, which includes the following specific steps: S51: taking the fan state quantity as the particle position and randomly initializing it to generate a finite particle population; S52: Calculate the fitness of all particles and select attractors from them; S53: Update particle velocity, calculate the new position of each particle, and calculate the optimal fitness of each particle; S54: Determine whether the optimal fitness satisfies the termination condition. If so, execute step S55; if not, execute S56; S55: output result; S56: Return to continue executing step S53-step S54.

3. The wind farm wake optimization method according to claim 2, characterized in that: In S2, the Jensen wake model is used to study the wake of a single wind turbine, and its expression is: In the formula, is the effective input wind speed of the upstream fan; Downstream of the fan The wake wind speed at a distance of times the fan impeller diameter; is the thrust coefficient of the fan; is the wake attenuation constant; is the fan impeller diameter; Downstream of the fan The wake diameter at a distance of times the fan impeller.

4. The wind farm wake optimization method according to claim 3, characterized in that: In S3, it is assumed that in the wind field, There are a total of The wake of the typhoon and the There is wake overlap between typhoon turbines, so the expression of the wind farm wake model is: In the formula, For the Wind speed of the typhoon; is the free wind speed in the wind farm; For the Typhoon machine; ; Upstream of the fan The input wind speed of the typhoon machine; Upstream of the fan The input wind speed of the typhoon is Wake wind speed at the typhoon head; For the Thrust coefficient of the typhoon turbine; For fans Impeller area; For the Typhoon and The distance of the typhoon turbine along the wind direction; is the wake overlap area, It represents an intermediate variable, which represents the difference between the input wind speed of the jth fan upstream and the downstream wind speed.

5. The wind farm wake optimization method according to claim 4, characterized in that: The expression of wake overlap area is: In the formula, is the radius of the wake area; is the radius of the downstream fan impeller; It is the distance between the center of the wake area and the center of the downstream fan impeller in the direction perpendicular to the wake.

6. The wind farm wake optimization method according to claim 5, characterized in that: In S4, based on the wind farm wake model, the total active power optimization model of the wind farm is obtained, which includes the following specific steps: Calculate the wind farm The power of the typhoon is expressed as: In the formula, For the wind farm The power of the typhoon; is the air density, For the Wind energy utilization factor of typhoon turbines; Based on the wind farm The power of the wind turbine is used to calculate the total output power of the wind farm. The expression is: In the formula, is the total output power of the wind farm; is the number of wind turbines in the wind farm; Finally, the total active power optimization model of the wind farm is expressed as: In the formula, is the axial induction factor; Indicates the wind farm The power of the fan, Represents the maximum value of the total output power of the wind farm in the total active power optimization model of the wind farm.

7. The method for optimizing the wind farm wake according to claim 5, characterized in that: The wind energy utilization coefficient is related to the axial induction factor, and its expression is: ； The thrust coefficient is related to the axial induction factor, and its expression is: 。 8. The method for optimizing the wind farm wake according to claim 7, characterized in that: In S52, the fitness of all particles is calculated, and the expression of attractor is selected from them: In the formula, For the The attractor position generated by the update; For the The first attractor position after iterations; For the The second attractor position after iterations; For the After the iteration attractor positions; For particle The position at the iteration.

9. The method for optimizing the wind farm wake according to claim 8, characterized in that: In S53, the expression for updating the particle velocity is: In the formula, Representative The particle velocity at the iteration; Representative The particle velocity at the iteration; For the The weight of the iteration; is the individual learning factor; is the population learning factor; , and are state variables, and are all random numbers between 0 and 1; For particle The position at the iteration; is the optimal position of an individual, that is, all particles in the population are in the The particle position with the highest fitness after iterations.

10. The method for optimizing the wind farm wake according to claim 9, characterized in that: In S53, the expression for calculating the new position of each particle is: In the formula, For particle The position at the iteration.

Images