Wind power plant layout optimization method and system based on adaptive differential evolution

Abstract

The invention discloses a wind power plant layout optimization method and system based on adaptive differential evolution, and the method comprises the steps: S1, obtaining the wind energy data of a wind power plant, the parameters of the wind power plant and a fan, and building a wind power plant layout optimization model; s2, randomly generating a wind power plant layout scheme to form an initial population; s3, randomly dividing the initial population into several groups of sub-populations, and searching the sub-populations to obtain a variation vector; s4, performing local difference on the variation vector to obtain a candidate layout solution, and performing adaptive replacement operation on the target vector to obtain a test vector; s5, repairing and replacing the test variable, and selecting between the target vector and the repaired test vector to obtain a proper individual; and S6, continuing to execute the steps S3-S5 until a set maximum evaluation frequency is reached, and finally obtaining an optimal wind power plant layout solution. The method has the advantages that the wake effect is reduced, and the expected generating capacity is maximized.

Description

Technical Field

[0001] The present invention mainly relates to the field of wind farm layout optimization, and in particular to a wind farm layout optimization method and system based on adaptive differential evolution. Background Art

[0002] As the world pays more and more attention to new energy and sustainable energy, wind power generation has gradually become the main force of renewable energy power generation equipment. Wind turbines use flexible structures and are extremely sensitive to wind loads. When wind turbines convert wind energy into electrical energy, the wind turbine wake generated by the upstream wind turbine will cause a loss in the wind speed of the downstream wind turbine, so that the energy obtained by the wind turbine is reduced. Traditional layout methods require a lot of manual comparison, which is a heavy workload and usually cannot obtain a better layout plan. Summary of the invention

[0003] In view of the technical problems existing in the prior art, the present invention provides a wind farm layout optimization method and system based on adaptive differential evolution, which can reduce the wake effect and maximize the expected power generation.

[0004] In order to solve the above technical problems, the technical solution proposed by the present invention is: A wind farm layout optimization method based on adaptive differential evolution comprises the following steps: S1. Obtain wind farm wind energy data, wind farm and wind turbine parameters, and establish a wind farm layout optimization model; S2. Randomly generate a preset number of wind farm layout plans that meet the constraints to form an initial population; S3, randomly divide the initial population into several sub-populations, and then search the sub-populations to obtain the mutation vector; S4, performing local differentiation on the mutation vector to obtain a candidate layout solution, and based on the candidate layout solution, performing an adaptive replacement operation on the target vector to obtain a test vector; S5, performing a repair and replacement operation on the test variable to obtain a repaired test vector, and then selecting between the target vector and the repaired test vector to obtain a suitable individual; S6. Continue to execute steps S3-S5 on the population until the set maximum number of evaluations is reached, and finally the optimal wind farm layout solution is obtained.

[0005] Preferably, the specific process of step S1 is: S11, obtaining wind energy data of the wind farm, wind farm and wind turbine parameters and performing preprocessing, and establishing a wind speed probability distribution model, a wake model and a wind turbine power curve model; S12. Based on the wind speed probability distribution model, the wake model and the wind turbine power curve model, the power output expectation function of each wind turbine is established to obtain the wind farm optimization model.

[0006] Preferably, in step S11, a two-parameter Weibull distribution is used to represent the wind speed probability distribution model; a Jensen model is used to establish a wake model; and a Gaussian function is used to represent the wind turbine power curve model, and the formula is as follows:

[0007] in For fans i The power, is the rated power of the fan; is the wind speed, , and are the cut-in wind speed, rated wind speed and cut-out wind speed of the fan respectively. a , b and c They are the parameters obtained by fitting the wind turbine power curve data with the Gaussian function.

[0008] Preferably, in step S12, the formula of the power output expectation function is as follows:

[0009] in For fans i The power output expectation is is the rated power of the fan, is the scaling parameter to take into account the wake effect, is the shape parameter, is the probability of each interval of wind direction, is the median of each wind direction interval, n =1, … , g ; is the median of each wind speed interval; , Divide into s intervals, each interval is [ , , j = 1, … , s ; g is the number of intervals into which the wind direction angle is evenly divided; The variables of the wind farm layout optimization model are the two-dimensional coordinates of each wind turbine, expressed as [ x i1 , x i2 ], i = 1,… , N ; N is the number of wind turbines in the wind farm; The objective function of the wind farm layout optimization model is expressed as follows:

[0010] The boundary constraints of the wind farm layout optimization model are: the wind turbines are within the preset range; The distance constraint of the wind farm layout optimization model is: the safe distance between two wind turbines is m times the diameter of the wind turbine rotor.

[0011] Preferably, in step S4, the specific process of locally differencing the mutation vector to obtain the candidate layout solution is: re-encoding the mutation vector, taking a wind farm layout scheme as a population Q, in which an individual is the coordinate of a wind turbine, locally differencing the population Q, and then re-encoding the differentiated offspring population to obtain the candidate layout solution.

[0012] Preferably, in step S4, the specific process of performing an adaptive replacement operation on the target vector based on the candidate layout solution to obtain the test vector is: When the number of evaluations is less than the learning cycle of the adaptive replacement operation, the coordinates of the first wind turbine in the candidate layout solution are used to randomly replace a coordinate in the target vector. The index of the replaced coordinate is r , get the test vector; When the number of evaluations reaches or exceeds the learning cycle of the adaptive replacement operation, adaptive replacement is adopted to obtain a test vector.

[0013] Preferably, the process of adaptive replacement is: Calculate the success rate of each wind turbine coordinate index, and select the index of the replaced coordinate in the individual by random traversal sampling based on the success rate information k , the coordinates of the first wind turbine in the candidate layout solution are used to replace the index in the target vector k The corresponding coordinates are obtained to obtain the test vector.

[0014] Preferably, the success rate of each wind turbine coordinate index is calculated The formula is as follows:

[0015] in Indicates the current number of evaluations. is the learning cycle of the adaptive replacement operation, Nsc i,g and Nfc i,g Indicates whether the test vector after the replacement operation satisfies the constraint condition. N i,g and Nf i,g Indicates whether the test vector after selection is better than the target vector. ; is a constant.

[0016] Preferably, in step S5, the specific process of performing a repair and replacement operation on the test variable to obtain a repaired test vector is: Find the coordinate in the trial vector that violates the constraint and replace it with the next coordinate in the candidate layout solution. Repeat this process until the first coordinate is replaced. p coordinates, and obtain the repaired test vector; p = N / 2, N is the number of wind turbines in the wind farm.

[0017] The present invention also discloses a wind farm layout optimization system based on adaptive differential evolution, comprising a memory and a processor connected to each other, wherein a computer program is stored on the memory, and when the computer program is run by the processor, the steps of the method described above are executed.

[0018] Compared with the prior art, the advantages of the present invention are: The wind farm layout optimization method based on adaptive differential evolution of the present invention first obtains wind farm wind energy data, wind farm and wind turbine parameters and performs preprocessing, establishes a wind farm layout optimization model that reduces the wake effect and increases the output power, then randomly generates a certain number of wind farm layout schemes that meet the constraints to form an initial population, and evaluates the initial population based on the objective function, and then randomly divides the initial population into several groups of sub-populations, and performs sub-population search to obtain mutation vectors, performs local difference on the mutation vectors to obtain candidate layout solutions, performs adaptive replacement operations on the candidate layout solutions to obtain test variables, and then performs repair operations on the test variables, and finally selects to obtain suitable individuals, and continues to perform the above-mentioned iterative process on the population until the set maximum number of evaluations is reached, thereby obtaining the optimal layout scheme. The present invention can optimize the layout of land or offshore wind farms within an acceptable time range, find the optimal layout of wind turbines to reduce the wake effect to the greatest extent, thereby maximizing the expected power generation.

[0019] The present invention adopts a Gaussian function with a high degree of fit to the actual wind turbine power curve data to represent the power curve, and establishes a wind farm layout optimization model that conforms to the actual wind farm situation; the wind farm layout is optimized based on a differential evolution method with a simple structure, easy implementation, fast convergence speed, and strong robustness. In combination with the characteristics that the wind farm layout optimization is prone to "dimensionality disaster" due to the increase in the number of wind turbines, a local adaptive replacement strategy is adopted. While maintaining the global search capability, under the premise of the same number of evaluations, it is easier to find the optimal solution by using the previous learning experience, thereby improving the convergence speed and stability of the algorithm. In addition, considering that the wind farm layout problem has strict constraints, the calculation speed of the algorithm can be accelerated by repairing and replacing operations, and the number and quality of feasible solutions can be improved. The present invention can be applied to offshore or land wind farms of various shapes, has high efficiency in layout optimization, and can provide a layout solution with high optimization quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of an embodiment of the wind farm layout optimization method of the present invention.

[0021] Figure 2 Schematic diagram of an adaptive replacement operation and a repair replacement operation in an embodiment of the present invention.

[0022] Figure 3 Schematic diagram of the structure of “success and failure memory” in an embodiment of the present invention.

[0023] Figure 4 Schematic diagram of updating “success and failure memory” in an embodiment of the present invention.

[0024] Figure 5 The figure is a comparison diagram between the traditional layout scheme and the optimized layout scheme of the present invention; (a) is the traditional layout scheme; (b) is the optimized layout scheme. DETAILED DESCRIPTION

[0025] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments.

[0026] like Figure 1 As shown, the wind farm layout optimization method based on adaptive differential evolution provided by the embodiment of the present invention specifically includes the following steps: S1. Obtain wind farm wind energy data, wind farm and wind turbine parameters and perform preprocessing to establish a wind farm layout optimization model to reduce wake effect and increase output power; wind energy data includes wind speed, wind direction, wind energy density, wind speed probability distribution, temperature, air pressure and humidity; wind farm parameters include wind farm location, scale, area and layout; wind turbine parameters include wind turbine rated power, cut-in wind speed, cut-out wind speed, wind turbine height and rotor diameter; The specific process of step S1 is: S11. Obtain wind farm and wind turbine parameters, as well as wind direction and wind speed data measured by the wind farm’s wind tower for 12 consecutive months. N The index of each fan is i , i = 1, … , N ; Preprocess the wind direction data of wind energy data: divide the wind direction into g (e.g. 16) integer intervals, calculate the probability of each interval , n =1,…, g ; Preprocess the wind speed data of wind energy data: use the two-parameter Weibull distribution to represent the wind speed probability distribution model, and divide the wind speed into s (e.g. 34) integer intervals; The wake model is established using the Jensen model; The Gaussian function is used to represent the wind turbine power curve model, and the formula is as follows:

[0027] in For fans i The power, =3000kW, is the rated power of the fan; is the wind speed, , and are the cut-in wind speed, rated wind speed and cut-out wind speed of the fan respectively. , and The values ​​are 3m / s, 11.5m / s and 25m / s respectively. a , b and c are the parameters obtained by fitting the wind turbine power curve data with the Gaussian function, a , b and c Specifically, they are 2959, 12.85 and 4.934; S12. Combining the two-parameter Weibull wind speed probability distribution model, the Jensen wake model and the wind turbine power curve model to establish the power output expectation function of each wind turbine, the formula is as follows:

[0028] in For fans i The power output expectation is is the rated power of the fan, is the scaling parameter to take into account the wake effect, is the shape parameter, is the probability of each interval of wind direction, is the median of each wind direction interval, n =1, … , g , is the median of each wind speed interval, [ , For each wind speed range, j = 1, … , s ; Finally, the variables of the wind farm layout optimization model are the two-dimensional coordinates of each wind turbine, expressed as [ x i1 , x i2 ], i =1, … , N ;like N =16; The objective function of the wind farm optimization model represents the i The expected value of the total power output is the largest, which is as follows:

[0029] The boundary constraints of the wind farm layout optimization model are as follows: the wind turbines are within the shape of the wind farm, such as a rectangular wind farm with a horizontal length of 2500m and a vertical length of 4000m; The distance constraint condition of the wind farm layout optimization model is: the safe distance between two wind turbines is m times the diameter of the wind turbine rotor; where m is 3-5; in this embodiment, it is 4 times.

[0030] S2: When the number of wind turbines in the wind farm is N (e.g., 16), randomly generate N p (e.g. 12) wind farm layout schemes that meet the constraints constitute the initial population P; each individual is a layout scheme, and each individual is represented by: { x 11 , x 12 , x 21 , x 22 , … , x N1 , x N2}; S3, randomly divide the initial population P into N fGroup (such as 4 groups) sub-populations, and then perform sub-population search to obtain mutation vectors. The specific process is: The conditions for neighbor exploration are set as follows: the number of evaluations reaches a certain number and the objective function value remains unchanged for a certain number of times; First, determine whether the conditions for setting neighboring exploration are met. If so, perform the neighborhood search "NSDE / best / 1" mutation operation (a conventional mutation strategy in the differential evolution algorithm); if not, perform the traditional "DE / best / 1" mutation operation (also a classic mutation strategy in the differential evolution algorithm) to obtain the mutation vector.

[0031] S4. Based on the mutation vector, a local adaptive replacement strategy is implemented on the target vector to obtain a test vector: First, local differences are performed to obtain candidate layout solutions, specifically: Recode the mutation vector, take a wind farm layout plan as a population Q, one of which is the coordinate of a wind turbine, locally differentiate the population Q, and then recode the differential offspring population to obtain the candidate layout solution (corresponding to Figure 2 Candidate solutions in ): u 11 , u 12 , u 21 , u 22 , u 31 , u 32 ,… , u N1 , u N2 ).

[0032] Second, implement adaptive replacement strategies, such as Figure 2 As shown, the specific process is: Set the learning period of the adaptive replacement operation to L p, such as 150 times; (1) When the number of evaluations is less than 150, random replacement is performed and the random replacement information is recorded, specifically: The coordinates of the first wind turbine in the candidate layout solution are used to randomly replace a coordinate in the target vector. The index of the replaced coordinate is r , get the test vector, and record the random replacement information in the "Success and failure memories (SFM)", such as Figure 3 The information to be recorded in "Success and Failure Memory (SFM)" includes: Nsci,G 、Nfc i,G 、Nse i,G and Nf i,G ,in i = 1, … , N , G Indicates the current number of evaluations. Nsc i,G and Nfc i,G Indicates whether the test vector after the replacement operation satisfies the constraint condition. N i,G and Nf i,G Indicates whether the trial vector after selection is better than the target vector; When the test vector after the replacement operation satisfies the constraints: Nsc r,G =1 ， and Nfc i,G = 0, i ≠ r ;otherwise Nfc r,G = 1 ， and Nsc i,G = 0, i ≠ r ; When the trial vector after selection is better than the target vector: N r,G = 1 ， and Nf i,G = 0, i ≠ r ;otherwise Nf r,G = 1 ， and N i,G = 0, i ≠ r ;in r The indices of the coordinates to be replaced for the adaptive replace operation.

[0033] (2) When the number of evaluations reaches or exceeds 150, calculate the index of each coordinate i The corresponding success rate is used to configure the replacement strategy according to the success rate information, perform adaptive replacement and update the adaptive replacement information. The process is as follows: Calculate the success rate of each wind turbine coordinate index, and select the index of the replaced coordinate in the individual by random traversal sampling based on the success rate information k, the coordinates of the first wind turbine in the candidate layout solution[ u 11 , u 12 ] is used to replace the target vector x l =( x 11 , x 12 , …, x k1 , x k2 , … , x N1 , x N2 ) k The corresponding coordinates [ x k1 , x k2 ], get the test vector u l =( x 11 , x 12 , …, u 21 , u 22 , …, x i1 , x i2 ,… , x N1 , x N2 ), and update the adaptive replacement information in SFM, such as Figure 4 As shown. Due to SFM overflow, the earliest information includes Nsc 1,G-LP 、Nfc 1,G-LP 、Nse 1,G-LP and Nf 1,G-LP will be removed so that the current replacement information is stored in SFM.

[0034] Success rate of each wind turbine coordinate index The calculation formula is as follows:

[0035] in G Indicates the current number of evaluations. Nsc i,g and Nfc i,gIndicates whether the test vector after the replacement operation satisfies the constraint condition. N i,g and Nf i,g Indicates whether the test vector after selection is better than the target vector. ; is a constant, which can be taken as 0.01.

[0036] S5, such as Figure 2 As shown, the test vector is repaired and replaced, and finally the target vector and the test vector are selected to obtain the appropriate individual, which is as follows: Find the trial vector u l =( x 11 , x 12 , …, u 21 , u 22 , …, x i1 , x i2 ,… , x N1 , x N2 ) in which the constraint is violated [ x i1 , x i2 ], and use the candidate layout solution ( u 11 , u 12 , u 21 , u 22 , u 31 , u 32 ,… , u N1 , u N2 ) in the next coordinate [ u 21 , u 22 ] to replace the coordinates that violate the constraints in the test vector [ x i1 , x i2 ]; Repeat the above process until the p coordinates, and obtain the repaired test vector ul =( x 11 , x 12 , …, u 21 , u 22 , …, u p1 , u p2 ,… , x N1 , x N2 ); p The value of N / 2=8; Finally, the target vector and the repaired test vector are selected to obtain the appropriate individual.

[0037] S6. Continue to perform S3-S5 process on the population until the set maximum number of evaluations, 150,000, is reached, thereby obtaining the optimal layout solution.

[0038] like Figure 5 As shown in (a), the power output of the traditional layout is expected to be 14712.69kW; Figure 5 As shown in (b), the power output expectation of the optimized layout scheme is 18327.56 kW. Compared with the traditional layout scheme, the power output expectation of the optimized layout scheme of the present invention is increased by 23.04%, and the optimization time is 87.18 seconds, which is relatively short and within an acceptable range.

[0039] The wind farm layout optimization method based on adaptive differential evolution of the present invention first obtains wind farm wind energy data, wind farm and wind turbine parameters and performs preprocessing, establishes a wind farm layout optimization model that reduces the wake effect and increases the output power, then randomly generates a certain number of wind farm layout schemes that meet the constraints to form an initial population, and evaluates the initial population based on the objective function, and then randomly divides the initial population into several groups of sub-populations, and performs sub-population search to obtain mutation vectors, performs local difference on the mutation vectors to obtain candidate layout solutions, performs adaptive replacement operations on the candidate layout solutions to obtain test variables, and then performs repair operations on the test variables, and finally selects to obtain suitable individuals, and continues to perform the above-mentioned iterative process on the population until the set maximum number of evaluations is reached, thereby obtaining the optimal layout scheme. The present invention can optimize the layout of land or offshore wind farms within an acceptable time range, find the optimal layout of wind turbines to reduce the wake effect to the greatest extent, thereby maximizing the expected power generation.

[0040] The present invention adopts a Gaussian function with a high degree of fit to the actual wind turbine power curve data to represent the power curve, and establishes a wind farm layout optimization model that conforms to the actual wind farm situation; the wind farm layout is optimized based on a differential evolution method with a simple structure, easy implementation, fast convergence speed, and strong robustness. In combination with the characteristics that the wind farm layout optimization is prone to "dimensionality disaster" due to the increase in the number of wind turbines, a local adaptive replacement operation strategy is adopted. While maintaining the global search capability, under the premise of the same number of evaluations, it is easier to find the optimal solution by using the previous learning experience, thereby improving the convergence speed and stability of the algorithm. In addition, considering that the wind farm layout problem has strict constraints, the calculation speed of the algorithm can be accelerated by repairing and replacing operations, and the number and quality of feasible solutions can be improved. The present invention can be applied to offshore or land wind farms of various shapes, has a higher efficiency when performing layout optimization, and can provide a layout solution with high optimization quality.

[0041] The embodiment of the present invention further provides a wind farm layout optimization system based on adaptive differential evolution, including an interconnected memory and a processor, wherein a computer program is stored on the memory, and the computer program executes the steps of the above method when it is run by the processor. The present invention implements all or part of the process in the above embodiment method, and can also be completed by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above method embodiment when it is executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable storage media include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. The memory is used to store computer programs and / or modules, and the processor implements various functions by running or executing computer programs and / or modules stored in the memory, and calling data stored in the memory. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0042] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should be regarded as the protection scope of the present invention.

Claims

1. A wind farm layout optimization method based on adaptive differential evolution, characterized in that: Includes steps: S1. Obtain wind farm wind energy data, wind farm and wind turbine parameters, and establish a wind farm layout optimization model; S2. Randomly generate a preset number of wind farm layout plans that meet the constraints to form an initial population; S3, randomly divide the initial population into several sub-populations, and then search the sub-populations to obtain the mutation vector; S4, performing local differentiation on the mutation vector to obtain a candidate layout solution, and based on the candidate layout solution, performing an adaptive replacement operation on the target vector to obtain a test vector; S5, performing a repair and replacement operation on the test variable to obtain a repaired test vector, and then selecting between the target vector and the repaired test vector to obtain a suitable individual; S6. Continue to execute steps S3-S5 on the population until the set maximum number of evaluations is reached, and finally the optimal wind farm layout solution is obtained.

2. The wind farm layout optimization method based on adaptive differential evolution according to claim 1, characterized in that: The specific process of step S1 is: S11, obtaining wind energy data of the wind farm, wind farm and wind turbine parameters and performing preprocessing, and establishing a wind speed probability distribution model, a wake model and a wind turbine power curve model; S12. Based on the wind speed probability distribution model, the wake model and the wind turbine power curve model, the power output expectation function of each wind turbine is established to obtain the wind farm optimization model.

3. The wind farm layout optimization method based on adaptive differential evolution according to claim 2, characterized in that: In step S11, a two-parameter Weibull distribution is used to represent the wind speed probability distribution model; a Jensen model is used to establish a wake model; and a Gaussian function is used to represent the wind turbine power curve model, and the formula is as follows: in For fans i The power, is the rated power of the fan; is the wind speed, , and are the cut-in wind speed, rated wind speed and cut-out wind speed of the fan respectively. a , b and c They are the parameters obtained by fitting the wind turbine power curve data with the Gaussian function.

4. The wind farm layout optimization method based on adaptive differential evolution according to claim 3 is characterized in that: In step S12, the formula of the power output expectation function is as follows: in For fans i The power output expectation is is the rated power of the fan, is the scaling parameter to take into account the wake effect, is the shape parameter, is the probability of each interval of wind direction, is the median of each wind direction interval, n = 1,… , g ; is the median of each wind speed interval; , Divide into s intervals, each interval is [ , , j = 1, … , s ; g is the number of intervals into which the wind direction angle is evenly divided; The variables of the wind farm layout optimization model are the two-dimensional coordinates of each wind turbine, expressed as [ x i1 , x i2 ], i = 1, …, N ; N is the number of wind turbines in the wind farm; The objective function of the wind farm layout optimization model is expressed as follows: The boundary constraints of the wind farm layout optimization model are: the wind turbines are within the preset range; The distance constraint of the wind farm layout optimization model is: the safe distance between two wind turbines is m times the diameter of the wind turbine rotor.

5. The wind farm layout optimization method based on adaptive differential evolution according to any one of claims 1 to 4, characterized in that: In step S4, the specific process of locally differencing the mutation vector to obtain the candidate layout solution is as follows: re-encode the mutation vector, take a wind farm layout plan as a population Q, in which an individual is the coordinate of a wind turbine, locally differentiate the population Q, and then re-encode the differentiated offspring population to obtain the candidate layout solution.

6. The wind farm layout optimization method based on adaptive differential evolution according to claim 5, characterized in that: In step S4, the specific process of performing an adaptive replacement operation on the target vector based on the candidate layout solution to obtain a test vector is as follows: When the number of evaluations is less than the learning cycle of the adaptive replacement operation, the coordinates of the first wind turbine in the candidate layout solution are used to randomly replace a coordinate in the target vector. The index of the replaced coordinate is r , get the test vector; When the number of evaluations reaches or exceeds the learning period of the adaptive replacement operation, the test vector is obtained by adaptive replacement.

7. The wind farm layout optimization method based on adaptive differential evolution according to claim 6, characterized in that: The process of adaptive replacement is: Calculate the success rate of each wind turbine coordinate index, and select the index of the replaced coordinate in the individual by random traversal sampling based on the success rate information k , the coordinates of the first wind turbine in the candidate layout solution are used to replace the index in the target vector k The corresponding coordinates are obtained to obtain the test vector.

8. The wind farm layout optimization method based on adaptive differential evolution according to claim 7, characterized in that: Calculate the success rate of each wind turbine coordinate index The formula is as follows: in Indicates the current number of evaluations. is the learning cycle of the adaptive replacement operation, Nsc i,g and Nfc i,g Indicates whether the test vector after the replacement operation satisfies the constraint condition. N i,g and Nf i,g Indicates whether the test vector after selection is better than the target vector. ; is a constant; N is the number of wind turbines in the wind farm.

9. The method for optimizing wind farm layout based on adaptive differential evolution according to claim 8, characterized in that: In step S5, the specific process of performing a repair and replacement operation on the test variable to obtain a repaired test vector is as follows: Find the coordinate in the trial vector that violates the constraint and replace it with the next coordinate in the candidate layout solution. Repeat this process until the first coordinate is replaced. p coordinates, and obtain the repaired test vector; p = N / 2.

10. A wind farm layout optimization system based on adaptive differential evolution, comprising a memory and a processor connected to each other, wherein a computer program is stored in the memory, characterized in that: When the computer program is executed by a processor, the computer program performs the steps of the method according to any one of claims 1 to 9.

Images