Wind farm energy storage optimization method, device, equipment and storage medium

Abstract

The application discloses a wind farm energy storage optimization method, device, equipment and storage medium. The application predicts the initial energy storage capacity and initial energy storage power corresponding to the wind farm, then constructs target populations based on the initial energy storage capacity and initial energy storage power, determines the fitness value set corresponding to the optimal individual in each target population, and optimizes the energy storage of the wind farm according to the minimum fitness value in the fitness value set. The application can obtain the energy storage prediction result by predicting the initial energy storage capacity and initial energy storage power corresponding to the wind farm, can obtain the optimal energy storage capacity and optimal energy storage power in each target population by determining the fitness value set corresponding to the optimal individual in each target population, and can optimize the energy storage of the wind farm according to the minimum fitness value in the fitness value set, so that the energy storage of the wind farm is optimized according to the minimum fitness value corresponding to all target populations, the speed of energy storage optimization is accelerated, and the optimal energy storage configuration mode is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind farms, and particularly relates to a wind farm energy storage optimization method, device, equipment and storage medium. BACKGROUND

[0002] The wind power generation system has the characteristics of randomness and fluctuation, and in the process of grid connection, it can cause great threat to the stability and safety of the power system. In the wind farm, the configuration of certain energy storage devices can suppress the power fluctuation of the wind power system and improve the utilization rate of wind energy converted into electric energy. Therefore, how to effectively optimize the energy storage of the wind farm and obtain the optimal energy storage configuration mode has become a problem to be solved. SUMMARY

[0003] The main purpose of the present application is to provide a wind farm energy storage optimization method, device, equipment and storage medium, which aims to solve the technical problem of how to effectively optimize the energy storage of the wind farm and obtain the optimal energy storage configuration mode.

[0004] To achieve the above purpose, the present application provides a wind farm energy storage optimization method, which comprises the following steps:

[0005] Predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm;

[0006] Building a target population based on the initial energy storage capacity and the initial energy storage power;

[0007] Determining the fitness value set corresponding to the optimal individual in each target population, and optimizing the energy storage of the wind farm according to the minimum fitness value in the fitness value set.

[0008] Optionally, the step of predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm specifically comprises:

[0009] Determining the predicted output and the actual output corresponding to the wind farm;

[0010] Determining the power deviation corresponding to the wind farm according to the predicted output and the actual output;

[0011] Predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm according to the power deviation.

[0012] Optionally, the step of predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm according to the power deviation specifically comprises:

[0013] Determining the average value and the standard deviation corresponding to the power deviation;

[0014] Determining the initial energy storage capacity according to the average value and the standard deviation;

[0015] determine a duration when the power deviation is within a preset range, and determine an initial energy storage power according to the initial energy storage capacity and the duration.

[0016] Optionally, the step of constructing the target population based on the initial energy storage capacity and the initial energy storage power specifically comprises:

[0017] constructing an initial population based on the initial energy storage capacity and the initial energy storage power, and processing the initial population through a genetic algorithm to obtain a processed population;

[0018] allocating individuals in the processed population to a plurality of preset populations, and initializing particles in each preset population to obtain a plurality of initialized populations;

[0019] correcting each initialized population to obtain a plurality of target populations.

[0020] Optionally, the step of correcting each initialized population to obtain a plurality of target populations specifically comprises:

[0021] determining a correction method corresponding to each initialized population, wherein the correction method comprises a particle swarm correction method corresponding to a particle swarm algorithm and a differential fusion correction method corresponding to a differential fusion algorithm;

[0022] correcting particles in each initialized population according to the particle swarm correction method and the differential fusion correction method to obtain a plurality of target populations.

[0023] Optionally, the step of determining a fitness value set corresponding to the optimal individual in each target population, and performing energy storage optimization on the wind farm according to the minimum fitness value in the fitness value set specifically comprises:

[0024] determining an individual fitness value set corresponding to each individual in each target population, and determining the optimal individual in each target population according to the individual fitness value set;

[0025] determining a fitness value set corresponding to the optimal individual in each target population, and determining the minimum fitness value in the fitness value set;

[0026] when the minimum fitness value is less than a preset fitness value, performing energy storage optimization on the wind farm according to the minimum fitness value.

[0027] Optionally, the step of performing energy storage optimization on the wind farm according to the minimum fitness value when the minimum fitness value is less than a preset fitness value specifically comprises:

[0028] When the minimum fitness value is less than a preset fitness value, the step of correcting the initialized populations to obtain a plurality of target populations is returned to obtain a new fitness value;

[0029] The current iteration number is obtained, and when the current iteration number is greater than a preset iteration number, the wind farm is optimized for energy storage according to a new energy storage capacity and a new energy storage power corresponding to the new fitness value.

[0030] Optionally, after the step of determining the fitness value set corresponding to the optimal individual in each target population and optimizing the wind farm for energy storage according to the minimum fitness value in the fitness value set, the method further comprises:

[0031] An optimized energy storage capacity and an optimized energy storage power are obtained;

[0032] The wind farm curtailment rate is determined according to the optimized energy storage capacity and the optimized energy storage power;

[0033] Whether the wind farm needs to be optimized for energy storage again is determined according to the wind farm curtailment rate.

[0034] Optionally, after the step of determining the fitness value set corresponding to the optimal individual in each target population and optimizing the wind farm for energy storage according to the minimum fitness value in the fitness value set, the method further comprises:

[0035] When the operating state of the power grid corresponding to the wind farm is a transient fault, a grid-connected point voltage drop is determined;

[0036] When the grid-connected point voltage drop is greater than a preset voltage drop, an active channel corresponding to the energy storage system in the wind farm is blocked, and a reactive channel is selected, and a reactive power compensation state is entered to provide reactive power support to the power grid corresponding to the wind farm.

[0037] In addition, to achieve the above-mentioned purpose, the application further provides a wind farm energy storage optimization device, which comprises:

[0038] An energy storage prediction module is configured to predict an initial energy storage capacity and an initial energy storage power corresponding to a wind farm;

[0039] A population construction module is configured to construct target populations based on the initial energy storage capacity and the initial energy storage power;

[0040] An energy storage optimization module is configured to determine a fitness value set corresponding to the optimal individual in each target population and optimize the wind farm for energy storage according to the minimum fitness value in the fitness value set.

[0041] In addition, to achieve the above object, the present application also provides a wind farm energy storage optimization device, which comprises a memory, a processor and a wind farm energy storage optimization program stored in the memory and executable on the processor, and the wind farm energy storage optimization program is configured to implement the steps of the wind farm energy storage optimization method as described above.

[0042] In addition, to achieve the above object, the present application also provides a storage medium, which stores a wind farm energy storage optimization program, and the wind farm energy storage optimization program implements the steps of the wind farm energy storage optimization method as described above when executed by a processor.

[0043] The present application can obtain the energy storage prediction result by predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm, then constructing a plurality of target populations based on the initial energy storage capacity and the initial energy storage power, determining the optimal energy storage capacity and the optimal energy storage power in each target population according to the fitness value set corresponding to the optimal individual in each target population, and optimizing the energy storage of the wind farm according to the minimum fitness value in the fitness value set, so as to optimize the energy storage of the wind farm according to the minimum fitness value corresponding to all target populations, thereby accelerating the speed of energy storage optimization and obtaining the optimal energy storage configuration mode. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 is a structural schematic diagram of the wind farm energy storage optimization device of the hardware running environment involved in the embodiment scheme of the present application;

[0045] Figure 2 is a flowchart of the first embodiment of the wind farm energy storage optimization method of the present application;

[0046] Figure 3 is a normal distribution diagram of the power deviation of the first embodiment of the wind farm energy storage optimization method of the present application;

[0047] Figure 4 is a flowchart of the second embodiment of the wind farm energy storage optimization method of the present application;

[0048] Figure 5 is a flowchart of the third embodiment of the wind farm energy storage optimization method of the present application;

[0049] Figure 6 is a flowchart of the fourth embodiment of the wind farm energy storage optimization method of the present application;

[0050] Figure 7 A schematic diagram of a wind farm for an embodiment of the wind farm energy storage optimization method of the present application;

[0051] Figure 8 A control block diagram of an energy storage converter for an embodiment of the wind farm energy storage optimization method of the present application;

[0052] Figure 9 A structural block diagram of a first embodiment of the wind farm energy storage optimization device of the present application.

[0053] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are merely exemplary and not intended to limit the present application.

[0055] Reference Figure 1 , Figure 1 A structural schematic diagram of a wind farm energy storage optimization device related to the hardware operating environment of the embodiment of the present application.

[0056] As Figure 1 shown, the wind farm energy storage optimization device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 can include a display, an input unit such as a keyboard, and can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM), and can also be a stable non-volatile memory (NVM), such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0057] Those skilled in the art can understand that the structure shown in the Figure 1 above does not constitute a limitation on the wind farm energy storage optimization device, and can include more or fewer components than shown, or combine certain components, or different component arrangements.

[0058] As Figure 1As shown, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and a wind farm energy storage optimization program.

[0059] In Figure 1 In the wind farm energy storage optimization device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the wind farm energy storage optimization device of the application can be arranged in the wind farm energy storage optimization device, and the wind farm energy storage optimization device calls the wind farm energy storage optimization program stored in the memory 1005 through the processor 1001, and executes the wind farm energy storage optimization method provided by the embodiments of the application.

[0060] Based on the above-mentioned wind farm energy storage optimization device, the embodiments of the application provide a wind farm energy storage optimization method, which is described with reference to Figure 2 , Figure 2 The flowchart of the first embodiment of the wind farm energy storage optimization method of the application is shown.

[0061] In this embodiment, the wind farm energy storage optimization method includes the following steps:

[0062] Step S10: predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm.

[0063] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as a computer, or an electronic device or a wind farm energy storage optimization device capable of realizing the above functions. The following takes the computer as an example to describe the present embodiment and the following embodiments.

[0064] It can be understood that the present embodiment can first predict the parameters of the energy storage system of the wind farm to obtain the initial energy storage capacity and the initial energy storage power. The initial energy storage capacity refers to the predicted capacity of the energy storage system, and the initial energy storage power refers to the predicted power of the energy storage system.

[0065] Further, in order to effectively predict the initial energy storage capacity and the initial energy storage power, in the present embodiment, the step S10 includes: determining the predicted output and the actual output corresponding to the wind farm; determining the power deviation corresponding to the wind farm according to the predicted output and the actual output; predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm according to the power deviation.

[0066] It should be noted that the output refers to the total electric power generated by all wind turbine generators in the current wind farm, that is, the active power delivered by the current wind farm to the power grid, the predicted output refers to the predicted output in a preset time period, and the actual output refers to the actual output in a preset time period.

[0067] It can be understood that the power deviation corresponding to the wind farm can be determined according to the predicted output and the actual output, specifically, ΔP(t) = P act (t) - P for (t f ), wherein t represents a current time, ΔP(t) represents the power deviation, P act (t) represents the actual output, t f represents an output prediction interval, generally less than or equal to 15 minutes, P for (t f ) represents the predicted output. The initial energy storage capacity and the initial energy storage power corresponding to the wind farm can be predicted according to the power deviation ΔP(t).

[0068] Further, in order to effectively predict the initial energy storage capacity and the initial energy storage power, in the embodiment, the step of predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm according to the power deviation specifically comprises: determining the average value and the standard deviation corresponding to the power deviation; determining the initial energy storage capacity according to the average value and the standard deviation; determining the length of time when the power deviation is within a preset range, and determining the initial energy storage power according to the initial energy storage capacity and the length of time.

[0069] It should be understood that the power deviation ΔP(t) is determined according to the predicted output and the actual output. Figure 3 , Figure 3 is a normal distribution diagram of the power deviation of an embodiment of the wind farm energy storage optimization method. As shown in Figure 3 , the horizontal coordinate represents the power deviation ΔP(t), the vertical coordinate represents the probability density, μ represents the average value, and σ represents the standard deviation. According to the normal distribution, the average value μ and the standard deviation σ calculated satisfy the principle of 99.7% of the power deviation.

[0070] It can be understood that n parallel samples can be taken in the embodiment, and each sample can contain a plurality of power deviations, and the average value of each sample is , wherein j represents the sample number, μ j represents the average value, also represents the average value, i represents the number of samples contained in the jth sample, b represents the time corresponding to the last sample, t j (j = 1, 2,..., n) represents the time corresponding to the jth sample, and ΔP(t j ) represents the power deviation corresponding to t j . The standard deviation of each sample is , wherein σ j represents the standard deviation, is the standard deviation of the jth sample at t j .the power deviation average value in the time. The way of averaging and standard deviation can refer to the prior art, and the embodiment will not be described in detail.

[0071] It should be understood that the initial energy storage capacity can be predicted according to the average value and the standard deviation, and specifically, E BESS = max{|μ j - 3σ j |, |μ j + 3σ j |}, j = 1, 2, 3,..., n, wherein E BESS represents the initial energy storage capacity, μ j represents the average value, and σ j represents the standard deviation. The length of time during which the power deviation in each sample is within a preset range, i.e., the length of time during which the power deviation is positive or negative, can be in hours, and the energy storage power of each sample can be determined according to the initial energy storage capacity and the length of time, and specifically, E BESS = P B H, P B represents the energy storage power of each sample, H represents the length of time, and P BESS = max{P B1 , P B2 , P B3 ,..., P Bj}, P BESS represents the initial energy storage power, P B1 , P B2 , P B3 ,..., P Bj are the energy storage powers calculated for each sample.

[0072] Step S20: constructing a target population based on the initial energy storage capacity and the initial energy storage power.

[0073] It should be understood that the target population can be constructed based on the initial energy storage capacity and the initial energy storage power, and specifically, the initial energy storage capacity and the initial energy storage power can be taken as individuals, a plurality of initial energy storage capacities and corresponding initial energy storage powers are obtained by the above method, and the target population can include a plurality of individuals composed of the initial energy storage capacity and the initial energy storage power. A plurality of target populations can also be constructed, and the individuals in each target population can be different, and the number of individuals in each population is not limited in the embodiment.

[0074] Step S30: determining a set of fitness values corresponding to the optimal individuals in each target population, and performing energy storage optimization on the wind farm according to the minimum fitness value in the set of fitness values.

[0075] It should be understood that the fitness values of all individuals in each target population can be calculated, the fitness values can represent the advantages and disadvantages of the individuals, the fitness value corresponding to the optimal individual is the largest, therefore, the maximum fitness value corresponding to the individuals in each target population can be included in the fitness value set, the optimal individual in each target population can be obtained, and the optimal energy storage power and the optimal energy storage capacity corresponding to the optimal individual can be obtained.

[0076] It can be understood that the minimum fitness value in the fitness value set can be determined in the embodiment, and the optimal energy storage power and the optimal energy storage capacity corresponding to the minimum fitness value can be taken as the final energy storage power and the final energy storage capacity. In addition, after the minimum fitness value is selected, the iteration of the target population can be continued, and the wind farm can be further optimized based on the population after iteration. The embodiment can accelerate the speed of obtaining the final energy storage power and the final energy storage capacity, and improve the convergence in the iteration process, by determining the minimum fitness value.

[0077] The embodiment can predict the initial energy storage capacity and the initial energy storage power corresponding to the wind farm, construct the target population based on the initial energy storage capacity and the initial energy storage power, determine the fitness value set corresponding to the optimal individual in each target population, and optimize the energy storage of the wind farm based on the minimum fitness value in the fitness value set. The embodiment can obtain the energy storage prediction result by predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm, construct a plurality of target populations based on the initial energy storage capacity and the initial energy storage power, determine the fitness value set corresponding to the optimal individual in each target population, obtain the optimal energy storage capacity and the optimal energy storage power in each target population, and optimize the energy storage of the wind farm based on the minimum fitness value in the fitness value set. Therefore, the speed of energy storage optimization can be accelerated, and the optimal energy storage configuration mode can be obtained, by optimizing the energy storage of the wind farm based on the minimum fitness value corresponding to all target populations.

[0078] Reference Figure 4 , Figure 4 The figure is a flowchart of the second embodiment of the wind farm energy storage optimization method.

[0079] Based on the first embodiment, in the embodiment, the step S20 includes:

[0080] Step S201: Construct an initial population based on the initial energy storage capacity and the initial energy storage power, and process the initial population by a genetic algorithm to obtain a processed population.

[0081] It can be understood that the initial population can be processed by a genetic algorithm after the initial population is constructed, and the processed population can be obtained by specific processing such as crossover, selection, and mutation.

[0082] It should be understood that when the initial population quantity is 2, the particle swarm algorithm and the differential fusion algorithm can be processed respectively, and specifically, the initial population corresponding to the particle swarm algorithm can be updated in power and capacity, and the update formula is as follows:

[0083]

[0084] In the formula, is the historical optimal energy storage capacity of the i-th particle at the t-th iteration, g(best) t is the population optimal energy storage capacity at the t-th iteration, w is the inertia weight, c1 and c2 are constants, and r1 and r2 are two random numbers independent of each other and subject to U∈(0, 1).

[0085] In a specific implementation, the initial population corresponding to the differential fusion algorithm can be processed by crossing, selecting, mutating, etc. Specifically, the formula used for crossing processing is as follows:

[0086]

[0087] In the formula, rand is a random number in [0, 1], and CR is a constant in [0, 1] and is called a crossover variable.

[0088] The formula used for selection processing is as follows:

[0089]

[0090] In the formula, u i is a competing individual, x i is a target individual.

[0091] The formula used for mutation processing is as follows:

[0092] vi=x r1 +F*(x r2 -x r3 );

[0093] In the formula, x r1 , x r2 , and x r3 are three different individuals randomly selected from the parent population and have different individual values, and F is a scaling factor between [0, 2].

[0094] Step S202: Distribute the individuals in the processed population to a plurality of preset populations, and initialize the particles in each preset population to obtain a plurality of initialized populations.

[0095] It should be understood that the processed population can be one or several, all individuals in all processed populations can be determined, and then all individuals are distributed into several preset populations, the number of preset populations can be one or multiple, and the preset populations in the embodiment are preferably two, which can be processed by the particle swarm algorithm and the differential fusion algorithm respectively.

[0096] It should be understood that the particles in each preset population can be initialized first, and the particle initialization formula is:

[0097]

[0098] In the formula, h k is the initialized particle of the kth iteration of the particle in the particle swarm algorithm, h k is the initialized particle of the kth iteration of the particle in the differential fusion algorithm.

[0099] Step S203: correcting each initialized population to obtain several target populations.

[0100] It should be understood that each initialized population can be corrected respectively, and correction refers to correcting the out-of-bound particles in the initialized population to obtain several target populations.

[0101] Further, in order to effectively correct each initialized population, in the embodiment, the step S203 includes: determining the correction mode corresponding to each initialized population, the correction mode including: the particle swarm correction mode corresponding to the particle swarm algorithm and the differential fusion correction mode corresponding to the differential fusion algorithm; and correcting the particles in each initialized population according to the particle swarm correction mode and the differential fusion correction mode respectively to obtain several target populations.

[0102] It should be understood that the correction mode in the embodiment can include: the particle swarm correction mode corresponding to the particle swarm algorithm and the differential fusion correction mode corresponding to the differential fusion algorithm, the particle swarm correction mode refers to the correction mode of the speed and position of the particle, and the differential fusion correction mode refers to the correction mode of the particle performing selection, hybridization, mutation operation and correcting the out-of-bound particles.

[0103] It should be understood that the particle swarm correction can be performed by the following formula:

[0104]

[0105] In the formula, u k is the corrected particle of the kth iteration of the particle in the particle swarm algorithm, u max , u minare the upper and lower limits of the particle motion range respectively, γ is the mutation rate, and r is a random number between 0 and 1.

[0106] In a specific implementation, the differential fusion correction manner can be to perform selection, crossover, and mutation operations on each particle in the corresponding population, and to correct the particles that exceed the boundary, that is, the particles whose speed and position exceed the boundary of the population. The initialized population in this embodiment can be two, and in this case, the particle swarm correction manner and the differential fusion correction manner can be used for correction respectively. If the initialized population is three, two of the initialized populations can be corrected by using the particle swarm correction manner, and one of the initialized populations can be corrected by using the differential fusion correction manner. Alternatively, one of the initialized populations can be corrected by using the particle swarm correction manner, and two of the initialized populations can be corrected by using the differential fusion correction manner. The number of the initialized populations is not specifically limited in this embodiment, and the correction manner corresponding to each initialized population is also not specifically limited.

[0107] In this embodiment, the initial population is constructed based on the initial energy storage capacity and the initial energy storage power, the initial population is processed by using the genetic algorithm, the processed population is obtained, the individuals in the processed population are distributed into a plurality of preset populations, the particles in each preset population are initialized, a plurality of initialized populations are obtained, and each initialized population is corrected to obtain a plurality of target populations. In this embodiment, the particles in each preset population are initialized, and each initialized population is corrected to obtain a plurality of target populations. The preset population can be initialized by using the particle swarm algorithm or the differential fusion algorithm, and the initialized population can be corrected, so that the target population is more in line with the actual requirements.

[0108] Reference Figure 5 , Figure 5 FIG. 3 is a flowchart of a wind farm energy storage optimization method according to a third embodiment of the present application.

[0109] Based on the above embodiments, in this embodiment, the step S30 includes:

[0110] Step S301: determining a set of individual fitness values corresponding to each individual in each target population, and determining an optimal individual in each target population according to the set of individual fitness values.

[0111] It can be understood that this embodiment can determine the individual fitness values corresponding to each individual in each target population, and form a set of fitness values. The fitness values can be determined according to the objective function in the prior art, and details are not described herein.

[0112] It should be understood that the optimal individual in each target population refers to the individual corresponding to the maximum fitness value. Therefore, in this embodiment, the fitness value corresponding to all individuals in each target population can be determined, and the individual corresponding to the maximum fitness value is the optimal individual in each target population.

[0113] Step S302: Determine the set of fitness values ​​corresponding to the best individual in each target population, and determine the minimum fitness value in the fitness value set.

[0114] Understandably, the fitness value set can contain the fitness of the best individual in each target population, and it is necessary to determine the minimum value in the fitness value set, i.e., the minimum fitness value.

[0115] In practical implementation, when there are two target populations, namely P PSO and P DE Population P can be calculated PSO and P DE The optimal individual and If we take the fitness value of the two populations and select the smaller fitness value as the overall extreme value in the k-th iteration, then we have:

[0116]

[0117] In the formula, and represents the fitness value corresponding to the best individual in the two populations.

[0118] Step S303: When the minimum fitness value is less than the preset fitness value, optimize the energy storage of the wind farm according to the minimum fitness value.

[0119] It should be understood that the preset fitness value refers to a pre-set fitness value used to determine whether the minimum fitness value meets the requirements. When the minimum fitness value is less than the preset fitness value, energy storage optimization of the wind farm can be performed based on the minimum fitness value. When the minimum fitness value is greater than or equal to the preset fitness value, the minimum fitness value corresponding to each target population can be recalculated until the minimum fitness value is less than the preset fitness value.

[0120] Furthermore, in order to effectively optimize the energy storage of the wind farm, in this embodiment, step S303 includes: when the minimum fitness value is less than the preset fitness value, returning to the step of correcting each initialized population to obtain several target populations and obtaining a new fitness value; obtaining the current iteration number, and when the current iteration number is greater than the preset iteration number, optimizing the energy storage of the wind farm according to the new energy storage capacity and new energy storage power corresponding to the new fitness value.

[0121] It can be understood that when the minimum fitness value is less than the preset fitness value, the initialized population can continue to be corrected, that is, returning to the step of correcting the initialized population to obtain a new target population, and the new target population will also correspond to a new fitness value.

[0122] It should be understood that the current iteration number can be the number of times of correcting the initialized population, and the preset iteration number refers to the preset iteration number. When the current iteration number is greater than the preset iteration number, it can be determined that the new fitness value corresponding to the target population after iteration is completed, which is the minimum fitness value after iteration is completed. The individual corresponding to the new fitness value is the new energy storage capacity and the new energy storage power, that is, the new energy storage capacity and the new energy storage power can be used as the capacity and power corresponding to the energy storage system of the wind farm.

[0123] Further, in order to determine whether the optimized energy storage capacity and the optimized energy storage power need to be optimized again, in the embodiment, after the step S30, the method further comprises: obtaining the optimized energy storage capacity and the optimized energy storage power; determining the wind farm curtailment rate according to the optimized energy storage capacity and the optimized energy storage power; and determining whether the wind farm needs to be optimized again according to the wind farm curtailment rate.

[0124] It can be understood that the wind farm curtailment rate refers to the wind farm curtailment rate corresponding to the wind farm when the energy storage system in the wind farm works at the optimized energy storage capacity and the optimized energy storage power. Specifically, the battery capacity can be calculated according to the optimized energy storage capacity and the optimized energy storage power, and the wind farm curtailment rate can be calculated by the following formula:

[0125]

[0126] In the formula, f is the objective function of the wind farm curtailment rate, T is the scheduling period, ΔP(t) represents the power deviation, C bat.N is the maximum capacity of the battery, C bat (t-1) is the maximum capacity of the battery at t-1, S L (t) is a Boolean quantity indicating whether there is wind curtailment phenomenon in the wind farm at t, and the value is

[0127] In specific implementation, after the wind farm curtailment rate is calculated, if it is less than a preset threshold, it means that the optimized energy storage capacity and the optimized energy storage power obtained meet the requirements and do not need to be optimized again. If it is greater than or equal to the preset threshold, the optimized energy storage capacity and the optimized energy storage power need to be optimized again by the above method.

[0128] The embodiment determines the individual fitness value set corresponding to each individual in each target population, determines the optimal individual in each target population according to the individual fitness set, then determines the fitness value set corresponding to the optimal individual in each target population, and determines the minimum fitness value in the fitness value set, and when the minimum fitness value is less than the preset fitness value, the wind farm is optimized according to the minimum fitness value. The embodiment can obtain the optimal individual in each target population, that is, the optimal energy storage capacity and the optimal energy storage power, by determining the fitness value set corresponding to the optimal individual in each target population, and can speed up the energy storage optimization speed and obtain the optimal energy storage configuration mode by optimizing the energy storage of the wind farm according to the minimum fitness value corresponding to all populations.

[0129] Reference Figure 6 , Figure 6 The figure is a flowchart of the fourth embodiment of the wind farm energy storage optimization method.

[0130] Based on the above embodiments, after step S30, the method further includes:

[0131] Step S40: When the operating state of the power grid corresponding to the wind farm is a transient fault, the voltage drop of the grid-connected point is determined.

[0132] It should be noted that the wind farm in the embodiment can include n wind turbines and n energy storage systems, and the energy storage system can be a VRB energy storage converter. For details, refer to Figure 7 , Figure 7 The figure is a schematic diagram of the wind farm of the first embodiment of the wind farm energy storage optimization method. Figure 7 DC / DC in the figure represents a direct current converter, DC / AC represents direct current to alternating current, l1 and l2 represent resistors, and the two rings in the equivalent circuit resistor represent transformers, including 690V / 35KV, 35KV / 220V, 35KV / 380V, and VRB represents an energy storage converter. In the embodiment, part of the electricity generated by the n wind turbines is output to the VRB energy storage converter for energy storage, and part of the electricity is output to the power grid for power supply to the equipment connected to the power grid.

[0133] It should be understood that, for details, refer to Figure 8 , Figure 8 The figure is a control block diagram of the energy storage converter of the first embodiment of the wind farm energy storage optimization method. The grid voltage oriented control is adopted, the voltage vector at the low voltage side of the AC transformer of the energy storage system is oriented to the d-axis of the synchronous coordinate system, that is, u d = u g , u a= 0, the voltage and power of the energy storage converter can be decomposed into d, q axis components to calculate respectively. Thus the voltage level of this side is quantified, and the positive feedback adjusts the generator output on this route. The formula is as follows:

[0134]

[0135]

[0136] In the formula, u * d , u * q are d, q axis components of the energy storage converter voltage respectively, i d , i q are d, q axis components of the energy storage converter current respectively, R, L are resistance and inductance of the filter respectively, u d , u q are d, q axis components of the grid voltage respectively.

[0137] It should be understood that the grid operating state can include a steady state operating state and a transient fault, when the grid operating state is the steady state operating state, i.e. the grid voltage, current and the like are in a stable state, the upper pass of the active and reactive channels is selected, and the reactive current The energy storage converter operates in a unity power factor state, and the charging and discharging power is all active power, and the energy storage system works in an active suppression state.

[0138] In a specific implementation, when the grid operating state is a transient fault, i.e. the grid voltage, current and the like have a temporary fault, after the mode switching system detects a grid voltage drop signal, a judgment step is entered, and it is necessary to determine the grid point voltage drop V drop .

[0139] Step S50: When the grid point voltage drop is greater than a preset voltage drop, the active channel corresponding to the energy storage system in the wind farm is blocked, the reactive channel is selected, and a reactive compensation state is entered to provide reactive support to the grid corresponding to the wind farm.

[0140] It can be understood that the preset voltage drop can be set to 10%, 11% and the like, and the embodiment does not make specific limitation thereon. When the grid point voltage drop is less than or equal to the preset voltage drop, the energy storage system continues to work in the active suppression state.

[0141] It should be understood that when the grid point voltage drop is greater than the preset voltage drop, the mode switching is performed by changing the given reference value of the active and reactive current inner loop, the lower pass of the active and reactive channels is selected, and the reactive compensation state is entered. The given q axis reactive current reference value is the rated current of the energy storage converter, i.e. The reactive channel is gated, so that the energy storage converter generates reactive power to the maximum extent, and at the same time The active current reference value is limited to 0, the active channel is blocked, and reactive support is provided to the power grid.

[0142] The embodiment determines the voltage drop at the grid-connected point when the operating state of the power grid corresponding to the wind farm is a transient fault, blocks the active channel corresponding to the energy storage system in the wind farm when the voltage drop at the grid-connected point is greater than the preset voltage drop, and gates the reactive channel, enters the reactive compensation state, and provides reactive support to the power grid corresponding to the wind farm. The embodiment realizes that the hybrid energy storage system can effectively smooth the active power output of the wind farm when the power grid is in a steady state, the energy storage system provides stable reactive support to the power grid to the maximum extent during a transient fault of the power grid, and the voltage at the grid-connected point of the wind farm is raised, thereby avoiding the negative effects of voltage drop.

[0143] Referring to Figure 9 , Figure 9 The structure block diagram of the first embodiment of the wind farm energy storage optimization device of the present application is shown.

[0144] As shown in Figure 9 , the wind farm energy storage optimization device provided by the embodiment of the present application comprises:

[0145] An energy storage prediction module 10 is configured to predict the initial energy storage capacity and the initial energy storage power corresponding to the wind farm.

[0146] A population construction module 20 is configured to construct a target population based on the initial energy storage capacity and the initial energy storage power.

[0147] An energy storage optimization module 30 is configured to determine a set of fitness values corresponding to the optimal individual in each target population, and to optimize the energy storage of the wind farm according to the minimum fitness value in the set of fitness values.

[0148] The embodiment predicts the initial energy storage capacity and the initial energy storage power corresponding to the wind farm, then constructs target populations based on the initial energy storage capacity and the initial energy storage power, determines the fitness value set corresponding to the optimal individual in each target population, and optimizes the energy storage of the wind farm according to the minimum fitness value in the fitness value set. The embodiment can obtain the energy storage prediction result by predicting the initial energy storage capacity and the initial energy storage power corresponding to the wind farm, then construct several target populations based on the initial energy storage capacity and the initial energy storage power, determine the optimal energy storage capacity and the optimal energy storage power in each target population according to the fitness value set corresponding to the optimal individual in each target population, and optimize the energy storage of the wind farm according to the minimum fitness value in the fitness value set, so as to optimize the energy storage of the wind farm according to the minimum fitness value corresponding to all target populations, thereby accelerating the speed of energy storage optimization and obtaining the optimal energy storage configuration mode.

[0149] It should be noted that the above-described workflow is only illustrative and does not limit the protection scope of the present application. In actual application, a person skilled in the art can select part or all of them to achieve the purpose of the embodiment scheme according to actual needs, which is not limited here.

[0150] In addition, technical details not described in detail in the embodiment can be referred to the wind farm energy storage optimization method provided by any embodiment of the present application, which will not be described here.

[0151] Based on the first embodiment of the wind farm energy storage optimization device of the present application, the second embodiment of the wind farm energy storage optimization device of the present application is proposed.

[0152] In the embodiment, the energy storage prediction module 10 is further configured to determine the predicted output and the actual output corresponding to the wind farm, determine the power deviation corresponding to the wind farm according to the predicted output and the actual output, and predict the initial energy storage capacity and the initial energy storage power corresponding to the wind farm according to the power deviation.

[0153] Further, the energy storage prediction module 10 is further configured to determine the average value and the standard deviation corresponding to the power deviation, determine the initial energy storage capacity according to the average value and the standard deviation, determine the duration of the power deviation within the preset range, and determine the initial energy storage power according to the initial energy storage capacity and the duration.

[0154] Further, the population constructing module 20 is further configured to construct an initial population based on the initial energy storage capacity and the initial energy storage power, and process the initial population by a genetic algorithm to obtain a processed population; distribute individuals in the processed population to a plurality of preset populations, and initialize particles in each preset population to obtain a plurality of initialized populations; and correct each initialized population to obtain a plurality of target populations.

[0155] Further, the population constructing module 20 is further configured to determine a correction mode corresponding to each initialized population, the correction mode including a particle swarm correction mode corresponding to a particle swarm algorithm and a differential fusion correction mode corresponding to a differential fusion algorithm; and correct particles in each initialized population according to the particle swarm correction mode and the differential fusion correction mode to obtain a plurality of target populations.

[0156] Further, the energy storage optimizing module 30 is further configured to determine a set of individual fitness values corresponding to each individual in each target population, and determine an optimal individual in each target population according to the set of individual fitness values; determine a set of fitness values corresponding to the optimal individual in each target population, and determine a minimum fitness value in the set of fitness values; and when the minimum fitness value is less than a preset fitness value, optimize energy storage of the wind farm according to the minimum fitness value.

[0157] Further, the energy storage optimizing module 30 is further configured to, when the minimum fitness value is less than a preset fitness value, return to the step of correcting each initialized population to obtain a plurality of target populations to obtain a new fitness value; obtain a current iteration number, and when the current iteration number is greater than a preset iteration number, optimize energy storage of the wind farm according to a new energy storage capacity and a new energy storage power corresponding to the new fitness value.

[0158] Further, the energy storage optimizing module 30 is further configured to obtain an optimized energy storage capacity and an optimized energy storage power; determine a wind farm curtailment rate according to the optimized energy storage capacity and the optimized energy storage power; and determine whether the wind farm needs to be optimized again according to the wind farm curtailment rate.

[0159] Further, the energy storage optimizing module 30 is further configured to, when an operating state of a power grid corresponding to the wind farm is a transient fault, determine a point of common coupling voltage drop; when the point of common coupling voltage drop is greater than a preset voltage drop, block an active channel corresponding to an energy storage system in the wind farm, and select a gate of a reactive channel to enter a reactive power compensation state to provide reactive power support to the power grid corresponding to the wind farm.

[0160] Other embodiments or specific implementations of the wind farm energy storage optimization device of the present application can refer to the above-mentioned method embodiments, which will not be described here.

[0161] In addition, the embodiment of the present application also proposes a storage medium, the storage medium stores a wind farm energy storage optimization program, the wind farm energy storage optimization program is executed by the processor to realize the steps of the wind farm energy storage optimization method as described above.

[0162] It should be noted that in this paper, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or system. Without more limitations, the element defined by the sentence "includes a" does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0163] The above-mentioned embodiment number of the present application is only for description, not representing the pros and cons of the embodiment.

[0164] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by software plus the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of software product, which is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk), including a number of instructions to make a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the method described in each embodiment of the present application.

[0165] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, any equivalent structure or equivalent flow transformation made by using the content of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for optimizing energy storage in wind farms, characterized in that, The wind farm energy storage optimization method includes the following steps: Predict the initial energy storage capacity and initial energy storage power corresponding to the wind farm; Construct a target population based on the initial energy storage capacity and the initial energy storage power; Determine the set of fitness values ​​corresponding to the optimal individuals in each target population, and optimize the energy storage of the wind farm based on the minimum fitness value in the set of fitness values; The step of constructing the target population based on the initial energy storage capacity and the initial energy storage power specifically includes: An initial population is constructed based on the initial energy storage capacity and the initial energy storage power, and the initial population is processed by a genetic algorithm to obtain a processed population. Individuals in the processed population are assigned to several preset populations, and the particles in each preset population are initialized to obtain several initialized populations. Determine the correction method corresponding to each initialized population, the correction method including: particle swarm correction method corresponding to particle swarm algorithm and differential fusion correction method corresponding to differential fusion algorithm; The particles in each initialized population are corrected according to the particle swarm correction method and the differential fusion correction method to obtain several target populations.

2. The wind farm energy storage optimization method as described in claim 1, characterized in that, The steps for predicting the initial energy storage capacity and initial energy storage power corresponding to the wind farm specifically include: Determine the predicted and actual power output of the wind farm; The power deviation of the wind farm is determined based on the predicted output and the actual output. The initial energy storage capacity and initial energy storage power of the wind farm are predicted based on the power deviation.

3. The wind farm energy storage optimization method as described in claim 2, characterized in that, The step of predicting the initial energy storage capacity and initial energy storage power of the wind farm based on the power deviation specifically includes: Determine the average value and standard deviation corresponding to the power deviation; The initial energy storage capacity is determined based on the average value and the standard deviation. The duration during which the power deviation remains within a preset range is determined, and the initial energy storage power is determined based on the initial energy storage capacity and the duration.

4. The wind farm energy storage optimization method as described in claim 1, characterized in that, The step of determining the set of fitness values ​​corresponding to the optimal individuals in each target population, and optimizing the energy storage of the wind farm based on the minimum fitness value in the set of fitness values, specifically includes: Determine the set of individual fitness values ​​corresponding to each individual in each target population, and determine the optimal individual in each target population based on the set of individual fitness values; Determine the set of fitness values ​​corresponding to the best individual in each target population, and determine the minimum fitness value in the set of fitness values; When the minimum fitness value is less than the preset fitness value, the wind farm is optimized for energy storage based on the minimum fitness value.

5. The wind farm energy storage optimization method as described in claim 4, characterized in that, The step of optimizing the energy storage of the wind farm based on the minimum fitness value when the minimum fitness value is less than the preset fitness value specifically includes: When the minimum fitness value is less than the preset fitness value, return to the step of correcting each initialized population to obtain several target populations and obtain a new fitness value; Obtain the current iteration number. When the current iteration number is greater than the preset iteration number, optimize the energy storage of the wind farm based on the new energy storage capacity and new energy storage power corresponding to the new fitness value.

6. The wind farm energy storage optimization method according to any one of claims 1 to 5, characterized in that, After determining the set of fitness values ​​corresponding to the optimal individuals in each target population, and optimizing the energy storage of the wind farm based on the minimum fitness value in the set of fitness values, the method further includes: Obtain the optimized energy storage capacity and optimized energy storage power; The wind curtailment rate of the wind farm is determined based on the optimized energy storage capacity and the optimized energy storage power. Determine whether further energy storage optimization of the wind farm is needed based on the wind curtailment rate of the wind farm.

7. The wind farm energy storage optimization method according to any one of claims 1 to 5, characterized in that, After determining the set of fitness values ​​corresponding to the optimal individuals in each target population, and optimizing the energy storage of the wind farm based on the minimum fitness value in the set of fitness values, the method further includes: When the grid operating state corresponding to the wind farm is a transient fault, a voltage drop at the grid connection point is determined. When the voltage drop at the grid connection point exceeds a preset voltage drop, the active power channel corresponding to the energy storage system in the wind farm is blocked, and the reactive power channel is selected to enter a reactive power compensation state, so as to provide reactive power support to the power grid corresponding to the wind farm.

8. A wind farm energy storage optimization device, characterized in that, The wind farm energy storage optimization device includes: The energy storage prediction module is used to predict the initial energy storage capacity and initial energy storage power of the wind farm. A population building module is used to build a target population based on the initial energy storage capacity and the initial energy storage power. An energy storage optimization module is used to determine the set of fitness values ​​corresponding to the best individuals in each target population, and to optimize the energy storage of the wind farm based on the minimum fitness value in the set of fitness values. The population construction module is further configured to construct an initial population based on the initial energy storage capacity and the initial energy storage power, and process the initial population using a genetic algorithm to obtain a processed population; assign individuals in the processed population to several preset populations, and initialize the particles in each preset population to obtain several initialized populations; determine the correction method corresponding to each initialized population, the correction method including: particle swarm correction method corresponding to the particle swarm algorithm and differential fusion correction method corresponding to the differential fusion algorithm; and correct the particles in each initialized population according to the particle swarm correction method and the differential fusion correction method to obtain several target populations.

9. A wind farm energy storage optimization device, characterized in that, The device includes: a memory, a processor, and a wind farm energy storage optimization program stored in the memory and executable on the processor, the wind farm energy storage optimization program being configured to implement the steps of the wind farm energy storage optimization method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a wind farm energy storage optimization program, which, when executed by a processor, implements the steps of the wind farm energy storage optimization method as described in any one of claims 1 to 7.

Images