A wind farm distributed control method and device based on data-driven sensitivity, equipment and medium

Abstract

The application discloses a wind farm distributed control method and device based on data-driven sensitivity, equipment and medium, and relates to the field of wind farm control. The method comprises the following steps: estimating wind farm state variables by using a data-driven model, calculating the gradient of the data-driven model by using a back propagation algorithm, determining power data-driven sensitivity and voltage data-driven sensitivity; calculating mathematical voltage sensitivity by using a mathematical analysis method based on the estimated wind farm state variables; calculating loss functions under different control modes based on the power data-driven sensitivity, the voltage data-driven sensitivity and the mathematical voltage sensitivity; converting nonlinear constraint conditions into linear constraint conditions by using a variable interval constraint linearization method, solving the loss functions, and determining control reference values of wind turbines; and controlling the wind turbines of the wind farm based on the control reference values of the wind turbines. The application can realize distributed control of the wind farm and improve the control effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wind farm control, and particularly relates to a wind farm distributed control method based on data-driven sensitivity, a device, equipment and medium. BACKGROUND

[0002] As a leading renewable energy, the rapid development of wind power matches the complex power dispatching challenges of wind farms. The research on wind farm optimization control has become the key to improving efficiency, reducing cost, enhancing the stability and reliability of wind power systems. With the continuous increase in the number of wind turbine generators, the control dimension has also been greatly improved, and the traditional centralized control method cannot meet the requirements of large-scale wind farm control. Therefore, it is urgent to realize the rapid control of wind farms. SUMMARY

[0003] The purpose of the present application is to provide a wind farm distributed control method based on data-driven sensitivity, device, equipment and medium, which can realize the distributed control of wind farms and effectively improve the control effect.

[0004] To achieve the above purpose, the present application provides the following solutions:

[0005] In a first aspect, the present application provides a wind farm distributed control method based on data-driven sensitivity, comprising:

[0006] Based on the operation data of local wind turbine generators, the data-driven model is used to estimate the wind farm state quantity;

[0007] Based on the estimated wind farm state quantity, the gradient of the data-driven model is calculated using the back propagation algorithm to determine the power data-driven sensitivity and the voltage data-driven sensitivity;

[0008] Based on the estimated wind farm state quantity, the mathematical analysis method is used to calculate the mathematical voltage sensitivity;

[0009] Based on the power data-driven sensitivity, the voltage data-driven sensitivity and the mathematical voltage sensitivity, the loss function under different control modes is calculated;

[0010] The nonlinear constraint condition is converted into a linear constraint condition based on the variable interval constraint linearization method;

[0011] Based on the linear constraint condition, the loss function under different control modes is solved to determine the control reference value of each wind turbine generator;

[0012] Based on the control reference value of each wind turbine generator, each wind turbine generator of the wind farm is controlled.

[0013] In a second aspect, the application provides a wind farm decentralized control device based on data-driven sensitivity, comprising:

[0014] a wind farm state quantity prediction module configured to estimate wind farm state quantities by using a data-driven model based on operation data of local wind turbines;

[0015] a data-driven sensitivity determination module configured to calculate gradients of the data-driven model by using a back propagation algorithm based on the estimated wind farm state quantities, and determine power data-driven sensitivity and voltage data-driven sensitivity;

[0016] a mathematical method voltage sensitivity calculation module configured to calculate mathematical method voltage sensitivity based on the estimated wind farm state quantities;

[0017] a loss function calculation module configured to calculate loss functions under different control modes based on the power data-driven sensitivity, the voltage data-driven sensitivity and the mathematical method voltage sensitivity;

[0018] a conversion module configured to convert nonlinear constraint conditions into linear constraint conditions by using a variable distance constraint linearization method;

[0019] a control reference value determination module configured to determine control reference values of wind turbines based on the linear constraint conditions and the loss functions under different control modes;

[0020] a control module configured to control wind turbines of a wind farm based on the control reference values of the wind turbines.

[0021] In a third aspect, the application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the wind farm decentralized control method based on data-driven sensitivity.

[0022] In a fourth aspect, the application provides a computer readable storage medium, which stores a computer program executable by a processor to implement the wind farm decentralized control method based on data-driven sensitivity.

[0023] According to the embodiments provided in the application, the application has the following technical effects:

[0024] The application provides a wind farm distributed control method and device based on data-driven sensitivity, a data-driven sensitivity (including power data-driven sensitivity and voltage data-driven sensitivity) can be determined through operation data of a local wind turbine and a data-driven model, a loss function under different control modes can be determined in combination with a mathematical voltage sensitivity, a control reference value of each wind turbine can be determined by solving the loss function, and control of each wind turbine is realized. In the above distributed control process, the local wind turbine has no need to communicate with a central processor or an adjacent wind turbine controller, and the control speed and effect are improved. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0026] Figure 1 A flowchart of a wind farm distributed control method based on data-driven sensitivity provided by an embodiment of the present application is shown in the figure.

[0027] Figure 2 A principle framework diagram of a wind farm distributed control method based on data-driven sensitivity provided by an embodiment of the present application is shown in the figure.

[0028] Figure 3 A structure diagram of a computer device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort fall within the scope of protection of the present application.

[0030] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0031] In an exemplary embodiment, as shown in Figures 1-2As shown, a data-driven sensitivity-based wind farm decentralized control method is provided, which is executed by a computer device, specifically, can be executed by a terminal or a server, or both, in the embodiments of the present application, the method is applied to the server, and includes the following steps S1 to S7. Wherein:

[0032] S1: based on the operation data of the local wind turbine, the data-driven model is used to estimate the wind farm state quantity.

[0033] S2: based on the estimated wind farm state quantity, the gradient of the data-driven model is calculated using the back propagation algorithm, and the power data-driven sensitivity and the voltage data-driven sensitivity are determined.

[0034] S3: based on the estimated wind farm state quantity, the mathematical analysis method is used to calculate the mathematical voltage sensitivity.

[0035] S4: based on the power data-driven sensitivity, the voltage data-driven sensitivity and the mathematical voltage sensitivity, the loss function under different control modes is calculated.

[0036] S5: the nonlinear constraint condition is converted into a linear constraint condition based on the variable interval constraint linearization method.

[0037] S6: based on the linear constraint condition, the loss function under different control modes is solved, and the control reference value of each wind turbine is determined.

[0038] S7: based on the control reference value of each wind turbine, the wind turbines of the wind farm are controlled.

[0039] In a specific embodiment, step S1 specifically includes:

[0040] The data-driven model uses a deep learning model to learn the relationship between the operation data of the local wind turbine and the global state quantity of the nodes and wind turbines in the wind farm at the current time. In this embodiment, the Seg-RNN model is used as an example to construct the data-driven model.

[0041] Due to the different characteristics of each operation data, a corresponding mapping model will be built for each variable in the data-driven model. The formula of the mapping model is as follows:

[0042] V g =DDM(V i )

[0043] V i =[U i ,θ i ,P i ,Q i ]

[0044]

[0045] where DDM denotes the data-driven model, V i represents the historical operation data of the i-th wind turbine (local wind turbine). N g is the data length of V i . i,l , θ i,l , P i,l , Q i,l represents the voltage amplitude, phase angle, active power and reactive power of the i-th wind turbine at the l-th time step. V g represents the state quantity of the wind farm estimated by the data-driven model.

[0046] In a specific embodiment, step S2 specifically comprises:

[0047] The present application calculates the gradient of the output of the data-driven model with respect to the input by using the forward propagation, loss calculation and back propagation of the back propagation algorithm.

[0048] Step 1: input V i into the data-driven model to obtain V g .

[0049] Step 2: define V g as the loss function value.

[0050] Step 3: calculate the gradient of V g with respect to P i and Q i by back propagation. V g may be the voltage of each node in the wind farm or the active and reactive power of each wind turbine.

[0051] The gradient of the voltage of each node in the wind farm with respect to P i and Q i is defined as the voltage data-driven sensitivity, and the gradient of the active and reactive power of each wind turbine with respect to P i and Q i is defined as the power data-driven sensitivity.

[0052] This embodiment takes the Seg-RNN model as an example to introduce how to calculate the voltage data-driven sensitivity and the power data-driven sensitivity.

[0053] The encoder part of the Seg-RNN model retains the transfer structure of the traditional RNN, but changes the input of each cycle unit to sequence data. Taking the GRU structure of the Seg-RNN model encoder as an example, the formula is as follows:

[0054] z t = σ(W zx ·xt +W zh ·h (t-1) +b z ) ↓

[0055] r t =σ(W rx ·x t +W rh ·h (t-1) +b r ) ↓

[0056]

[0057] where σ denotes the sigmoid function. x t is the input sequence data of the GRU unit. z t and r t correspond to the update gate and the reset gate that control the information flow. represents the candidate hidden state, mainly responsible for preserving information. h t is the hidden state output by the unit. W zx , W zh , W rx , W rx , W hh and W hx are the learnable weights corresponding to the variables, b z , b r and b h are learnable biases. “·” denotes matrix multiplication. denotes element-wise multiplication.

[0058] When calculating the GRU unit for the kth time, x t is the kth segment of sequence information V i split by V i k is obtained through a fully connected layer, and the formula is as follows:

[0059]

[0060] where W x,k and denote the learnable weights and biases that convert V i k into x t . y k denotes the output of the kth data-driven model, representing the estimated value of the state quantity of other nodes. denotes the hidden state of the kth data-driven model in the decoder. and denote the conversion of into yk The learnable weights and biases.

[0061] The i-th local controller uses the back propagation algorithm to calculate the data-driven model output y k For the active power P of the i-th wind turbine i and reactive power Q i The gradient of . The calculation formula of data-driven sensitivity is as follows:

[0062]

[0063]

[0064] The resulting gradient and This is data-driven sensitivity. In this embodiment, a total of four data-driven models are constructed to estimate the voltage and phase of each node in the wind farm, and the active power and reactive power of each wind turbine. k (k=1,2,3,4) represents the global voltage, phase, active power and reactive power output by the data-driven model. k When is voltage, and is the voltage data drive sensitivity, y k When is active power and reactive power, and is the power data driving sensitivity.

[0065] In a specific embodiment, step S3 specifically includes:

[0066] Calculate the voltage U of the i-th node using mathematical analysis i and phase θ i The active power P of the first wind turbine l and reactive power Q l Sensitivity of phase to active power and reactive power is a mathematical relationship used to describe how changes in voltage phase angle (θ) affect changes in active power (P) and reactive power (Q). The formula is as follows:

[0067]

[0068] in, express The conjugation of .

[0069] In a specific embodiment, step S4 specifically comprises: calculating a loss function in the first control mode based on the voltage data-driven sensitivity and the wind farm state space equation; determining a local prediction model according to the power data-driven sensitivity and the wind farm state space equation; calculating a loss function in the second control mode based on the local prediction model and the mathematical method voltage sensitivity; and calculating a loss function in the third control mode based on the local prediction model and the voltage-driven data sensitivity.

[0070] When the wind farm network parameters are not accurate and accurate calculation is required, the loss function in the first control mode is used; when the wind farm network parameters are accurate and fast calculation is required, the loss function in the second control mode is used; and when the wind farm network parameters are not accurate and fast calculation is required, the loss function in the third control mode is used.

[0071] This embodiment takes the control target as power tracking and voltage stability maintenance as an example to illustrate the construction process of the loss function. The method can also be used in other scenarios.

[0072] Considering the time delay of the control system, the active power and reactive power regulation of the wind turbine can be expressed as:

[0073]

[0074] where ΔP WT is the active power increment; s is a complex variable; is the time delay coefficient of the active power; is the active power increment reference value; ΔQ WT is the reactive power increment; is the time delay coefficient of the reactive power; is the reactive power increment reference value; is the reference value of the active power; P WT (t0) is the measured value of the active power at t0; is the reference value of the reactive power; Q WT (t0) is the measured value of the reactive power at t0.

[0075] From the above formula, the regulation model of the active power and the reactive power of the wind turbine can be derived as:

[0076]

[0077] where, is the first derivative of ΔP WT ; is the first derivative of ΔQ WT .

[0078] Then the wind farm state space equation can be obtained as follows:

[0079]

[0080] y = Cx

[0081]

[0082]

[0083] where x is the state variable; is the first derivative of x; A is the system matrix; B is the control matrix; u is the control variable; y is the response result; C is the output matrix or observation matrix, which is a 2N W *2N W identity matrix; N W is the number of wind turbines; and are the time delay coefficients of active power and reactive power of the i-th wind turbine, respectively; and represent the active power and reactive power of the i-th wind turbine, i = 1, 2, …, N W .

[0084] The power data-driven sensitivity can be used to construct the linear relationship between the powers of each unit, and the formula is as follows:

[0085]

[0086] where, and represent the increments of the active power and reactive power of the i-th wind turbine. and represent the active and reactive power data-driven sensitivity (power data-driven sensitivity) of the j-th wind turbine to the active and reactive power of the i-th wind turbine, which is obtained by the back propagation algorithm.

[0087] The linear relationship between the local wind turbine power and other wind turbines can be obtained, and the formula is as follows:

[0088]

[0089] where S PQ is the data-driven power sensitivity matrix.

[0090] Combining the power linear relationship with the state space equation of the wind farm, the local prediction model can be obtained:

[0091]

[0092] where x i is the state variable of the local prediction model of the i-th wind turbine. is the first derivative of x i . is the system matrix of the local prediction model; is the control matrix of the local prediction model; u i is the control variable of x i . is the output matrix or observation matrix of the local prediction model, which is a 2*2 unit matrix.

[0093] The power tracking is performed using a proportional distribution strategy. The active power of the i-th wind turbine should be very close to its proportional distribution reference Therefore, the power tracking loss function Obj P can be described as:

[0094]

[0095] where N p is the total number of prediction steps in the MPC; is the tracking power of the wind farm. is the power increment of the i-th wind turbine at the prediction step k, is the power reference value of the i-th wind turbine at the prediction step k, is the power estimation value of the i-th wind turbine.

[0096] The voltage regulation loss function Obj V can be described as:

[0097]

[0098] where N WF is the number of nodes in the wind farm; and are the active power increment and the reactive power increment of the i-th wind turbine, respectively. and are the active and reactive sensitivities of the j-th wind turbine to the i-th wind turbine. and can be either mathematical voltage sensitivities calculated by mathematical analysis method, or voltage data-driven sensitivities calculated by data-driven model.U j (t0) is the voltage estimation value of the j-th wind turbine, is the voltage reference value of the j-th wind turbine at the prediction step k.

[0099] The power tracking loss function Obj P and the voltage regulation loss function Obj V are weighted and added to obtain the total loss function Obj:

[0100] Obj = W p Obj P + W v Obj V

[0101] wherein W p , W v are the weight of power tracking loss function and the weight of voltage regulation loss function, respectively.

[0102] In this embodiment, the expression forms of the loss functions in the three control modes are the same. The difference lies in:

[0103] First control mode: the loss function Obj V in the first control mode is: and the voltage data driven sensitivity is adopted.

[0104] Second control mode: the local prediction model is substituted into the loss function Obj to obtain a loss function containing only local control variables:

[0105] Obj local = W p Obj P,loacl + W v Obj V,loacl

[0106]

[0107] wherein and the mathematical voltage sensitivity is adopted.

[0108] Third control mode: the and in the loss function of the second control mode are substituted by the voltage data driven sensitivity.

[0109] In a specific embodiment, the step S5 specifically comprises:

[0110] In current control methods, active and reactive power inputs are limited by quadratic inequality constraints due to the rated capacity limit of wind turbines. Directly applying this nonlinear inequality constraint to predictive control can lead to excessive computation time, making it difficult to meet control requirements. Therefore, a variable interval constraint linearization method is proposed to approximate the nonlinear constraint within a specific linearized region. The default constraint condition is greater than zero. If the corresponding nonlinear function is a concave function, a hyperplane formed by the region endpoints is used as a substitute linear function; if it is a convex function, a hyperplane parallel to the hyperplane formed by the endpoints and tangent to the function is used as a substitute linear function. A growth function is used to determine the region radius, which increases gradually from small to large. Small radius regions effectively retain the feasible region of the nonlinear constraint, while large radius regions reduce the total number of linear constraints, thereby reducing the computational burden of MPC solution.

[0111] The specific operation process of the algorithm is as follows:

[0112] Step 1: Convert all constraints to greater than zero and obtain the corresponding nonlinear function.

[0113] Step 2: Determine the function for generating region radius, the number of region division, and the inflection point of the function to divide the linearization region.

[0114] Step 3: Linearization substitution based on the divided region and the concavity and convexity of the function within each region.

[0115] Step 4: Derive the linearized constraint inequality.

[0116] In this embodiment, the constraint conditions include wind turbine active power constraints and wind turbine reactive power constraints.

[0117] The wind turbine active power constraint is a linear constraint condition, and the active power constraint of the i th wind turbine is as follows:

[0118]

[0119] wherein, is the available active power of the i th wind turbine.

[0120] The reactive power constraint of the i th wind turbine is as follows:

[0121]

[0122]

[0123] The upper and lower limits of the wind turbine reactive power constraint contain the active power, which is a nonlinear constraint condition.

[0124] The proposed variable-spaced constraint linearization method can be converted into the following linear constraints.

[0125]

[0126] n = 1, …, N n m = 1, …, N m

[0127] where N n and N m represent the number of upper and lower linear constraints, respectively, and are proportional coefficients, and are constant terms.

[0128] Using the optimized linear constraints, the calculation time of the control algorithm can be greatly reduced.

[0129] In a specific embodiment, step S6 specifically comprises:

[0130] According to the loss function obtained in step S4 and the linear constraints obtained in step S5, the following quadratic programming problem can be obtained.

[0131] The first control mode is:

[0132]

[0133] s.t. K ln P i (k) + b ln ≤ Q i (k) ≤ K um P i (k) + b um

[0134] The second control mode is:

[0135]

[0136] s.t. K ln P l (k) + b ln ≤ Q l (k) ≤ K um P l (k) + b um

[0137] The third control mode is:

[0138]

[0139] s.t. K ln Pl (k) + b ln ≤ Q l (k) ≤ K um P l (k) + b um

[0140] The above-mentioned quadratic programming problem can be solved using a standard optimization solver. In the first control mode, the reference values of all the fans are solved, and then the reference values corresponding to the fans are taken as the local control variables. In the second control mode and the third control mode, the reference values of the local control variables are directly solved.

[0141] The data-driven sensitivity-based wind farm decentralized control method provided in the application uses a deep learning model to establish a data-driven model, and uses a back propagation algorithm to obtain the gradient of the data-driven model, i.e., the data-driven sensitivity (including power data-driven sensitivity and voltage data-driven sensitivity) of the operation data of each wind turbine or each node state variable in the wind farm to the local wind turbine. The data-driven sensitivity can be substituted into the existing MPC control optimization control, such as the power-to-power sensitivity, which can reduce the number of variables in the objective function of the control problem and reduce the dimension of the objective function of the control problem; the voltage-to-power sensitivity can replace the sensitivity based on the mathematical model in the existing control method, which can increase the stability in the case of missing wind farm network parameters.

[0142] With the decentralized control method provided in the application, there is no need for communication with the central processor or the adjacent wind turbine controller in the local wind turbine control process. At the same time, the centralized control method can be deployed to the local wind turbine, combined with the data-driven sensitivity, to greatly reduce the control dimension while achieving an effect close to centralized control.

[0143] Based on the same inventive concept, the embodiments of the application also provide a device for implementing the data-driven sensitivity-based wind farm decentralized control method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more data-driven sensitivity-based wind farm decentralized control device embodiments provided below can be referred to the limitations of the data-driven sensitivity-based wind farm decentralized control method in the above text, which will not be repeated here.

[0144] In one exemplary embodiment, a data-driven sensitivity-based wind farm decentralized control device is provided, comprising:

[0145] A wind farm state variable prediction module is configured to estimate wind farm state variables based on the operation data of the local wind turbine using a data-driven model.

[0146] a data-driven sensitivity determination module configured to determine power data-driven sensitivities and voltage data-driven sensitivities by calculating gradients of the data-driven model based on the estimated wind farm state quantities using a backpropagation algorithm.

[0147] a mathematical voltage sensitivity calculation module configured to calculate mathematical voltage sensitivities based on the estimated wind farm state quantities.

[0148] a loss function calculation module configured to calculate loss functions under different control modes based on the power data-driven sensitivities, the voltage data-driven sensitivities, and the mathematical voltage sensitivities.

[0149] a transformation module configured to transform nonlinear constraint conditions into linear constraint conditions based on a variable distance constraint linearization method.

[0150] a control reference value determination module configured to determine control reference values of wind turbines based on the linear constraint conditions and the loss functions under different control modes.

[0151] a control module configured to control wind turbines of the wind farm based on the control reference values of the wind turbines.

[0152] In an exemplary embodiment, a computer device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program. The computer device can be a server or a terminal, and its internal structure diagram can be as shown in Figure 3 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store to-be-processed data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a wind farm distributed control method based on data-driven sensitivity.

[0153] Those skilled in the art can understand that, Figure 3The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0154] In one exemplary embodiment, a computer readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the steps in the above method embodiments.

[0155] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0156] A person of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium and can include the processes of the above method embodiments when executed. Any reference to a memory, database or other medium used in the embodiments provided by the present application can include at least one of a non-volatile and volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive memory (MRAM), a ferroelectric memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0157] The database involved in each embodiment provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, and the like, without being limited thereto. The processor involved in each embodiment provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, and the like, without being limited thereto.

[0158] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but it should be considered that any combination of the technical features is within the scope of the present disclosure, as long as there is no contradiction.

[0159] The principles and implementation modes of the present application are described by applying specific examples herein, and the above embodiments are only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, the specific implementation modes and application ranges will be changed according to the idea of the present application. In conclusion, the content of the present description should not be understood as a limitation of the present application.

Claims

1. A wind farm distributed control method based on data-driven sensitivity, characterized in that: include: Based on the operating data of local wind turbines, the data-driven model is used to estimate the state of the wind farm; Based on the estimated wind farm state quantity, a back propagation algorithm is used to calculate the gradient of the data-driven model to determine the power data-driven sensitivity and the voltage data-driven sensitivity; Based on the estimated wind farm state quantity, the mathematical analysis method is used to calculate the voltage sensitivity; Calculating loss functions under different control modes based on the power data driving sensitivity, the voltage data driving sensitivity, and the mathematical method voltage sensitivity; Specifically including: calculating the loss function under the first control mode based on the voltage data driving sensitivity and the wind farm state space equation; determining the local prediction model based on the power data driving sensitivity and the wind farm state space equation; calculating the loss function under the second control mode based on the local prediction model and the mathematical method voltage sensitivity; calculating the loss function under the third control mode based on the local prediction model and the voltage driving data sensitivity; The nonlinear constraints are converted into linear constraints based on the variable spacing constraint linearization method; Solving the loss function under different control modes based on the linear constraint conditions to determine the control reference value of each wind turbine generator set; Each wind turbine in the wind farm is controlled based on a control reference value of each wind turbine.

2. The method for decentralized wind farm control based on data-driven sensitivity according to claim 1, characterized in that: The data-driven model is built based on the Seg-RNN model.

3. The method for decentralized wind farm control based on data-driven sensitivity according to claim 1, characterized in that: The wind farm state space equation is expressed as follows: y=Cx in, is the first-order derivative of the state variable x, A is the system matrix, B is the control matrix, u is the control amount, y is the response result, C is the output matrix or observation matrix, and its dimension is 2N W ×2N W The identity matrix, is the active power increment of the i-th wind turbine, i=1,2,...,N W , N W is the number of wind turbines, is the reactive power increment of the i-th wind turbine, is the reference value of the active power increment of the i-th wind turbine, is the reactive power increment reference value of the i-th wind turbine group, is the time delay coefficient of the active power of the i-th wind turbine; is the time delay coefficient of the reactive power of the i-th wind turbine.

4. The method for decentralized wind farm control based on data-driven sensitivity according to claim 3, characterized in that: The expression of the local prediction model is: in, is the state variable x of the local prediction model of the i-th wind turbine i The first derivative of is the system matrix of the local prediction model, is the control matrix of the local prediction model, u i is x i The amount of control; is the output matrix or observation matrix of the local prediction model, S PQ Drives the sensitivity matrix for power data.

5. The method for decentralized wind farm control based on data-driven sensitivity according to claim 4, characterized in that: The expressions of loss functions under different control modes are: Obj=W p Rev P +W v Rev V in, and is the sensitivity of the voltage of the j-th wind turbine to the active and reactive power of the i-th wind turbine, W p is the power tracking loss function Obj P The weight, W v is the voltage regulation loss function Obj V The weight, N p is the total number of prediction steps; is the power reference value of the i-th wind turbine when the prediction step number is k, is the estimated power value of the i-th wind turbine at time t0, is the power increment of the i-th wind turbine when the number of prediction steps is k, N WF is the number of nodes in the wind farm, U j (t0) is the estimated voltage value of the j-th wind turbine generator set at time t0, is the voltage reference value of the j-th wind turbine generator set when the prediction step number is k, and are the active power increment and reactive power increment of the i-th wind turbine when the prediction step number is k, respectively.

6. The method for decentralized wind farm control based on data-driven sensitivity according to claim 5, characterized in that: The linear constraints include wind turbine active power constraints and wind turbine reactive power constraints; The active power constraint of the wind turbine is: in, is the available active power of the i-th wind turbine; The reactive power constraint of the wind turbine is: Among them, P i (k) is the active power control quantity of the i-th wind turbine when the prediction step number is k, Q i (k) is the reactive power control quantity of the i-th wind turbine when the prediction step number is k, and is the proportionality coefficient, and is a constant term, N n and N m are the number of upper and lower linear constraints, respectively.

7. A wind farm distributed control device based on data-driven sensitivity, characterized in that: include: Wind farm state quantity prediction module, which is used to estimate wind farm state quantities using a data-driven model based on the operating data of local wind turbines; a data-driven sensitivity determination module, configured to calculate the gradient of the data-driven model using a back-propagation algorithm based on the estimated wind farm state quantity, and determine the power data-driven sensitivity and the voltage data-driven sensitivity; A mathematical voltage sensitivity calculation module, used for calculating mathematical voltage sensitivity based on estimated wind farm state quantities; a loss function calculation module, configured to calculate loss functions under different control modes based on the power data driving sensitivity, the voltage data driving sensitivity, and the mathematical method voltage sensitivity; Specifically including: calculating the loss function under the first control mode based on the voltage data driving sensitivity and the wind farm state space equation; determining the local prediction model based on the power data driving sensitivity and the wind farm state space equation; calculating the loss function under the second control mode based on the local prediction model and the mathematical method voltage sensitivity; calculating the loss function under the third control mode based on the local prediction model and the voltage driving data sensitivity; A conversion module, used for converting nonlinear constraints into linear constraints based on a variable spacing constraint linearization method; A control reference value determination module, configured to determine a control reference value for each wind turbine generator set based on the linear constraint conditions and loss functions under different control modes; The control module is used to control each wind turbine generator set in the wind farm based on a control reference value of each wind turbine generator set.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the wind farm decentralized control method based on data-driven sensitivity according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for decentralized control of a wind farm based on data-driven sensitivity according to any one of claims 1 to 6 is implemented.

Images