Coordinated control system of wind generating set

Abstract

The invention discloses a coordinated control system of a wind generating set, which relates to the technical field of wind power generation control, and comprises an acquisition module, a control module and a control module, the adaptive algorithm module is responsible for constructing a wind power load prediction model through a machine learning model, and performing load prediction based on historical data and real-time data to obtain a prediction result; the energy storage management module is used for calculating the charging and discharging rate of the energy storage system and absorbing or releasing electric energy when the wind power load fluctuation exceeds an allowable range; the coupling module is used for collecting and analyzing real-time meteorological data, combining a meteorological prediction result with a wind power load prediction model, and predicting future wind speed and wind direction changes by analyzing the meteorological data; the emergency regulation and control module triggers an emergency regulation and control mechanism when the system detects that the wind power load fluctuation exceeds a prediction range; and the coordination module is responsible for data transmission among the modules, issuing of control commands and summarizing of feedback information.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation control, in particular to a coordinated control system of a wind power generator set. Background Art

[0002] With the continuous growth of global energy demand and the enhancement of environmental protection awareness, wind power generation, as a clean and renewable energy technology, has received widespread attention and rapid development. In recent years, the progress of wind power generation technology has led to the continuous expansion of the scale of wind turbines, and the significant increase in the capacity of single units and the installed capacity of wind farms. The proportion of wind power in the global energy structure continues to increase. However, due to the intermittent and uncontrollable nature of wind energy, the output power of wind power generation is often accompanied by large volatility and uncertainty, which brings many challenges to the stability of the power grid. In order to improve the economy and reliability of wind power generation, researchers and engineers have been committed to developing more advanced wind turbine control technology to accurately predict wind power load, optimize unit operating parameters, and balance the volatility of wind power output through energy storage systems and other means;

[0003] Existing wind turbine control systems usually rely on basic information such as wind speed sensors and generator output data to adjust the unit operating parameters. However, these control systems have several obvious shortcomings. First, traditional control systems lack accurate predictions of future wind speed and load changes, resulting in the control strategy of wind turbines lagging behind changes in actual wind energy conditions, which in turn causes large fluctuations in output power. Second, when wind power load fluctuations exceed the allowable range, existing technologies usually rely on energy storage systems for slow adjustments and are unable to cope with instantaneous power fluctuations caused by drastic changes in wind speed. In addition, existing wind power control systems lack effective coordination and real-time feedback mechanisms when coordinating various subsystems (such as energy storage systems and meteorological monitoring systems), which can easily cause data transmission delays or untimely command responses between modules, affecting the operating efficiency of the entire wind farm. Therefore, there is room for improvement in the accuracy of load forecasting, the response speed of energy storage systems, and the coordination between system modules. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a coordinated control system for wind turbines to solve the problem that traditional control systems lack accurate prediction of future wind speed and load changes, resulting in the control strategy of the wind turbine lagging behind the changes in actual wind energy conditions, thereby causing large fluctuations in output power.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a coordinated control system for a wind turbine generator set, which includes a collection module, an adaptive algorithm module, an energy storage management module, a coupling module, an emergency control module and a coordination module.

[0008] The acquisition module is responsible for collecting electrical data, meteorological data and energy storage system status of wind turbines from various subsystems, is connected to all other modules, and is responsible for providing real-time wind power load, meteorological data and energy storage system status;

[0009] The adaptive algorithm module is responsible for building a wind power load prediction model through a machine learning model, performing load prediction based on historical data and real-time data, and dynamically adjusting the operating parameters of the wind turbine according to the prediction results;

[0010] The energy storage management module is used to calculate the charge and discharge rate of the energy storage system and absorb or release electric energy when the wind power load fluctuation exceeds the allowable range;

[0011] The coupling module collects and analyzes real-time meteorological data, combines meteorological forecast results with the wind power load forecast model, and predicts future wind speed and wind direction changes by analyzing meteorological data;

[0012] The emergency control module triggers the emergency control mechanism when the system detects that the wind power load fluctuation exceeds the predicted range, and preferentially uses the superconducting energy storage system for rapid response;

[0013] The coordination module is responsible for data transmission between modules, issuing of control commands and aggregation of feedback information.

[0014] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, the electrical data, meteorological data and energy storage system status of the wind turbine generator set are collected from each subsystem, specifically,

[0015] Deploy wind turbine sensors to monitor power generation, rotation speed, and blade angle;

[0016] Deploy meteorological monitoring sensors to monitor wind speed;

[0017] Deploy energy storage monitoring sensors to monitor the charging and discharging rates of energy storage status;

[0018] Each sensor transmits the collected data to the edge computing device in real time through wireless transmission;

[0019] The collected data is preprocessed by filtering and removing noise.

[0020] As a preferred solution of the coordinated control system of the wind turbine generator set described in the present invention, wherein: the wind power load prediction model is constructed by a machine learning model, and load prediction is performed based on historical data and real-time data. The specific steps are:

[0021] Select the long short-term memory neural network LSTM as the wind power load forecasting model;

[0022] To forecast wind power load, the preprocessed data combined with historical load data are input into the load forecasting model. The expression is:

[0023] f(v i (t),θ i (t),E i (t)) = a 1 v i (t) 3 +a 2 θ i (t)+a 3 E i (t)+a 4 v i (t)θ i (t)+a 5 v i (t)E i

[0024] (t);

[0025] g(p hist (t),P i (t)) = b 1 p hist (t)+b 2 P i (t)+b 3 p hist (t)P i (t);

[0026]

[0027] Where L(t+Δt) represents the predicted wind power load value at the future time t+Δt, t represents the current time point, Δt represents the time interval, i is the index variable, N represents the number of wind turbines, and v i (t) represents the wind speed of the i-th wind turbine at time t, θ i (t) represents the blade angle of the i-th wind turbine at time t, E i (t) represents the speed of the i-th wind turbine at time t, a 1 、a 2 and a 3 They represent the linear coefficients of wind speed, blade angle and rotation speed, respectively, and a4 The coefficient representing the interaction between wind speed and blade angle, a 5 The coefficient representing the interaction between wind speed and rotation speed, b 1 represents the linear weight of historical power on future load forecast, b 2 represents the linear weight of current power generation on future load forecast, b 3 The coefficient representing the interaction between historical power generation and current power generation, p hist (t) represents the historical power generation, P i (t) represents the power generation of the i-th wind turbine at time t, f represents the nonlinear function, and g represents the time series correlation.

[0028] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, the specific steps of dynamically adjusting the operating parameters of the wind turbine generator set according to the prediction results are as follows:

[0029] Model predictive control (MPC) is used to construct the objective function to dynamically adjust the operating parameters of the wind turbine. The objective function expression is:

[0030]

[0031] Where J represents the objective function of MPC, T represents the length of the prediction time window, P(t+Δt) represents the power generated at time t+Δt, Δθ(t+Δt) represents the change in blade angle at time t+Δt, ΔE(t+Δt)| 2 Indicates the change in speed at time t+Δt, λ 1 and λ 2 It represents the penalty coefficient for adjusting the blade angle and speed change, and dt+Δt represents the integral variable.

[0032] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, wherein: the charging and discharging rate of the energy storage system is calculated, and when the wind power load fluctuation exceeds the allowable range, electric energy is absorbed or released. The specific steps are:

[0033] The charge and discharge rate of the energy storage system is calculated based on the load forecast value. The expression is:

[0034]

[0035] Where R(t) represents the charge and discharge rate of the energy storage system at the current time t, & represents the regulation coefficient of the energy storage system, and S(t) represents the power state of the energy storage system at time t;

[0036] When R(t)>0, it means that the load of the energy storage system is too high and the energy storage system will discharge;

[0037] When R(t)<0, it means that the load of the energy storage system is too low and the energy storage system will be charged;

[0038] When R(t)=0, it means that the load of the energy storage system is normal and no other operation is required.

[0039] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, the specific steps of collecting and analyzing real-time meteorological data are as follows:

[0040] Use the deployed meteorological monitoring sensors to collect on-site meteorological data in real time;

[0041] The autoregressive model is used to analyze the time series characteristics between wind speed and wind direction. The calculation formula is:

[0042]

[0043] Among them, A j Represents the coefficient matrix of the autoregressive model at time step j, where j is the index variable and a 11,j and a 21,j Indicates the influence of the wind speed observation value before the jth time step on the current wind speed forecast value, a 12,j and a 22,j Indicates the degree of influence of the observed value of wind direction before the jth time step on the current wind direction prediction value;

[0044] The moving average model is used to analyze the time series characteristics between wind speed white noise and wind direction white noise. The coefficient matrix B of the moving average model is k , which is also a 2×2 matrix, represents the coupling relationship between wind speed white noise and wind direction white noise. The calculation formula is:

[0045]

[0046] Among them, B k represents the coefficient matrix of the moving average model at k time steps, k is the index variable, b 11,k and b 21,k Indicates the degree of influence of the wind speed prediction error k time steps ago on the current wind speed prediction value, b 12,k and b 22,k It indicates the influence of the wind direction prediction error k time steps ago on the current wind speed prediction value.

[0047] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, the weather forecast result is combined with the wind power load forecast model to predict future wind speed and wind direction changes by analyzing the weather data. The specific steps are as follows:

[0048] Based on the time series characteristics of wind speed and wind direction, the multivariate autoregressive integrated moving average model ARIMA is selected as the basis of the meteorological forecast model to predict future wind speed and wind direction. The expression is:

[0049]

[0050] Where W(t+Δt) represents the predicted wind speed at time t+Δt, ψ(t+Δt) represents the predicted wind direction at time t+Δt, Δt represents the time interval, p represents the order of the autoregressive model, q represents the order of the moving average model, W(t-j) represents the observed wind speed at time t-j in the past, ψ(t-j) represents the observed wind direction at time t-j in the past, ∈ W (t-k) represents the wind speed white noise at the past time t-k, v ψ (t-k) represents the wind direction white noise at the past time t-k.

[0051] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, when the system detects that the wind power load fluctuation exceeds the predicted range, it will trigger the emergency control mechanism and give priority to using the superconducting energy storage system for rapid response. The specific steps are as follows:

[0052] The prediction error is obtained by subtracting the predicted wind power load value from the actual load value;

[0053] Set the maximum fluctuation threshold ΔL. When the prediction error exceeds the maximum fluctuation threshold ΔL, the system determines that the negative max

[0054] Load fluctuations are beyond the controllable range, triggering the emergency regulation mechanism.

[0055] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, the emergency control mechanism is specifically:

[0056] The superconducting energy storage system SMES is started first for rapid response. At this time, the charging and discharging rate R(t) of the energy storage system is dynamically adjusted according to the magnitude of the load fluctuation;

[0057] The power state S(t) of the energy storage system is continuously monitored. When the prediction error continues to increase or the energy storage system approaches its limit state, the priority of the energy storage system is adjusted to obtain the priority adjustment amount ΔS(t) of the energy storage system.

[0058] As a preferred solution of the coordinated control system of the wind turbine generator set of the present invention, the said responsible for data transmission, control command issuance and feedback information aggregation between various modules means that the coordination module is responsible for receiving real-time data from the acquisition module, adaptive algorithm module, energy storage management module, coupling module and emergency control module;

[0059] Based on the real-time data collected from each module, the coordination module comprehensively analyzes the current operating status of the wind turbine, load forecast results and energy storage system status, generates corresponding control commands, and sends the control commands to each subsystem according to priority through the communication network within the system;

[0060] The coordination module is also responsible for receiving feedback information from each subsystem after executing the control command in real time. The coordination module summarizes and analyzes these feedback data, and compares them with the new predicted data to determine whether the control effect meets expectations. When deviations are detected, the coordination module will adjust the control strategy in a timely manner and generate new control commands.

[0061] The beneficial effects of the present invention are as follows: the present invention collects the electrical, meteorological and energy storage system data of the wind turbine in real time through the acquisition module; the adaptive algorithm module accurately predicts the load based on the machine learning model and dynamically adjusts the unit operating parameters; the energy storage management module calculates the charging and discharging rate of the energy storage system and responds quickly when the load fluctuation exceeds the allowable range; the coupling module combines meteorological forecasts to further improve the prediction accuracy; the emergency control module gives priority to the use of superconducting energy storage systems to ensure rapid response to sudden load fluctuations; the coordination module is responsible for the data transmission between modules and the aggregation and analysis of feedback information; the data is pre-processed by the edge computing device, which further improves the data transmission efficiency and accuracy; the overall system achieves the beneficial effects of improving the wind power load prediction accuracy, reducing power fluctuations, optimizing the response speed of the energy storage system and enhancing the system collaborative control capability, and effectively improves the economy and reliability of the wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0063] Figure 1 Schematic diagram of the coordinated control system of the wind turbine generator set in Example 1.

[0064] Figure 2 This is a schematic diagram of error determination in Example 1. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0066] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0067] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0068] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a coordinated control system for a wind turbine generator set, comprising the following steps: an acquisition module, an adaptive algorithm module, an energy storage management module, a coupling module, an emergency control module and a coordination module,

[0069] The acquisition module is responsible for collecting electrical data, meteorological data and energy storage system status of wind turbines from various subsystems. It is connected to all other modules and is responsible for providing real-time wind power load, meteorological data and energy storage system status;

[0070] Deploy wind turbine sensors to monitor power generation, rotation speed, and blade angle;

[0071] Deploy meteorological monitoring sensors to monitor wind speed. Meteorological data is an important basis for predicting wind power load;

[0072] Deploy energy storage monitoring sensors to monitor the charging and discharging rates of energy storage status;

[0073] Each sensor transmits the collected data to the edge computing device in real time through wireless transmission. The edge computing device is located on site close to the wind turbine and can perform preliminary processing on the collected raw data to reduce the occupancy of transmission bandwidth.

[0074] Filter and pre-process the collected data to remove noise, ensuring that the data transmitted to the central system is accurate and stable;

[0075] The data collected by each subsystem is synchronized with the central control system through edge devices and stored in the cloud data platform to ensure that the data can be called by subsequent modules;

[0076] The adaptive algorithm module is responsible for building a wind power load forecasting model through a machine learning model, making load forecasts based on historical data and real-time data, and dynamically adjusting the operating parameters of wind turbines according to the forecast results;

[0077] We choose the long short-term memory neural network LSTM as the wind power load forecasting model. LSTM has a strong ability to analyze time series: wind power changes have a strong time correlation. LSTM can well capture the relationship between historical data and future load changes, which is suitable for wind power load forecasting.

[0078] Adaptive control capability of MPC: MPC can dynamically adjust system parameters based on future load forecasts to ensure stable power output of wind turbines and adapt to wind speed changes;

[0079] Real-time and accuracy: LSTM provides accurate load forecasting, while MPC can perform real-time regulation based on this, which is suitable for complex and dynamic wind power generation scenarios;

[0080] To forecast wind power load, the preprocessed data combined with historical load data are input into the load forecasting model. The expression is:

[0081] f(v i (t),θ i (t),E i (t)) = a 1 v i (t) 3 +a 2 θ i (t)+a 3 E i (t)+a 4 v i (t)θ i (t)+a 5 v i (t)E i

[0082] (t);

[0083] g(p hist (t),P i (t)) = b 1 p hist (t)+b 2 P i (t)+b 3 p hist (t)P i (t);

[0084]

[0085] Where L(t+Δt) represents the predicted wind power load value at the future time t+Δt, t represents the current time point, Δt represents the time interval, i is the index variable, N represents the number of wind turbines, and v i(t) represents the wind speed of the i-th wind turbine at time t, θ i (t) represents the blade angle of the i-th wind turbine at time t, E i (t) represents the speed of the i-th wind turbine at time t, a 1 、a 2 and a 3 They represent the linear coefficients of wind speed, blade angle and rotation speed, respectively, and a 4 The coefficient representing the interaction between wind speed and blade angle, a 5 The coefficient representing the interaction between wind speed and rotation speed, b 1 represents the linear weight of historical power on future load forecast, b 2 represents the linear weight of current power generation on future load forecast, b 3 The coefficient representing the interaction between historical power generation and current power generation, p hist (t) represents the historical power generation, P i (t) represents the power generated by the i-th wind turbine at time t, f represents a nonlinear function used to describe the relationship between these physical quantities, and g represents the time series correlation;

[0086] The objective function is constructed by using model predictive control (MPC) to dynamically adjust the operating parameters of the wind turbines so that the actual load is close to the predicted load. The objective function expression is:

[0087]

[0088] Where J represents the objective function of MPC, T represents the length of the prediction time window, P(t+Δt) represents the power generated at time t+Δt, Δθ(t+Δt) represents the change in blade angle at time t+Δt, ΔE(t+Δt)| 2 Indicates the change in speed at time t+Δt, λ 1 and λ 2 represents the penalty coefficient for adjusting the blade angle and speed change, dt+Δt represents the integral variable;

[0089] The objective function J of MPC has a value range of non-negative real numbers. The closer it is to 0, the smaller the load tracking error is and the better the control effect is.

[0090] The energy storage management module is used to calculate the charge and discharge rate of the energy storage system and absorb or release electric energy when the wind power load fluctuation exceeds the allowable range;

[0091] The charge and discharge rate of the energy storage system is calculated based on the load forecast value. The expression is:

[0092]

[0093] Where R(t) represents the charge and discharge rate of the energy storage system at the current time t, & represents the regulation coefficient of the energy storage system, and S(t) represents the power state of the energy storage system at time t;

[0094] By introducing the integral formula, the energy storage management module can calculate the charge and discharge rate R(t) of the energy storage system based on the difference between the wind power load forecast value L(t+Δt) and the actual power generation power P(t+Δt). The originality of this design lies in that it takes into account the load change trend in the future time period through integral calculation, rather than just regulating based on instantaneous values. This method solves the problem of delayed response of traditional energy storage systems because it can foresee future load conditions and make adjustments in advance.

[0095] When R(t)>0, it means that the load of the energy storage system is too high and the energy storage system will discharge;

[0096] When R(t)<0, it means that the load of the energy storage system is too low and the energy storage system will be charged;

[0097] When R(t) = 0, it means that the load of the energy storage system is normal and no other operation is required;

[0098] The range of R(t) is [―R max ,R max ], where R max is the maximum charge and discharge rate of the energy storage system;

[0099] The value range of the energy storage system's state of charge S(t) is [0,1], indicating the energy storage system's state of charge, 0 indicates no charge, and 1 indicates full charge;

[0100] By incorporating the energy storage system's state of charge S(t) into the calculation of the charge and discharge rate, it is ensured that the energy storage system will not operate in a low-charge or overcharged state. S(t) is used as a normalized quantity to simplify the control logic between different energy storage systems. This design cleverly solves the problem of abnormal charging and discharging caused by the energy storage system under extreme conditions (such as too low or too high power);

[0101] In the existing energy storage management technology, there is usually a lack of effective dynamic regulation of the power state of the energy storage system, which easily leads to overcharging or insufficient energy storage. The present invention ensures that the energy storage system always operates within a reasonable power range by dynamically monitoring S(t), thereby avoiding system efficiency reduction or hardware loss caused by improper power.

[0102] The coupling module collects and analyzes real-time meteorological data, combines meteorological forecast results with the wind power load forecast model, and predicts future wind speed and wind direction changes by analyzing meteorological data;

[0103] Use the deployed meteorological monitoring sensors to collect on-site meteorological data in real time, including wind speed, wind direction, temperature, air pressure, and humidity. The collection frequency is usually set once per minute, but it can also be adjusted according to the actual needs of the wind farm;

[0104] The collected meteorological data is transmitted to the edge computing device through wireless communication technology. The edge computing device performs preliminary processing on the data, including filtering, denoising and outlier detection, to ensure the accuracy and stability of the data. The processed meteorological data will be used to build a meteorological forecast model. The focus of this step is to ensure the quality of the input data, because the accuracy of meteorological data directly determines the accuracy of subsequent forecasts.

[0105] The autoregressive model is used to analyze the time series characteristics between wind speed and wind direction. The coefficient matrix A of the autoregressive model is j , which is a 2×2 matrix, represents the coupling relationship between wind speed and wind direction, and the calculation formula is:

[0106]

[0107] Among them, A j Represents the coefficient matrix of the autoregressive model at time step j, where j is the index variable and a 11,j and a 21,j Indicates the influence of the wind speed observation value before the jth time step on the current wind speed forecast value, a 12,j and a 22,j Indicates the degree of influence of the observed value of wind direction before the jth time step on the current wind direction prediction value;

[0108] The moving average model is used to analyze the time series characteristics between wind speed white noise and wind direction white noise. The coefficient matrix B of the moving average model is k , which is also a 2×2 matrix, represents the coupling relationship between wind speed white noise and wind direction white noise. The calculation formula is:

[0109]

[0110] Among them, B k represents the coefficient matrix of the moving average model at k time steps, k is the index variable, b 11,k and b 21,k Indicates the degree of influence of the wind speed prediction error k time steps ago on the current wind speed prediction value, b 12,k and b 22,k Indicates the degree of influence of the prediction error of wind direction k time steps ago on the current wind speed prediction value;

[0111] Based on the time series characteristics of wind speed and wind direction, the multivariate autoregressive integrated moving average model ARIMA is selected as the basis of the meteorological forecast model to predict future wind speed and wind direction. The expression is:

[0112]

[0113] Where W(t+Δt) represents the predicted wind speed at time t+Δt, ψ(t+Δt) represents the predicted wind direction at time t+Δt, Δt represents the time interval, p represents the order of the autoregressive model, q represents the order of the moving average model, W(t-j) represents the observed wind speed at time t-j in the past, ψ(t-j) represents the observed wind direction at time t-j in the past, ∈ W (t-k) represents the wind speed white noise at the past time t-k, ∈ ψ (t-k) represents the wind direction white noise at the past time t-k;

[0114] The purpose of predicting wind speed and direction is to serve the forecast of wind power load, and then provide a basis for calculating the charging and discharging rate of the energy storage system;

[0115] The predicted wind speed and wind direction will be used as input to the wind power load prediction model, which predicts the wind power load at future times based on wind speed, blade angle and rotation speed;

[0116] The energy storage management module will use the difference between the predicted load and the actual generated power to calculate the charge and discharge rate of the energy storage system;

[0117] The connection relationship is: wind speed and wind direction prediction → wind power load prediction model → energy storage system charge and discharge rate calculation;

[0118] Emergency control module: When the system detects that the wind power load fluctuation exceeds the predicted range, it will trigger the emergency control mechanism and give priority to using the superconducting energy storage system for rapid response;

[0119] The prediction error is obtained by subtracting the predicted wind load value from the actual negative wind charge value;

[0120] By real-time monitoring of the difference between the actual wind power load value and the predicted wind power load value (i.e., the prediction error), the system can quickly determine whether the load fluctuation exceeds the preset controllable range. The originality of this design lies in that it provides an accurate emergency response trigger mechanism by combining the difference between the predicted wind power load value and the actual wind power load value, avoiding the lag of traditional control strategies that rely on a single standard (such as voltage or frequency fluctuations);

[0121] Solution to technical problem: In the prior art, many load control systems rely on post-event monitoring. For example, the control mechanism is not started until the load fluctuation has affected the system stability, resulting in untimely response. The present invention predicts the abnormal situation of load fluctuation in advance through real-time calculation of the prediction error, avoids the problem of delayed response, and thus improves the stability and response speed of the system.

[0122] Set the maximum fluctuation threshold ΔL. When the prediction error exceeds the maximum fluctuation threshold ΔL, the system determines that the negative max

[0123] Load fluctuations are beyond the controllable range, triggering the emergency control mechanism;

[0124] By setting the maximum fluctuation threshold ΔL, the system can automatically trigger the load fluctuation when it exceeds the threshold.

[0125] max

[0126] Develop emergency control mechanisms;

[0127] The coordination module is responsible for data transmission between modules, issuing control commands and summarizing feedback information;

[0128] The superconducting energy storage system SMES is started first for rapid response. The SMES system can provide or absorb high-power electric energy within milliseconds, which is suitable for dealing with rapid changes in wind power load. At this time, the charging and discharging rate R(t) of the energy storage system is dynamically adjusted according to the magnitude of the load fluctuation.

[0129] The power state S(t) of the energy storage system is continuously monitored. When the prediction error continues to increase or the energy storage system approaches its limit state, the priority of the energy storage system is adjusted to obtain the priority adjustment amount ΔS(t) of the energy storage system, which is expressed as:

[0130]

[0131] Among them, ΔS(t) represents the priority adjustment of the energy storage system, γ represents the adjustment coefficient, S max Indicates the maximum capacity of the energy storage system;

[0132] ΔS(t) is used to adjust the system's priority for energy storage use, ensuring that when the energy storage system approaches its limit state, the system can appropriately reduce its response strength to avoid overuse of the energy storage system;

[0133] Responsible for data transmission between modules, issuing control commands and summarizing feedback information. The coordination module is responsible for receiving real-time data from the acquisition module, adaptive algorithm module, energy storage management module, coupling module and emergency control module.

[0134] Based on the real-time data collected from each module, the coordination module comprehensively analyzes the current operating status of the wind turbine, load forecast results and energy storage system status, and generates corresponding control commands. The control commands include dynamic adjustment of the wind turbine blade angle, speed, and energy storage system charge and discharge rate. The coordination module sends the control commands to each subsystem according to priority through the communication network within the system to ensure that the unit and energy storage system can work according to the optimized control strategy;

[0135] The coordination module is also responsible for receiving feedback information from each subsystem after executing the control command in real time. This feedback information includes the adjusted operating status of the unit, the charging and discharging status of the energy storage system, and the update of meteorological data. The coordination module summarizes and analyzes these feedback data, and compares them with the new forecast data to determine whether the control effect meets expectations. When deviations are detected, the coordination module will adjust the control strategy in a timely manner and generate new control commands to ensure the stable operation of the system.

[0136] This embodiment also provides a computer device, which is suitable for the coordinated control system of a wind turbine generator set, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the coordinated control system of the wind turbine generator set proposed in the above embodiment.

[0137] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0138] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the coordinated control system of the wind turbine generator set as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0139] In summary, the present invention is achieved through: the acquisition module collects the electrical, meteorological and energy storage system data of the wind turbine in real time; the adaptive algorithm module accurately predicts the load based on the machine learning model and dynamically adjusts the unit operating parameters; the energy storage management module calculates the charging and discharging rate of the energy storage system and responds quickly when the load fluctuation exceeds the allowable range; the coupling module combines meteorological forecasts to further improve the prediction accuracy; the emergency control module gives priority to the use of superconducting energy storage systems to ensure rapid response to sudden load fluctuations; the coordination module is responsible for the data transmission between modules and the aggregation and analysis of feedback information, and pre-processes the data through edge computing devices, which further improves the data transmission efficiency and accuracy. The overall system achieves the beneficial effects of improving the wind power load prediction accuracy, reducing power fluctuations, optimizing the response speed of the energy storage system and enhancing the system collaborative control capability, and effectively improves the economy and reliability of the wind farm.

[0140] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A coordinated control system for a wind turbine generator set, characterized in that: Including acquisition module, adaptive algorithm module, energy storage management module, coupling module, emergency control module and coordination module. The acquisition module is responsible for collecting electrical data, meteorological data and energy storage system status of wind turbines from various subsystems, is connected to all other modules, and is responsible for providing real-time wind power load, meteorological data and energy storage system status; The adaptive algorithm module is responsible for building a wind power load prediction model through a machine learning model, performing load prediction based on historical data and real-time data, and dynamically adjusting the operating parameters of the wind turbine according to the prediction results; The energy storage management module is used to calculate the charge and discharge rate of the energy storage system and absorb or release electric energy when the wind power load fluctuation exceeds the allowable range; The coupling module collects and analyzes real-time meteorological data, combines meteorological forecast results with the wind power load forecast model, and predicts future wind speed and wind direction changes by analyzing meteorological data; The emergency control module triggers the emergency control mechanism when the system detects that the wind power load fluctuation exceeds the predicted range, and preferentially uses the superconducting energy storage system for rapid response; The coordination module is responsible for data transmission between modules, issuing of control commands and aggregation of feedback information.

2. The coordinated control system of a wind turbine generator set according to claim 1, characterized in that: The electrical data, meteorological data and energy storage system status of the wind turbine generator set are collected from each subsystem, specifically, Deploy wind turbine sensors to monitor power generation, rotation speed, and blade angle; Deploy meteorological monitoring sensors to monitor wind speed; Deploy energy storage monitoring sensors to monitor the charging and discharging rates of energy storage status; Each sensor transmits the collected power generation, rotation speed, blade angle, wind speed and charging and discharging rate of energy storage status to the edge computing device in real time through wireless transmission; The collected data is preprocessed by filtering and removing noise.

3. The coordinated control system of a wind turbine generator set as claimed in claim 2, characterized in that: The wind power load prediction model is constructed by using a machine learning model, and load prediction is performed based on historical data and real-time data. The specific steps are: Select the long short-term memory neural network LSTM as the wind power load forecasting model; To predict the wind power load, the pre-processed data combined with the historical wind power load data are input into the wind power load prediction model. The expression is: f(v i (t),θ i (t),E i (t))=a1v i (t) 3 +a2θ i (t)+a3E i (t)+a4v i (t)θ i (t)+a5v i (t)E i (t); g(p hist (t),P i (t))=b1p hist (t)+b2P i (t)+b3p hist (t)P i (t); Where L(t+Δt) represents the predicted wind power load value at the future time t+Δt, t represents the current time point, Δt represents the time interval, i is the index variable, N represents the number of wind turbines, and v i (t) represents the wind speed of the i-th wind turbine at time t, θ i (t) represents the blade angle of the i-th wind turbine at time t, E i (t) represents the speed of the i-th wind turbine at time t, a1, a2 and a3 represent the linear coefficients of wind speed, blade angle and speed respectively, a4 represents the coefficient of interaction between wind speed and blade angle, a5 represents the coefficient of interaction between wind speed and speed, b1 represents the linear weight of historical power for future load prediction, b2 represents the linear weight of current power generation for future load prediction, b3 represents the coefficient of interaction between historical power generation and current power generation, p hist (t) represents the historical power generation, P i (t) represents the power generation of the i-th wind turbine at time t, f represents the nonlinear function, and g represents the time series correlation.

4. The coordinated control system of a wind turbine generator set as claimed in claim 3, characterized in that: The specific steps of dynamically adjusting the operating parameters of the wind turbine generator set according to the prediction results are as follows: Model predictive control (MPC) is used to construct the objective function to dynamically adjust the operating parameters of the wind turbine. The objective function expression is: Where J represents the objective function of MPC, T represents the length of the prediction time window, P(t+Δt) represents the power generated at time t+Δt, Δθ(t+Δt) represents the change in blade angle at time t+Δt, ΔE(t+Δt)| 2 represents the change in speed at time t+Δt, λ1 and λ2 represent the penalty coefficients for adjusting the blade angle and speed change, and dt+Δt represents the integral variable.

5. The coordinated control system of a wind turbine generator set as claimed in claim 4, characterized in that: The specific steps of calculating the charging and discharging rate of the energy storage system and absorbing or releasing electric energy when the wind power load fluctuation exceeds the allowable range are as follows: The charging and discharging rate of the energy storage system is calculated based on the predicted wind power load value. The expression is: Where R(t) represents the charge and discharge rate of the energy storage system at the current time t, & represents the regulation coefficient of the energy storage system, and S(t) represents the power state of the energy storage system at time t; When R(t)>0, it means that the load of the energy storage system is too high and the energy storage system will discharge; When R(t)<0, it means that the load of the energy storage system is too low and the energy storage system will be charged; When R(t)=0, it means that the load of the energy storage system is normal and no other operation is required.

6. The coordinated control system of a wind turbine generator set as claimed in claim 5, characterized in that: The specific steps of collecting and analyzing real-time meteorological data are as follows: Use the deployed meteorological monitoring sensors to collect on-site meteorological data in real time; The autoregressive model is used to analyze the time series characteristics between wind speed and wind direction. The calculation formula is: Among them, A j Represents the coefficient matrix of the autoregressive model at time step j, where j is the index variable and a 11,j and a 21,j Indicates the influence of the wind speed observation value before the jth time step on the current wind speed forecast value, a 12,j and a 22,j Indicates the degree of influence of the observed value of wind direction before the jth time step on the current wind direction prediction value; The moving average model is used to analyze the time series characteristics between wind speed white noise and wind direction white noise. The coefficient matrix B of the moving average model is k , the calculation formula is: Among them, B k represents the coefficient matrix of the moving average model at k time steps, k is the index variable, b 11,k and b 21,k Indicates the degree of influence of the wind speed prediction error before b time steps on the current wind speed prediction value, b 12,k and k 22,k It indicates the influence of the wind direction prediction error k time steps ago on the current wind speed prediction value.

7. The coordinated control system of a wind turbine generator set according to claim 6, characterized in that: The weather forecast results are combined with the wind power load forecast model to predict future wind speed and wind direction changes by analyzing the weather data. The specific steps are as follows: Based on the time series characteristics between wind speed and wind direction, the multivariate autoregressive integrated moving average model ARIMA is selected as the basis of the meteorological forecast model to predict future wind speed and wind direction. The expression is: Where W(t+Δt) represents the predicted wind speed at time t+Δt, ψ(t+Δt) represents the predicted wind direction at time t+Δt, Δt represents the time interval, p represents the order of the autoregressive model, q represents the order of the moving average model, W(t-j) represents the observed wind speed at time t-j in the past, ψ(t-j) represents the observed wind direction at time t-j in the past, ∈ W (t-k) represents the wind speed white noise at the past time t-k, ∈ ψ (t-k) represents the wind direction white noise at the past time t-k.

8. The coordinated control system of a wind turbine generator set according to claim 7, characterized in that: When the system detects that the wind power load fluctuation exceeds the predicted range, it will trigger the emergency control mechanism and give priority to using the superconducting energy storage system for rapid response. The specific steps are: The prediction error is obtained by subtracting the predicted wind power load value from the actual wind power load value; Set the maximum fluctuation threshold ΔL max , when the prediction error exceeds the maximum fluctuation threshold ΔL max , the system determines that the load fluctuation is beyond the controllable range and triggers the emergency control mechanism.

9. The coordinated control system of a wind turbine generator set according to claim 8, characterized in that: The emergency control mechanism is specifically: The superconducting energy storage system SMES is started first for rapid response. At this time, the charging and discharging rate R(t) of the energy storage system is dynamically adjusted according to the magnitude of the load fluctuation; The power state S(t) of the energy storage system is continuously monitored. When the prediction error continues to increase or the energy storage system approaches its limit state, the priority of the energy storage system is adjusted to obtain the priority adjustment amount ΔS(t) of the energy storage system.

10. The coordinated control system of a wind turbine generator set according to claim 9, characterized in that: The said responsible for data transmission, control command issuance and feedback information aggregation between various modules means that the coordination module is responsible for receiving real-time data from the acquisition module, adaptive algorithm module, energy storage management module, coupling module and emergency control module; Based on the real-time data collected from each module, the coordination module comprehensively analyzes the current operating status of the wind turbine, load forecast results and energy storage system status, generates corresponding control commands, and sends the control commands to each subsystem according to priority through the communication network within the system; The coordination module is also responsible for receiving feedback information from each subsystem after executing the control command in real time. The coordination module summarizes and analyzes these feedback data, and compares them with the new predicted data to determine whether the control effect meets expectations. When deviations are detected, the coordination module will adjust the control strategy and generate new control commands.

Images