Virtual oscillator auxiliary wind power plant reactive power coordination system and method

Abstract

The invention discloses a virtual oscillator assisted reactive power coordination system and method for a wind power plant, which are used in the technical field of automatic voltage control of a power system, and the virtual oscillator assisted reactive power coordination system for the wind power plant comprises a comprehensive prediction module, a multi-objective optimization module, a high-volatility response module and a low-volatility management module. The active power output data of the wind power plant are acquired in real time, the voltage fluctuation and frequency fluctuation indexes are calculated, the reactive power demand and the voltage stability requirement of the power grid are combined, the needed reactive power regulation quantity is dynamically calculated by using the multi-target optimization model, the response priority can be determined according to the regulation capability of equipment, and the reactive power regulation quantity can be accurately calculated. And a reactive power regulation task and a control strategy of the equipment are formulated, so that the stability of voltage and frequency is maintained while the reactive power demand of the power grid is met, the operation efficiency and stability of the wind power plant and the power grid are improved, and the allocation and management of resources are optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic voltage control of electric power systems, and in particular to a virtual oscillator-assisted wind farm reactive power coordination system and method. Background Art

[0002] As one of the new energy sources with the greatest value for large-scale commercial development and application, wind energy has extremely abundant reserves around the world. Compared with traditional fossil energy sources such as coal, oil, and natural gas, the biggest advantage of wind energy is its renewability. Wind energy is generated by the flow of a large amount of air on the surface of the earth, so to some extent, it is an inexhaustible energy source. In addition, as a representative of renewable energy, wind energy has the potential for sustainable use and is environmentally friendly.

[0003] At present, with the rapid development of economy and technology, the construction speed of wind farms often exceeds the development of regional power grids. When the active power generated by wind turbines is too large, the interconnection lines of the power grid usually cannot meet the safety standards. Due to the volatility and randomness of the power output of wind turbines, coupled with the insufficient means of reactive voltage control of the power grid, the problem of grid voltage quality has become particularly prominent.

[0004] As a new type of power electronic control method, virtual oscillator control technology has received more and more attention. The virtual oscillator can imitate the dynamic behavior of traditional synchronous generators in the power grid, and adjust the power output by introducing the control mechanism of the oscillator to achieve intelligent coordination of the reactive power of wind turbines.

[0005] China Patent Publication No.: CN117639125A, disclosed wind farm reactive coordination method and device, electronic equipment, storage medium, by proposing a reactive coordination control method for wind farm group when offshore wind power is sent out via flexible direct current considering wind power output fluctuation, can ensure the rationality of reactive power flow distribution of wind farm collection system when offshore wind power sent out via flexible direct current is affected by wind speed changes and active power output has large fluctuation, reduce active power loss and reactive power compensation capacity in collection system, reduce offshore wind power project construction cost and give full play to offshore wind farm's ability to participate in power grid reactive power control. This method can be applied to solving reactive coordination control of wind farm group when offshore wind power is sent out via flexible direct current considering wind power output fluctuation, has high computational efficiency, and can provide scientific and reasonable solution for reactive power-voltage stability analysis and control of power system when offshore wind power is sent out on a large scale.

[0006] However, traditional methods have difficulty in achieving rapid response and dynamic adjustment when processing the active power output data of wind farms and the real-time needs of the power grid, and cannot meet the real-time needs for reactive power regulation during the operation of the power grid. In addition, it is often difficult to effectively evaluate the reactive power regulation capabilities of each device, resulting in the failure to fully utilize the regulation potential of different devices in reactive power distribution, affecting the regulation efficiency and the overall stability of the power grid. In addition, many existing methods rely on centralized control, which makes it difficult to achieve automatic synchronization and collaborative control among devices, and responds slowly when the power grid stability faces challenges. At the same time, in the allocation of reactive power regulation tasks, traditional technologies cannot effectively optimize the allocation of resources, resulting in some equipment being overloaded and some equipment being underutilized, affecting the overall operating efficiency of wind farms and power grids.

[0007] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0008] In order to overcome the above problems, the present invention aims to propose a virtual oscillator-assisted wind farm reactive power coordination system and method, with the aim of solving the problem that traditional methods are difficult to respond quickly and dynamically when processing the active power output data of wind farms and the real-time needs of the power grid, and are unable to meet the real-time needs for reactive power regulation during the operation of the power grid. In addition, it is often difficult to effectively evaluate the reactive power regulation capability of each device, resulting in the failure to fully utilize the regulation potential of different devices in reactive power distribution, affecting the regulation efficiency and the overall stability of the power grid.

[0009] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a virtual oscillator-assisted wind farm reactive coordination system is provided, the virtual oscillator-assisted wind farm reactive coordination system comprising: a comprehensive prediction module, a multi-objective optimization module, a high volatility response module and a low volatility management module; Comprehensive prediction module, which is used to use multi-level neural networks to comprehensively predict the multi-dimensional operating parameters of wind farms and power grids, and evaluate the parameter operating status and power fluctuation trend within a preset time in the future; The multi-objective optimization module is used to dynamically calculate the voltage fluctuation index and frequency fluctuation index based on the evaluation results and the real-time active power output of the wind farm. It also calculates the required reactive power regulation through multi-objective optimization analysis and combines the reactive power demand and voltage stability requirements to determine the response priority and control strategy of each device. High volatility response module, which is used to adjust the virtual oscillator according to the response priority of each device and take corresponding control measures based on the control strategy to stabilize the voltage and frequency of the power grid when the voltage volatility index and frequency volatility index exceed the preset threshold; The low volatility management module is used to control the reactive power output of each device according to the real-time demand of the power grid when the voltage volatility index and frequency volatility index do not exceed the preset threshold. The virtual oscillator realizes automatic synchronization between devices through a decentralized control mechanism, dynamically allocates reactive power regulation tasks, and adaptively adjusts the power output of each device.

[0010] Optionally, the comprehensive prediction module includes a data collection unit, a feature selection unit, a model building and training unit, a prediction and verification unit, and a comparative analysis unit; A data collection unit, used to collect multi-dimensional operating parameters from the historical database of the wind farm and the power grid; A feature selection unit, used for extracting feature data associated with the operating state and power fluctuation from the collected multi-dimensional operating parameters using a feature selection algorithm; The model building and training unit is used to build a multi-level neural network model, input the extracted feature data, perform multiple rounds of iterative training through the training set, and use the optimization algorithm to adjust the weights and biases of the multi-level neural network model; The prediction and verification unit is used to use the trained multi-level neural network model to predict the operation status of the wind farm and the power grid within a preset time in the future, output the prediction results of voltage fluctuation, frequency fluctuation and power fluctuation, and verify the prediction results through the test set; The comparison and analysis unit is used to compare and analyze the predicted voltage fluctuation, frequency fluctuation and power fluctuation with the historical operation data of the wind farm and the power grid, and evaluate the parameter operation status and power fluctuation trend within a preset time in the future.

[0011] Optionally, when the feature selection unit extracts feature data associated with the operating state and power fluctuation from the collected multi-dimensional operating parameters using a feature selection algorithm, the feature selection unit includes: Standardize the collected multi-dimensional operating parameters; Calculate the covariance matrix of standardized multi-dimensional operating parameters; Perform eigenvalue decomposition on the covariance matrix to extract eigenvalues ​​and corresponding eigenvectors, where the eigenvalues ​​represent the size of the data variance explained by each principal component, and the eigenvectors represent the directions of each principal component; Sort the eigenvalues ​​from high to low, and select the principal components that meet the preset proportion requirements as the extracted feature data; The collected multi-dimensional operating parameters are projected into the space composed of the selected principal components to obtain the feature data after dimensionality reduction.

[0012] Optionally, the model building and training unit includes the following steps when building a multi-level neural network model, inputting the extracted feature data, performing multiple rounds of iterative training through a training set, and adjusting the weights and biases of the multi-level neural network model using an optimization algorithm: Divide the extracted feature data into training set, validation set and test set, and prepare the time series data required by the long short-term memory network and the tensor format required by the convolutional neural network; Construct a multi-level neural network model including 1D convolution layer, maximum pooling layer, long short-term memory network layer and fully connected layer to extract spatial features and temporal dependencies respectively; Build a multi-level neural network model, select mean square error as the loss function, Adam optimizer as the optimizer, and set the evaluation indicators; Use the training data to perform multiple rounds of iterative training. In each round of iteration, calculate the loss and evaluation indicators based on the data of the validation set, and dynamically adjust the weights and biases of the multi-level neural network model; Monitor the loss changes of the validation set during training and select the best model parameters based on the performance of the validation set; The prediction performance of the model is evaluated using the test set and the final evaluation metrics are calculated.

[0013] Optionally, the comparison and analysis unit compares and analyzes the predicted voltage fluctuation, frequency fluctuation and power fluctuation with the historical operation data of the wind farm and the power grid to evaluate the parameter operation status and power fluctuation trend within a preset time in the future, including: Collect the voltage fluctuation, frequency fluctuation and power fluctuation data predicted by the model and match them with the historical operation data of the corresponding time period; Use error indicators to evaluate the error between the forecast results and historical data, and draw comparative analysis charts to show the matching degree between the forecast results and historical data and the error trend; Based on the calculated error indicators and chart analysis results, the model's prediction accuracy for voltage, frequency, and power fluctuations is evaluated, and the prediction effect of the model at different time points and conditions is determined; Based on the error analysis results, evaluate the parameter operating status and power fluctuation trend within the future preset time.

[0014] Optionally, the multi-objective optimization module dynamically calculates the voltage fluctuation index and the frequency fluctuation index based on the evaluation results and the real-time active power output of the wind farm, and combines the reactive power demand and the voltage stability requirement to calculate the required reactive power regulation through multi-objective optimization analysis, and determines the response priority and control strategy of each device, including: Obtaining real-time active power output data from the wind farm at the current moment; Calculate the current voltage fluctuation index and frequency fluctuation index based on the real-time active power output data and the operating status of the wind farm; Obtain the current reactive power demand and voltage stability requirements of the power grid, and establish a multi-objective optimization model with the goals of minimizing voltage fluctuation, minimizing frequency fluctuation and meeting the reactive power demand of the power grid; Based on the multi-objective optimization model, the reactive power regulation that meets the voltage stability and frequency stability requirements is dynamically calculated; and the response priority of different equipment is determined according to the reactive power regulation and the regulation capabilities of various equipment; Based on the response priority of different devices, the control strategy of the equipment is formulated to adjust the reactive power output of each device to ensure that the reactive power demand of the power grid is met in real time, maintain voltage and frequency stability, and optimize the operating efficiency of the wind farm.

[0015] Optionally, the expression for minimizing voltage fluctuation, minimizing frequency fluctuation and satisfying reactive power demand of the power grid is: ; In the formula, It represents the weighted sum of voltage fluctuation, frequency fluctuation and reactive power deviation in the multi-objective optimization model; Indicates the current reactive power demand of the power grid; Represents the reactive power output provided by the wind farm; Indicates the absolute value of frequency deviation; Indicates the absolute value of voltage deviation; w 1 represents the weight factor of voltage fluctuation; w 2 represents the weight factor of frequency fluctuation; w 3 represents the weighting factor of reactive power deviation.

[0016] Optionally, based on a multi-objective optimization model, a reactive power regulation amount that meets the voltage stability and frequency stability requirements is dynamically calculated; and according to the reactive power regulation amount and the regulation capabilities of various types of equipment, the response priorities of different equipment are determined, including: Calculate the optimal reactive power regulation that meets the voltage and frequency stability requirements based on a multi-objective optimization model; Calculate the reactive power regulation capacity of each device by the ratio of its actual reactive power output capacity to its rated output; Evaluate the regulation capability of each device based on its reactive power regulation capability; Determine the response priority of each device based on the reactive power regulation amount and the regulation capacity of each device, and formulate the reactive power regulation task of each device in the order of response priority; The expression for determining the response priority of each device is: ; ; In the formula, Indicates the device i The actual reactive power output; Indicates the device i Rated reactive output; α i Indicates the device i Reactive power regulation capability; Indicates the device i The response priority.

[0017] Optionally, when the voltage volatility index and the frequency volatility index do not exceed a preset threshold, the low volatility management module controls the reactive power output of each device according to the real-time demand of the power grid through a virtual oscillator; and realizes automatic synchronization between devices through a decentralized control mechanism, while dynamically allocating reactive power regulation tasks and adaptively adjusting the power output of each device, including: Monitor the voltage fluctuation index and frequency fluctuation index of the power grid in real time to determine whether they exceed the preset threshold; When the voltage and frequency volatility indicators do not exceed the preset thresholds, the virtual oscillator controls the reactive power output of each device according to the real-time needs of the power grid; Using a decentralized control mechanism, each device is allowed to automatically adjust its output according to the control instructions of the virtual oscillator, achieving automatic synchronization between devices; Dynamically allocate reactive power regulation tasks to different devices according to the real-time needs of the power grid; Each device adaptively adjusts its reactive power output according to real-time grid demand and its own operating status, ensuring that the grid voltage and frequency remain stable when demand changes; Continuously monitor the output of the equipment and the response of the power grid, and dynamically adjust the reactive output of each device based on the feedback.

[0018] According to another aspect of the present invention, a virtual oscillator-assisted wind farm reactive power coordination method is also provided. The virtual oscillator-assisted wind farm reactive power coordination method comprises the following steps: S1. Use multi-level neural networks to comprehensively predict the multi-dimensional operating parameters of wind farms and power grids, and evaluate the parameter operating status and power fluctuation trend within a preset time in the future; S2. Based on the evaluation results and the real-time active power output of the wind farm, the voltage fluctuation index and frequency fluctuation index are dynamically calculated. In combination with the reactive power demand and voltage stability requirements, the required reactive power regulation is calculated through multi-objective optimization analysis to determine the response priority and control strategy of each device. S3. When the voltage fluctuation index and the frequency fluctuation index exceed the preset threshold, the virtual oscillator will be adjusted according to the response priority of each device and take corresponding control measures based on the control strategy to stabilize the voltage and frequency of the power grid; S4. When the voltage volatility index and the frequency volatility index do not exceed the preset threshold, the virtual oscillator controls the reactive power output of each device according to the real-time demand of the power grid; and realizes automatic synchronization between devices through a decentralized control mechanism, while dynamically allocating reactive power regulation tasks and adaptively adjusting the power output of each device.

[0019] Compared with the prior art, this application has the following beneficial effects: 1. The present invention uses a multi-level neural network model, combined with a feature selection algorithm and historical data for training, to effectively predict the future voltage fluctuations, frequency fluctuations and power fluctuations of wind farms and power grids. By comparing and analyzing historical data with the prediction results, the prediction accuracy of the model is evaluated, and the future power grid operation status and power fluctuation trends can be foreseen in advance, thereby improving the operating stability and regulation efficiency of wind farms and power grids, and helping to optimize the decision-making and management of the power system.

[0020] 2. The present invention obtains the active power output data of the wind farm in real time, calculates the voltage volatility and frequency volatility indicators, and combines the reactive power demand and voltage stability requirements of the power grid. It uses a multi-objective optimization model to dynamically calculate the required reactive power regulation amount, and can determine the response priority according to the regulation capability of the equipment, and formulate the reactive power regulation tasks and control strategies of the equipment, so as to ensure that the power grid maintains the stability of voltage and frequency while meeting the reactive power demand, thereby improving the operating efficiency and stability of the wind farm and the power grid, and optimizing the allocation and management of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above characteristics, features and advantages of the present invention and their implementation methods and methods will become more clearly understood in conjunction with the following description of the embodiments, which are described in detail in conjunction with the accompanying drawings. Herein, a schematic diagram is shown: Figure 1 is a principle block diagram of a virtual oscillator assisted wind farm reactive power coordination system according to an embodiment of the present invention; Figure 2 The present invention is a flowchart of a method for wind farm reactive power coordination assisted by a virtual oscillator according to an embodiment of the present invention.

[0022] In the figure: 1. Comprehensive prediction module; 2. Multi-objective optimization module; 3. High volatility response module; 4. Low volatility management module. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] According to an embodiment of the present invention, a virtual oscillator-assisted wind farm reactive power coordination system and method are provided.

[0025] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a virtual oscillator-assisted wind farm reactive coordination system is provided, and the virtual oscillator-assisted wind farm reactive coordination system includes: a comprehensive prediction module 1, a multi-objective optimization module 2, a high volatility response module 3 and a low volatility management module 4; The comprehensive prediction module 1 is used to use a multi-level neural network to comprehensively predict the multi-dimensional operating parameters of the wind farm and the power grid, and evaluate the parameter operating status and power fluctuation trend within a preset time in the future.

[0026] Preferably, the comprehensive prediction module includes a data collection unit, a feature selection unit, a model building and training unit, a prediction and verification unit, and a comparative analysis unit; A data collection unit, used to collect multi-dimensional operating parameters from the historical database of the wind farm and the power grid; A feature selection unit, used for extracting feature data associated with the operating state and power fluctuation from the collected multi-dimensional operating parameters using a feature selection algorithm; The model building and training unit is used to build a multi-level neural network model, input the extracted feature data, perform multiple rounds of iterative training through the training set, and use the optimization algorithm to adjust the weights and biases of the multi-level neural network model; The prediction and verification unit is used to use the trained multi-level neural network model to predict the operation status of the wind farm and the power grid within a preset time in the future, output the prediction results of voltage fluctuation, frequency fluctuation and power fluctuation, and verify the prediction results through the test set; The comparison and analysis unit is used to compare and analyze the predicted voltage fluctuation, frequency fluctuation and power fluctuation with the historical operation data of the wind farm and the power grid, and evaluate the parameter operation status and power fluctuation trend within a preset time in the future.

[0027] Preferably, the feature selection unit, when extracting feature data associated with the operating state and power fluctuation from the collected multi-dimensional operating parameters using a feature selection algorithm, includes: Standardize the collected multi-dimensional operating parameters; Calculate the covariance matrix of standardized multi-dimensional operating parameters; Perform eigenvalue decomposition on the covariance matrix to extract eigenvalues ​​and corresponding eigenvectors, where the eigenvalues ​​represent the size of the data variance explained by each principal component, and the eigenvectors represent the directions of each principal component; Sort the eigenvalues ​​from high to low, and select the principal components that meet the preset proportion requirements as the extracted feature data; The collected multi-dimensional operating parameters are projected into the space composed of the selected principal components to obtain the feature data after dimensionality reduction.

[0028] Preferably, the model building and training unit includes the following steps when building a multi-level neural network model, inputting the extracted feature data, performing multiple rounds of iterative training through a training set, and adjusting the weights and biases of the multi-level neural network model using an optimization algorithm: Divide the extracted feature data into training set, validation set and test set, and prepare the time series data required by the long short-term memory network and the tensor format required by the convolutional neural network; Construct a multi-level neural network model including 1D convolution layer, maximum pooling layer, long short-term memory network layer and fully connected layer to extract spatial features and temporal dependencies respectively; Build a multi-level neural network model, select mean square error as the loss function, Adam optimizer as the optimizer, and set the evaluation indicators; Use the training data to perform multiple rounds of iterative training. In each round of iteration, calculate the loss and evaluation indicators based on the data of the validation set, and dynamically adjust the weights and biases of the multi-level neural network model; Monitor the loss changes of the validation set during training and select the best model parameters based on the performance of the validation set; The prediction performance of the model is evaluated using the test set and the final evaluation metrics are calculated.

[0029] Preferably, the comparison and analysis unit compares and analyzes the predicted voltage fluctuation, frequency fluctuation and power fluctuation with the historical operation data of the wind farm and the power grid, and evaluates the parameter operation status and power fluctuation trend within a preset time in the future, including: Collect the voltage fluctuation, frequency fluctuation and power fluctuation data predicted by the model and match them with the historical operation data of the corresponding time period; Use error indicators to evaluate the error between the forecast results and historical data, and draw comparative analysis charts to show the matching degree between the forecast results and historical data and the error trend; Based on the calculated error indicators and chart analysis results, the model's prediction accuracy for voltage, frequency, and power fluctuations is evaluated, and the prediction effect of the model at different time points and conditions is determined; Based on the error analysis results, evaluate the parameter operating status and power fluctuation trend within the future preset time.

[0030] It should be explained that, first, the data collection unit obtains multi-dimensional operating data from the historical database, and the feature selection unit extracts key features related to power fluctuations through the feature selection algorithm. Then, the model construction and training unit constructs and trains a multi-level neural network model, uses an optimization algorithm to adjust weights and biases, and performs multiple rounds of iterative optimization through a validation set. The trained model is used to predict future voltage, frequency, and power fluctuations, and the prediction results are compared and analyzed with historical data to evaluate the accuracy of the model and future trends.

[0031] The multi-objective optimization module 2 is used to dynamically calculate the voltage fluctuation index and the frequency fluctuation index based on the evaluation results and the real-time active power output of the wind farm, and to determine the response priority and control strategy of each device by calculating the required reactive power regulation amount through multi-objective optimization analysis and calculation in combination with the reactive power demand and voltage stability requirements.

[0032] The control strategy specifically refers to the specific operation plan used to manage and adjust the reactive power output of each device, aiming to ensure the voltage and frequency stability of the power grid and meet the reactive power demand. It mainly includes the following aspects: 1. Priority allocation of reactive power regulation: According to the response priority of the equipment, determine which equipment should be given priority for reactive power regulation. The response priority is usually determined based on the equipment's regulation capability, real-time status and grid demand, and equipment with fast response and strong regulation capability is prioritized.

[0033] 2. Reactive power output control: For each selected device, the control strategy will define its specific reactive power output. This involves increasing or decreasing the reactive power of the device to ensure that the total reactive power meets the needs of the grid while optimizing the stability of voltage and frequency.

[0034] 3. Decentralized control and automatic synchronization: Through the decentralized control mechanism, each device independently adjusts the reactive power output to avoid the delay and single point failure caused by centralized control. At the same time, the control strategy ensures that the power output of the devices can be automatically synchronized to maintain coordination and avoid unnecessary power conflicts or interference.

[0035] 4. Dynamic adjustment and feedback mechanism: The control strategy will continuously monitor the real-time operation status of the power grid and dynamically adjust the output of each device. When the power grid conditions or device status change, the control strategy will update the output instructions of the device in real time to ensure that the stability of the power grid is not affected.

[0036] 5. Emergency response strategy: When voltage or frequency fluctuations exceed preset thresholds, the control strategy triggers emergency response measures, such as rapidly increasing or decreasing reactive power output, to ensure that the grid can quickly recover stability in extreme situations.

[0037] Preferably, the multi-objective optimization module dynamically calculates the voltage fluctuation index and the frequency fluctuation index based on the evaluation results and the real-time active power output of the wind farm, and combines the reactive power demand and the voltage stability requirement to calculate the required reactive power regulation through multi-objective optimization analysis, and determines the response priority and control strategy of each device, including: Obtaining real-time active power output data from the wind farm at the current moment; Calculate the current voltage fluctuation index and frequency fluctuation index based on the real-time active power output data and the operating status of the wind farm; Obtain the current reactive power demand and voltage stability requirements of the power grid, and establish a multi-objective optimization model with the goals of minimizing voltage fluctuation, minimizing frequency fluctuation and meeting the reactive power demand of the power grid; Based on the multi-objective optimization model, the reactive power regulation that meets the voltage stability and frequency stability requirements is dynamically calculated; and the response priority of different equipment is determined according to the reactive power regulation and the regulation capabilities of various equipment; Based on the response priority of different devices, the control strategy of the equipment is formulated to adjust the reactive power output of each device to ensure that the reactive power demand of the power grid is met in real time, maintain voltage and frequency stability, and optimize the operating efficiency of the wind farm.

[0038] Preferably, the expression for minimizing voltage fluctuation, minimizing frequency fluctuation and satisfying reactive power demand of the power grid is: ; In the formula, It represents the weighted sum of voltage fluctuation, frequency fluctuation and reactive power deviation in the multi-objective optimization model; Indicates the current reactive power demand of the power grid; Represents the reactive power output provided by the wind farm; Indicates the absolute value of frequency deviation; Indicates the absolute value of voltage deviation; w 1 represents the weight factor of voltage fluctuation; w 2 represents the weight factor of frequency fluctuation; w 3 represents the weighting factor of reactive power deviation.

[0039] Preferably, based on the multi-objective optimization model, the reactive power regulation amount that meets the voltage stability and frequency stability requirements is dynamically calculated; and according to the reactive power regulation amount and the regulation capabilities of various types of equipment, the response priorities of different equipment are determined, including: Calculate the optimal reactive power regulation that meets the voltage and frequency stability requirements based on a multi-objective optimization model; Calculate the reactive power regulation capacity of each device by the ratio of its actual reactive power output capacity to its rated output; Evaluate the regulation capability of each device based on its reactive power regulation capability; Determine the response priority of each device based on the reactive power regulation amount and the regulation capacity of each device, and formulate the reactive power regulation task of each device in the order of response priority; The expression for determining the response priority of each device is: ; ; In the formula, Indicates the device i The actual reactive power output; Indicates the device i Rated reactive output; α i Indicates the device i Reactive power regulation capability; Indicates the device i The response priority.

[0040] It should be explained that the above content describes the workflow of a multi-objective optimization module, which is used to dynamically calculate the voltage volatility and frequency volatility indicators, and determine the reactive regulation amount and the response priority of each device through optimization analysis. First, based on the real-time active power output and evaluation results of the wind farm, the current voltage and frequency volatility indicators are calculated. Then, combined with the reactive power demand and voltage stability requirements of the power grid, a multi-objective optimization model is established to minimize voltage, frequency fluctuations and reactive power deviations. Through this optimization model, the required reactive regulation amount is calculated, and the response priority of each device is determined based on its reactive regulation capability, and the device control strategy is formulated to ensure the stability of the power grid and optimize the operating efficiency of the wind farm.

[0041] The high volatility response module 3 is used to adjust the virtual oscillator according to the response priority of each device when the voltage volatility index and the frequency volatility index exceed the preset threshold, and take corresponding control measures based on the control strategy to stabilize the voltage and frequency of the power grid.

[0042] It needs to be explained that when the voltage and frequency volatility indicators exceed the preset safety thresholds, the virtual oscillator will be adjusted according to the response priority of each device and take corresponding control measures according to the pre-set control strategy to quickly stabilize the voltage and frequency of the power grid and ensure the stable operation of the power grid under high fluctuations.

[0043] The low volatility management module 4 is used to control the reactive power output of each device according to the real-time demand of the power grid by the virtual oscillator when the voltage volatility index and the frequency volatility index do not exceed the preset threshold value; and realize automatic synchronization between devices through a decentralized control mechanism, while dynamically allocating reactive power regulation tasks and adaptively adjusting the power output of each device.

[0044] Preferably, when the voltage volatility index and the frequency volatility index do not exceed the preset threshold, the low volatility management module controls the reactive power output of each device according to the real-time demand of the power grid through the virtual oscillator; and realizes automatic synchronization between devices through a decentralized control mechanism, while dynamically allocating reactive power regulation tasks and adaptively adjusting the power output of each device, including: Monitor the voltage fluctuation index and frequency fluctuation index of the power grid in real time to determine whether they exceed the preset threshold; When the voltage and frequency volatility indicators do not exceed the preset thresholds, the virtual oscillator controls the reactive power output of each device according to the real-time needs of the power grid; Using a decentralized control mechanism, each device is allowed to automatically adjust its output according to the control instructions of the virtual oscillator, achieving automatic synchronization between devices; Dynamically allocate reactive power regulation tasks to different devices according to the real-time needs of the power grid; Each device adaptively adjusts its reactive power output according to real-time grid demand and its own operating status, ensuring that the grid voltage and frequency remain stable when demand changes; Continuously monitor the output of the equipment and the response of the power grid, and dynamically adjust the reactive output of each device based on the feedback.

[0045] It should be explained that when the voltage and frequency volatility indicators do not exceed the preset thresholds, the virtual oscillator controls the reactive power output of each device according to the real-time needs of the power grid. Through the decentralized control mechanism, each device automatically adjusts the output and keeps synchronization. According to real-time needs, reactive regulation tasks are dynamically allocated, and each device adaptively adjusts the power output to ensure the stability of the power grid. At the same time, the device output and the power grid response are continuously monitored, and the reactive power output is dynamically adjusted based on feedback to ensure the stability of voltage and frequency.

[0046] According to another embodiment of the present invention, Figure 2 As shown, a virtual oscillator-assisted wind farm reactive power coordination method is also provided, and the virtual oscillator-assisted wind farm reactive power coordination method comprises the following steps: S1. Use multi-level neural networks to comprehensively predict the multi-dimensional operating parameters of wind farms and power grids, and evaluate the parameter operating status and power fluctuation trend within a preset time in the future; S2. Based on the evaluation results and the real-time active power output of the wind farm, the voltage fluctuation index and frequency fluctuation index are dynamically calculated. In combination with the reactive power demand and voltage stability requirements, the required reactive power regulation is calculated through multi-objective optimization analysis to determine the response priority and control strategy of each device. S3. When the voltage fluctuation index and the frequency fluctuation index exceed the preset threshold, the virtual oscillator will be adjusted according to the response priority of each device and take corresponding control measures based on the control strategy to stabilize the voltage and frequency of the power grid; S4. When the voltage volatility index and the frequency volatility index do not exceed the preset threshold, the virtual oscillator controls the reactive power output of each device according to the real-time demand of the power grid; and realizes automatic synchronization between devices through a decentralized control mechanism, while dynamically allocating reactive power regulation tasks and adaptively adjusting the power output of each device.

[0047] In summary, with the help of the above technical scheme of the present invention, the present invention uses a multi-level neural network model, combined with a feature selection algorithm and historical data for training, to effectively predict the future voltage fluctuations, frequency fluctuations and power fluctuations of wind farms and power grids, and by comparing and analyzing historical data with the prediction results, the prediction accuracy of the model is evaluated, and the future power grid operation status and power fluctuation trend can be foreseen in advance, thereby improving the operation stability and regulation efficiency of wind farms and power grids, and helping to optimize the decision-making and management of power systems; the present invention obtains the active power output data of the wind farm in real time, calculates the voltage volatility and frequency volatility indicators, and combines the reactive power demand and voltage stability requirements of the power grid, and uses a multi-objective optimization model to dynamically calculate the required reactive power regulation amount, and can determine the response priority according to the regulation capability of the equipment, and formulate the reactive power regulation task and control strategy of the equipment, thereby ensuring that the power grid maintains the stability of voltage and frequency while meeting the reactive power demand, improving the operation efficiency and stability of the wind farm and the power grid, and optimizing the allocation and management of resources.

[0048] Although the present invention has been disclosed as above with preferred embodiments, the embodiments are merely examples for the convenience of description and are not intended to limit the present invention. Those skilled in the art may make several changes and modifications without departing from the spirit and scope of the present invention. The scope of protection claimed by the present invention shall be based on the claims.

Claims

1. A virtual oscillator assisted wind farm reactive power coordination system, characterized in that: The virtual oscillator assisted wind farm reactive power coordination system includes: a comprehensive prediction module, a multi-objective optimization module, a high volatility response module and a low volatility management module; The comprehensive prediction module is used to use a multi-level neural network to comprehensively predict the multi-dimensional operating parameters of the wind farm and the power grid, and evaluate the parameter operating status and power fluctuation trend within a preset time in the future; The multi-objective optimization module is used to dynamically calculate the voltage fluctuation index and the frequency fluctuation index based on the evaluation results and the real-time active power output of the wind farm, and to determine the response priority and control strategy of each device by calculating the required reactive power regulation amount through multi-objective optimization analysis and calculation in combination with reactive power demand and voltage stability requirements; The high volatility response module is used to adjust the virtual oscillator according to the response priority of each device when the voltage volatility index and the frequency volatility index exceed the preset threshold, and take corresponding control measures based on the control strategy to stabilize the voltage and frequency of the power grid; The low volatility management module is used to control the reactive power output of each device according to the real-time demand of the power grid by the virtual oscillator when the voltage volatility index and the frequency volatility index do not exceed the preset threshold value; and realize automatic synchronization between devices through a decentralized control mechanism, while dynamically allocating reactive power regulation tasks and adaptively adjusting the power output of each device.

2. A virtual oscillator assisted wind farm reactive power coordination system according to claim 1, characterized in that: The comprehensive prediction module includes a data collection unit, a feature selection unit, a model building and training unit, a prediction and verification unit, and a comparative analysis unit; The data collection unit is used to collect multi-dimensional operating parameters from the historical database of the wind farm and the power grid; The feature selection unit is used to extract feature data associated with the operating state and power fluctuation from the collected multi-dimensional operating parameters using a feature selection algorithm; The model building and training unit is used to build a multi-level neural network model, input the extracted feature data, perform multiple rounds of iterative training through the training set, and use an optimization algorithm to adjust the weights and biases of the multi-level neural network model; The prediction and verification unit is used to use the trained multi-level neural network model to predict the operation status of the wind farm and the power grid within a preset time in the future, output the prediction results of voltage fluctuation, frequency fluctuation and power fluctuation, and verify the prediction results through a test set; The comparison and analysis unit is used to compare and analyze the predicted voltage fluctuation, frequency fluctuation and power fluctuation with the historical operation data of the wind farm and the power grid, and evaluate the parameter operation status and power fluctuation trend within a preset time in the future.

3. A virtual oscillator assisted wind farm reactive power coordination system according to claim 2, characterized in that: The feature selection unit, when extracting feature data associated with the operating state and power fluctuation from the collected multi-dimensional operating parameters using a feature selection algorithm, includes: Standardize the collected multi-dimensional operating parameters; Calculate the covariance matrix of standardized multi-dimensional operating parameters; Perform eigenvalue decomposition on the covariance matrix to extract eigenvalues ​​and corresponding eigenvectors, where the eigenvalues ​​represent the size of the data variance explained by each principal component, and the eigenvectors represent the directions of each principal component; Sort the eigenvalues ​​from high to low, and select the principal components that meet the preset proportion requirements as the extracted feature data; The collected multi-dimensional operating parameters are projected into the space composed of the selected principal components to obtain the feature data after dimensionality reduction.

4. A virtual oscillator assisted wind farm reactive power coordination system according to claim 3, characterized in that: The model building and training unit includes the following steps when building a multi-level neural network model, inputting the extracted feature data, performing multiple rounds of iterative training through a training set, and adjusting the weights and biases of the multi-level neural network model using an optimization algorithm: Divide the extracted feature data into training set, validation set and test set, and prepare the time series data required by the long short-term memory network and the tensor format required by the convolutional neural network; Construct a multi-level neural network model including 1D convolution layer, maximum pooling layer, long short-term memory network layer and fully connected layer to extract spatial features and temporal dependencies respectively; Build a multi-level neural network model, select mean square error as the loss function, Adam optimizer as the optimizer, and set the evaluation indicators; Use the training data to perform multiple rounds of iterative training. In each round of iteration, calculate the loss and evaluation indicators based on the data of the validation set, and dynamically adjust the weights and biases of the multi-level neural network model; Monitor the loss changes of the validation set during training and select the best model parameters based on the performance of the validation set; The prediction performance of the model is evaluated using the test set and the final evaluation metrics are calculated.

5. A virtual oscillator assisted wind farm reactive power coordination system according to claim 4, characterized in that: The comparison and analysis unit compares and analyzes the predicted voltage fluctuation, frequency fluctuation and power fluctuation with the historical operation data of the wind farm and the power grid to evaluate the parameter operation status and power fluctuation trend within a preset time in the future, including: Collect the voltage fluctuation, frequency fluctuation and power fluctuation data predicted by the model and match them with the historical operation data of the corresponding time period; Use error indicators to evaluate the error between the forecast results and historical data, and draw comparative analysis charts to show the matching degree between the forecast results and historical data and the error trend; Based on the calculated error indicators and chart analysis results, the model's prediction accuracy for voltage, frequency, and power fluctuations is evaluated, and the prediction effect of the model at different time points and conditions is determined; Based on the error analysis results, evaluate the parameter operating status and power fluctuation trend within the future preset time.

6. A virtual oscillator assisted wind farm reactive power coordination system according to claim 1, characterized in that: The multi-objective optimization module dynamically calculates the voltage fluctuation index and the frequency fluctuation index based on the evaluation results and the real-time active power output of the wind farm, and combines the reactive power demand and the voltage stability requirements to calculate the required reactive power regulation through multi-objective optimization analysis and determine the response priority and control strategy of each device. Obtaining real-time active power output data from the wind farm at the current moment; Calculate the current voltage fluctuation index and frequency fluctuation index based on the real-time active power output data and the operating status of the wind farm; Obtain the current reactive power demand and voltage stability requirements of the power grid, and establish a multi-objective optimization model with the goals of minimizing voltage fluctuation, minimizing frequency fluctuation and meeting the reactive power demand of the power grid; Based on the multi-objective optimization model, the reactive power regulation that meets the voltage stability and frequency stability requirements is dynamically calculated; and the response priority of different equipment is determined according to the reactive power regulation and the regulation capabilities of various equipment; Based on the response priority of different devices, the control strategy of the equipment is formulated to adjust the reactive power output of each device to ensure that the reactive power demand of the power grid is met in real time, maintain voltage and frequency stability, and optimize the operating efficiency of the wind farm.

7. A virtual oscillator assisted wind farm reactive power coordination system according to claim 6, characterized in that: The expression for minimizing voltage fluctuation, minimizing frequency fluctuation and satisfying reactive power demand of the power grid is: ； In the formula, It represents the weighted sum of voltage fluctuation, frequency fluctuation and reactive power deviation in the multi-objective optimization model; Indicates the current reactive power demand of the power grid; Represents the reactive power output provided by the wind farm; Indicates the absolute value of frequency deviation; Indicates the absolute value of voltage deviation; w 1 represents the weight factor of voltage fluctuation; w 2 represents the weight factor of frequency fluctuation; w 3 represents the weighting factor of reactive power deviation.

8. A virtual oscillator assisted wind farm reactive power coordination system according to claim 7, characterized in that: The reactive power regulation amount that meets the voltage stability and frequency stability requirements is dynamically calculated based on the multi-objective optimization model; According to the reactive power regulation amount and the regulation capability of various equipment, the response priority of different equipment is determined, including: Calculate the optimal reactive power regulation that meets the voltage and frequency stability requirements based on a multi-objective optimization model; Calculate the reactive power regulation capacity of each device by the ratio of its actual reactive power output capacity to its rated output; Evaluate the regulation capability of each device based on its reactive power regulation capability; Determine the response priority of each device based on the reactive power regulation amount and the regulation capacity of each device, and formulate the reactive power regulation task of each device in the order of response priority; The expression for determining the response priority of each device is: ； ； In the formula, Indicates the device i The actual reactive power output; Indicates the device i Rated reactive output; α i Indicates the device i Reactive power regulation capability; Indicates the device i The response priority.

9. A virtual oscillator assisted wind farm reactive power coordination system according to claim 1, characterized in that: The low volatility management module controls the reactive power output of each device according to the real-time demand of the power grid by the virtual oscillator when the voltage volatility index and the frequency volatility index do not exceed the preset threshold value; The decentralized control mechanism is used to achieve automatic synchronization between devices, dynamically allocate reactive power regulation tasks, and adaptively adjust the power output of each device, including: Monitor the voltage fluctuation index and frequency fluctuation index of the power grid in real time to determine whether they exceed the preset threshold; When the voltage and frequency volatility indicators do not exceed the preset thresholds, the virtual oscillator controls the reactive power output of each device according to the real-time needs of the power grid; Using a decentralized control mechanism, each device is allowed to automatically adjust its output according to the control instructions of the virtual oscillator, achieving automatic synchronization between devices; Dynamically allocate reactive power regulation tasks to different devices according to the real-time needs of the power grid; Each device adaptively adjusts its reactive power output according to real-time grid demand and its own operating status, ensuring that the grid voltage and frequency remain stable when demand changes; Continuously monitor the output of the equipment and the response of the power grid, and dynamically adjust the reactive output of each device based on the feedback.

10. A virtual oscillator assisted wind farm reactive power coordination method, used to implement the virtual oscillator assisted wind farm reactive power coordination system according to any one of claims 1 to 9, characterized in that: The virtual oscillator assisted wind farm reactive power coordination method comprises the following steps: S1. Use multi-level neural networks to comprehensively predict the multi-dimensional operating parameters of wind farms and power grids, and evaluate the parameter operating status and power fluctuation trend within a preset time in the future; S2. Based on the evaluation results and the real-time active power output of the wind farm, the voltage fluctuation index and frequency fluctuation index are dynamically calculated. In combination with the reactive power demand and voltage stability requirements, the required reactive power regulation is calculated through multi-objective optimization analysis to determine the response priority and control strategy of each device. S3. When the voltage fluctuation index and the frequency fluctuation index exceed the preset threshold, the virtual oscillator will be adjusted according to the response priority of each device and take corresponding control measures based on the control strategy to stabilize the voltage and frequency of the power grid; S4. When the voltage volatility index and the frequency volatility index do not exceed the preset threshold, the virtual oscillator controls the reactive power output of each device according to the real-time demand of the power grid; and realizes automatic synchronization between devices through a decentralized control mechanism, while dynamically allocating reactive power regulation tasks and adaptively adjusting the power output of each device.

Images