Grid frequency regulation method and device based on wind-storage coordinated inertia response

Abstract

The present invention discloses a grid frequency regulation method and device based on wind-storage collaborative inertia response, which relates to the field of grid safety technology, and is mainly capable of improving the timeliness and accuracy of grid frequency regulation. It includes: obtaining the operating status time series data and environmental time series data of the local grid under different frequency regulation nodes; based on the operating status time series data and environmental time series data, performing high-frequency prediction on the frequency of each local grid in the first preset time window in the future and performing low-frequency prediction on the frequency in the second preset time window in the future, and obtaining the high-frequency fluctuation extreme value and the low-frequency trend mean; based on the high-frequency fluctuation extreme value and the low-frequency trend mean, determining the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment, and distributively and collaboratively regulating the local grid based on the wind power output power regulation value and the energy storage output power regulation value. The present invention is applicable to grid frequency regulation scenarios.

Description

Technical Field

[0001] The present invention relates to the field of power grid safety technology, and in particular to a power grid frequency regulation method and device based on wind-storage coordinated inertia response. Background Art

[0002] As global demand for renewable energy increases, wind power, as a key renewable energy source, continues to expand its application. However, the random and intermittent nature of wind power leads to unstable output power, which in turn exacerbates grid frequency fluctuations. This frequency regulation becomes even more complex, especially when large-scale wind power is integrated. This fluctuation not only affects grid stability but also poses significant challenges to traditional power systems.

[0003] Currently, grid frequency is typically regulated based on existing grid frequency fluctuations. However, this regulation method has a certain lag, which can cause the grid frequency to remain unstable during the regulation process, adversely affecting power equipment and user experience. Furthermore, new fluctuations may occur during the regulation process, leading to inaccurate grid frequency regulation. Summary of the Invention

[0004] The present invention provides a grid frequency regulation method and device based on wind-storage collaborative inertia response, which mainly aims to improve the timeliness and accuracy of grid frequency regulation and avoid adverse effects on power equipment and user electricity consumption.

[0005] According to a first aspect of the present invention, a method for regulating grid frequency based on wind-storage coordinated inertia response is provided, comprising:

[0006] In response to a frequency adjustment signal of a target power grid, obtaining time series data on the operating status of local power grids at different frequency adjustment nodes and time series data on the environment in which the wind power supply equipment corresponding to each of the local power grids is located, wherein the target power grid is composed of multiple local power grids, and different local power grids perform frequency adjustment through different frequency adjustment nodes;

[0007] Based on the operating status time series data and the environmental time series data, a high-frequency prediction is performed in real time on the frequency of each of the local power grids within a first preset time window in the future to obtain a high-frequency fluctuation extreme value of the local power grid frequency; and based on the operating status time series data and the environmental time series data, a low-frequency prediction is performed in real time on the frequency of each of the local power grids within a second preset time window in the future to obtain a low-frequency trend mean value of the local power grid frequency;

[0008] Based on the high-frequency fluctuation extreme value and the low-frequency trend mean value, the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids are determined, and based on the wind power output power adjustment value, the corresponding wind power supply equipment is coordinated and adjusted in real time to perform power transmission operations to the corresponding local power grid, and based on the energy storage output power adjustment value, the corresponding energy storage equipment is coordinated and controlled in real time to perform charging and discharging operations to the corresponding local power grid.

[0009] Optionally, the operating status time series data includes grid frequency time series data and grid load time series data of the local power grid, and the environmental time series data includes wind speed time series data;

[0010] The method of performing high-frequency prediction on the frequency of each local power grid within a first preset time window in the future based on the operating state time series data and the environmental time series data in real time to obtain a high-frequency fluctuation extreme value of the local power grid frequency includes:

[0011] Determine the grid frequency change rate based on the grid frequency time series data, determine the grid load change amount based on the grid load time series data, and determine the wind speed change rate based on the wind speed time series data;

[0012] Respectively determining a frequency characteristic vector corresponding to the grid frequency change rate, a load characteristic vector corresponding to the grid load change amount, and a wind speed characteristic vector corresponding to the wind speed change rate, and determining a frequency prediction characteristic vector based on the frequency characteristic vector, the load characteristic vector, and the wind speed characteristic vector;

[0013] The frequency prediction feature vector is input into a preset high-frequency prediction model for frequency prediction to obtain the high-frequency fluctuation extreme value of each local power grid within a first preset time window in the future, wherein the preset high-frequency prediction model is pre-trained based on a high-frequency sample data set with high-frequency fluctuation extreme value labels.

[0014] Optionally, the performing of a low-frequency prediction on the frequency of each local power grid within a second preset time window in the future in real time based on the operating status time series data and the environmental time series data to obtain a low-frequency trend mean of the local power grid frequency includes:

[0015] The grid frequency time series data in the operating status time series data and the wind speed time series data in the environmental time series data are input into a preset low-frequency prediction model for frequency prediction to obtain the low-frequency trend mean of each local power grid in a second preset time window in the future, wherein the second preset time window is larger than the first preset time window, and the preset low-frequency prediction model is pre-trained based on a low-frequency sample data set with a low-frequency trend mean label.

[0016] Optionally, determining the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment in each of the local power grids based on the high-frequency fluctuation extreme value and the low-frequency trend mean value includes:

[0017] Determining a high-frequency prediction error of the high-frequency fluctuation extreme value during the prediction process and a low-frequency prediction error of the low-frequency trend mean during the prediction process, and determining a high-frequency fusion coefficient corresponding to the high-frequency fluctuation extreme value and a low-frequency fusion coefficient corresponding to the low-frequency trend mean based on the high-frequency prediction error and the low-frequency prediction error, respectively;

[0018] Based on the high frequency fusion coefficient and the low frequency fusion coefficient, the high frequency fluctuation extreme value and the low frequency trend mean value are fused to obtain the fused grid frequency value. ;

[0019] Based on the integrated grid frequency value , determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids.

[0020] Optionally, the frequency value of the integrated power grid is , determining the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids, including:

[0021] Determine the virtual inertia reference value of wind power supply equipment i and the virtual inertia response adjustment factor at the current time t ;

[0022] Based on the virtual inertia reference value , the virtual inertia response adjustment factor , the fused grid frequency value , determine the wind power supply equipment under each local power grid The wind power output power adjustment value at the current time t ,in, ;

[0023] Determine the rated power of the energy storage device and the energy storage adjustment factor at the current time t ;

[0024] Based on the rated power , the energy storage adjustment factor and the fused grid frequency value , determine the energy storage output power adjustment value of each energy storage device under the local power grid at the current time t ,in, .

[0025] Optionally, determine the virtual inertia response adjustment factor at the current time t ,include:

[0026] determining a frequency relationship function between a grid frequency deviation of the local power grid at the current time t and a virtual inertia response adjustment factor to be optimized, and determining an optimization constraint condition for the virtual inertia response adjustment factor to be optimized based on an output power constraint of the wind power supply equipment and a power relationship function between the virtual inertia response adjustment factor to be optimized and the output power of the wind power supply equipment;

[0027] Based on the optimization constraints, the grid frequency deviation satisfies the preset conditions as the optimization index, the virtual inertia response adjustment factor to be optimized is optimized, and based on the optimization result, the virtual inertia response adjustment factor of the wind power supply equipment at the current time t is determined. , wherein the preset condition is that the grid frequency deviation is within a preset deviation range.

[0028] Optionally, the real-time distributed coordinated adjustment of corresponding wind power supply equipment to perform power transmission operations to the corresponding local power grid based on the wind power output power adjustment value, and the real-time distributed coordinated control of corresponding energy storage equipment to perform charging and discharging operations to the corresponding local power grid based on the energy storage output power adjustment value, include:

[0029] Any frequency regulation node in each of the frequency regulation nodes is respectively used as a target frequency regulation node, the wind power output power regulation value and the energy storage output power regulation value under the target frequency regulation node are respectively determined as the reference wind power output power regulation value and the reference energy storage output power regulation value, and the reference wind power output power regulation value and the reference energy storage output power regulation value are respectively sent to other frequency regulation nodes, so that the other frequency regulation nodes perform distributed collaborative frequency regulation on the corresponding local power grid based on the corresponding wind power output power regulation value, the energy storage output power regulation value, the reference wind power output power regulation value, and the reference energy storage output power regulation value, wherein the other frequency regulation nodes refer to the nodes in each of the frequency regulation nodes excluding the target frequency regulation node.

[0030] According to a second aspect of the present invention, there is provided a grid frequency regulation device based on wind-storage coordinated inertia response, comprising:

[0031] an acquisition unit, configured to acquire, in response to a frequency adjustment signal of a target power grid, time series data of operating states of local power grids under different frequency adjustment nodes and time series data of the environment in which the wind power supply equipment corresponding to each of the local power grids is located, wherein the target power grid is composed of a plurality of local power grids, and frequency adjustment is performed on different local power grids through different frequency adjustment nodes;

[0032] a frequency prediction unit, configured to perform a high-frequency prediction on the frequency of each of the local power grids in a first preset time window in the future based on the operating status time series data and the environmental time series data, in real time, to obtain a high-frequency fluctuation extreme value of the local power grid frequency; and to perform a low-frequency prediction on the frequency of each of the local power grids in a second preset time window in the future based on the operating status time series data and the environmental time series data, in real time, to obtain a low-frequency trend mean value of the local power grid frequency;

[0033] a frequency regulation unit for determining, based on the high-frequency fluctuation extreme value and the low-frequency trend mean, a wind power output power regulation value of the wind power supply equipment and an energy storage output power regulation value of the energy storage equipment under each of the local power grids, and for performing real-time distributed and coordinated regulation of the corresponding wind power supply equipment to perform power transmission operations to the corresponding local power grid based on the wind power output power regulation value, and for performing real-time distributed and coordinated control of the corresponding energy storage equipment to perform charging and discharging operations to the corresponding local power grid based on the energy storage output power regulation value.

[0034] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the above-mentioned grid frequency regulation method based on the coordinated inertia response of wind and storage is implemented.

[0035] According to a fourth aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the grid frequency regulation method based on the coordinated inertia response of wind and storage is implemented.

[0036] According to the present invention, a grid frequency regulation method and device based on wind-storage collaborative inertia response is provided. Compared with the current method of regulating the grid frequency based on the grid frequency fluctuations that have already occurred, the present invention uses the operating status time series data of the local grid under different frequency regulation nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each local grid is located to perform high-frequency prediction and low-frequency prediction of the grid frequency at future moments, respectively, and determines the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment based on the predicted high-frequency fluctuation extreme value and low-frequency trend mean value. Finally, based on the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment, the frequency of the local grid is distributed and coordinated. Therefore, by adjusting the grid frequency according to the predicted grid frequency value at a future moment, potential frequency fluctuation trends can be discovered in time, so that preventive measures can be taken in advance, thereby improving the timeliness of frequency adjustment and ensuring the stable operation of the grid; at the same time, combining the high-frequency prediction and low-frequency prediction of the grid frequency to adjust the grid frequency, it is possible to capture both the short-term rapid changes in the grid frequency and the long-term change trends of the grid frequency, thereby realizing comprehensive monitoring and analysis of the grid frequency, thereby improving the adjustment accuracy of the grid frequency; at the same time, the present invention can ensure that when a frequency adjustment node fails, it will not affect the control process of other frequency adjustment nodes by distributedly and collaboratively adjusting the frequency of the corresponding local grid through multiple frequency adjustment nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0038] Figure 1 A flow chart of a grid frequency regulation method based on wind-storage coordinated inertia response provided by an embodiment of the present invention is shown;

[0039] Figure 2 A schematic diagram of frequency fluctuations for high-frequency prediction of a local power grid provided by an embodiment of the present invention is shown;

[0040] Figure 3 A schematic diagram of a frequency fluctuation trend for low-frequency prediction of a local power grid provided by an embodiment of the present invention is shown;

[0041] Figure 4A A schematic diagram of a local power grid frequency fluctuation situation provided by an embodiment of the present invention is shown;

[0042] Figure 4B An embodiment of the present invention provides a method for Figure 4ASchematic diagram of power output of wind power supply equipment when adjusting the local grid frequency fluctuation;

[0043] Figure 4C An embodiment of the present invention provides a method for Figure 4A Schematic diagram of the power output of the energy storage device when adjusting the local grid frequency fluctuation;

[0044] Figure 5 A flow chart of another grid frequency regulation method based on wind-storage collaborative inertia response provided by an embodiment of the present invention is shown;

[0045] Figure 6 A schematic diagram of the structure of a power grid frequency regulation device based on wind-storage coordinated inertia response provided by an embodiment of the present invention is shown;

[0046] Figure 7 A schematic structural diagram of another power grid frequency regulation device based on wind-storage coordinated inertia response provided by an embodiment of the present invention is shown;

[0047] Figure 8 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0048] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0049] At present, the method of adjusting the grid frequency based on the grid frequency fluctuations that have already occurred has a certain lag. This lag may cause the grid frequency to remain unstable during the adjustment process, causing adverse effects on power equipment and users' electricity consumption experience.

[0050] In order to solve the above problems, the embodiment of the present invention provides a grid frequency regulation method based on wind-storage coordinated inertia response, such as Figure 1 As shown, the method includes:

[0051] 101. In response to the frequency regulation signal of the target power grid, obtain the operating status time series data of the local power grid under different frequency regulation nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each local power grid is located, wherein the target power grid is composed of multiple local power grids, and different local power grids perform frequency regulation through different frequency regulation nodes.

[0052] Among them, the operating status time series data refers to the grid frequency time series data composed of the grid frequency from the historical moment to the current moment and the grid load time series data composed of the grid load; the environmental time series data refers to the time series data composed of the wind speed around the wind power supply equipment from the historical moment to the current moment.

[0053] In this embodiment of the present invention, a deep intelligent scheduling algorithm within the grid frequency regulation system dynamically adjusts the power output of wind power supply equipment and energy storage devices to achieve dynamic, real-time frequency regulation of the target power grid. The grid frequency regulation system includes a wide-area measurement module, a wind power monitoring module, and an energy storage management module. The wide-area measurement module measures grid frequency, grid load, wind speed, and other data; the wind power monitoring module controls the output power of wind power supply equipment and collects wind turbine speed data; and the energy storage management module controls the charging and discharging operations of the energy storage device. To improve grid frequency regulation accuracy, this embodiment of the present invention also constructs a grid frequency regulation simulation platform before performing grid frequency regulation. This simulation platform configures a wind power-energy storage joint simulation model and uses a deep learning framework for model training and optimization. For hardware deployment, edge intelligent gateways and industrial modules (e.g., end-to-end latency ≤ 3 ms) can be used to ensure real-time and low-latency data processing. Furthermore, regarding core parameters, the virtual inertia reference value can be set within an adjustable range of 1.8 seconds to 6.5 seconds, and the energy storage device output is capped at 40% of the wind power supply device output. Afterwards, the grid frequency regulation is simulated based on the grid frequency regulation simulation platform to verify the feasibility and accuracy of the grid frequency regulation method in the embodiment of the present invention.

[0054] Specifically, when the grid frequency regulation system is used to regulate the grid frequency, the target grid is divided into multiple local grids based on factors such as region, load type, and grid structure, and each local grid is controlled by a different frequency regulation node. Furthermore, when a frequency regulation signal for the target grid is received, the operating status time series data and environmental time series data of the local grid under each frequency regulation node can be collected based on modules such as wide-area measurement, and distributed collaborative frequency regulation can be performed on each local grid using the operating status time series data and environmental time series data. Thus, by performing distributed collaborative regulation on multiple local grids, the impact of single-point failures on the entire grid is avoided.

[0055] 102. Based on the operating status time series data and the environmental time series data, a high-frequency prediction is performed in real time on the frequency of each local power grid in a first preset time window in the future to obtain the high-frequency fluctuation extreme value of the local power grid frequency; and based on the operating status time series data and the environmental time series data, a low-frequency prediction is performed in real time on the frequency of each local power grid in a second preset time window in the future to obtain the low-frequency trend mean value of the local power grid frequency.

[0056] Among them, the first preset time window and the second preset time window are set according to actual needs. The size of the first preset time window is smaller than the size of the second preset time window. For example, the first preset time window can be set to a 3-second time window, and the second preset time window can be set to a 10-minute time window.

[0057] For the embodiment of the present invention, a high-frequency prediction within a first preset time window and a low-frequency prediction within a second preset time window are performed on each local power grid respectively, such as Figure 2 The frequency fluctuation situation obtained by high-frequency prediction of a certain local power grid is shown. Based on the frequency fluctuation situation, the high-frequency fluctuation extreme value of the local power grid within the first preset time window can be determined. Figure 3 The frequency fluctuation trend obtained by low-frequency prediction of a certain local power grid is shown. Based on the frequency fluctuation trend, the low-frequency trend mean of the local power grid within the second preset time window can be determined. The embodiment of the present invention adjusts the power grid frequency by combining high-frequency prediction and low-frequency prediction of the power grid frequency. It can simultaneously capture the rapid changes in the power grid frequency and the long-term change trend of the power grid frequency, realize comprehensive monitoring and analysis of the power grid frequency, and thus improve the accuracy of power grid frequency regulation. At the same time, the embodiment of the present invention adjusts the power grid frequency by predicting future power grid frequency fluctuations, which can achieve timely power grid frequency regulation.

[0058] 103. Based on the high-frequency fluctuation extreme values ​​and the low-frequency trend mean values, determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each local power grid, and based on the wind power output power adjustment value, coordinately adjust the corresponding wind power supply equipment in a distributed manner to perform power transmission operations to the corresponding local power grid in real time, and based on the energy storage output power adjustment value, coordinately control the corresponding energy storage equipment in a distributed manner to perform charging and discharging operations to the corresponding local power grid in real time.

[0059] In this embodiment of the present invention, after determining the wind power output power adjustment value for each wind power supply device and the energy storage device's energy storage output power adjustment value for each local power grid, each wind power supply device and energy storage device can independently make adjustment decisions based on local information (the wind power output power adjustment value and the energy storage output power adjustment value). Specifically, each frequency adjustment node implements an autonomous grid frequency and power adjustment strategy by monitoring local grid frequency, grid load, and wind speed changes in real time. This decentralized control approach ensures high system responsiveness and flexibility. Simultaneously, each frequency adjustment node periodically transmits local adjustment status information (such as the current grid frequency, wind power output power adjustment value, and energy storage output power adjustment value) to other frequency adjustment nodes. Through this information exchange mechanism, each frequency adjustment node can coordinately adjust the power output of the corresponding wind power supply device and energy storage device in a distributed manner, ensuring adjustment consistency between wind power supply devices and energy storage devices at different frequency adjustment nodes and avoiding over-adjustment or inconsistent responses. Furthermore, the wind power supply devices and energy storage devices in this embodiment of the present invention also utilize a coordinated adjustment approach to achieve optimal frequency regulation. Therefore, the embodiment of the present invention uses multiple frequency regulation nodes to coordinately regulate the frequency of the corresponding local power grid in a distributed manner, which can ensure that when a frequency regulation node fails, the control process of other frequency regulation nodes is not affected.

[0060] Embodiments of the present invention propose an adaptive frequency response strategy that employs different adjustment methods based on the type of grid frequency fluctuation (such as low-frequency events and high-frequency events) and the magnitude of the fluctuation. For example, in low-frequency event adjustment, when the grid frequency falls below a preset threshold (the preset threshold is a value set based on actual needs), the system enters low-frequency response mode, during which wind power supply equipment and energy storage devices prioritize response. The wind power supply equipment's virtual inertia output power and the energy storage equipment's power output increase to help the grid restore frequency. The energy storage device dynamically adjusts its charging and discharging strategy based on frequency deviation and predicted low-frequency fluctuations to provide necessary power support. In high-frequency event adjustment, when the grid frequency rises above a preset threshold, the system enters high-frequency response mode, during which wind power supply equipment and energy storage devices reduce their power output to prevent excessively high grid frequency. The output power of the wind power supply equipment and energy storage devices is dynamically adjusted based on the grid's real-time frequency and predicted high-frequency fluctuations to balance excessive grid frequency fluctuations. Frequency fluctuation amplitude adjustment: The grid frequency adjustment system can adjust the response strategy according to the amplitude and duration of the frequency fluctuation. When the frequency fluctuation amplitude is large, the wind power supply equipment and energy storage equipment will increase the response strength and adjust the power output in time. When the frequency fluctuation amplitude is small, the system will reduce the response strength to avoid instability caused by over-adjustment. Through the above-mentioned dynamic adjustment mechanism, the grid frequency adjustment system can ensure the accuracy and timeliness of grid frequency adjustment and avoid over-response or delayed response. Furthermore, each adjustment of the wind power supply equipment and energy storage equipment will be transmitted back to the grid frequency adjustment system in real time through the feedback mechanism to ensure the consistency and stability of the equipment adjustment of all frequency adjustment nodes. For example, Figure 4A A schematic diagram showing the fluctuation of grid frequency over time is shown. Figure 4B Shows the Figure 4A Schematic diagram of wind power supply equipment power output when adjusting to grid frequency fluctuations. Figure 4C Shows the Figure 4A Schematic diagram of the power output of energy storage equipment when adjusting to grid frequency fluctuations.

[0061] According to the grid frequency regulation method based on wind-storage collaborative inertia response provided by the present invention, compared with the current method of regulating the grid frequency based on the grid frequency fluctuations that have already occurred, the present invention uses the operating status time series data of the local grid under different frequency regulation nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each local grid is located to perform high-frequency prediction and low-frequency prediction of the grid frequency at future moments, respectively, and determines the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment based on the predicted high-frequency fluctuation extreme value and low-frequency trend mean value, and finally performs distributed collaborative regulation of the frequency of the local power grid based on the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment. Therefore, by adjusting the grid frequency according to the predicted grid frequency value at a future moment, potential frequency fluctuation trends can be discovered in time, so that preventive measures can be taken in advance, thereby improving the timeliness of frequency adjustment and ensuring the stable operation of the grid; at the same time, combining the high-frequency prediction and low-frequency prediction of the grid frequency to adjust the grid frequency, it is possible to capture both the rapid changes in the grid frequency and the long-term change trends of the grid frequency, thereby realizing comprehensive monitoring and analysis of the grid frequency, thereby improving the adjustment accuracy of the grid frequency; at the same time, the present invention can ensure that when a frequency adjustment node fails, it will not affect the control process of other frequency adjustment nodes by distributedly and collaboratively adjusting the frequency of the corresponding local grid through multiple frequency adjustment nodes.

[0062] Furthermore, in order to better illustrate the above process of adjusting the grid frequency, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another grid frequency adjustment method based on the wind-storage coordinated inertia response, such as Figure 5 As shown, the method includes:

[0063] 201. In response to the frequency regulation signal of the target power grid, obtain the operating status time series data of the local power grid under different frequency regulation nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each local power grid is located, wherein the target power grid is composed of multiple local power grids, and different local power grids perform frequency regulation through different frequency regulation nodes.

[0064] 202. Based on the operating status time series data and the environmental time series data, a high-frequency prediction is performed in real time on the frequency of each local power grid in a first preset time window in the future to obtain the high-frequency fluctuation extreme value of the local power grid frequency; and based on the operating status time series data and the environmental time series data, a low-frequency prediction is performed in real time on the frequency of each local power grid in a second preset time window in the future to obtain the low-frequency trend mean value of the local power grid frequency.

[0065] For the embodiment of the present invention, in order to be able to adjust the grid frequency in a timely manner, it is first necessary to perform a high-frequency prediction on the frequency of each local grid within the first preset time window in the future. Based on this, step 202 specifically includes: determining the grid frequency change rate based on the grid frequency time series data, determining the grid load change amount based on the grid load time series data, and determining the wind speed change rate based on the wind speed time series data; respectively determining the frequency characteristic vector corresponding to the grid frequency change rate, the load characteristic vector corresponding to the grid load change amount, and the wind speed characteristic vector corresponding to the wind speed change rate, and determining a frequency prediction characteristic vector based on the frequency characteristic vector, the load characteristic vector, and the wind speed characteristic vector; inputting the frequency prediction characteristic vector into a preset high-frequency prediction model for frequency prediction to obtain the high-frequency fluctuation extreme value of each local grid within the first preset time window in the future, wherein the preset high-frequency prediction model is pre-trained based on a high-frequency sample data set with a high-frequency fluctuation extreme value label.

[0066] Specifically, first determine the time interval between adjacent data points in the grid frequency time series data, calculate their frequency difference for two adjacent data points, divide the frequency difference by the corresponding time interval, and obtain the rate of change of the grid frequency within the time interval. Finally, determine the mean value of the rate of change of each time interval to obtain the rate of change of the grid frequency. Similarly, the wind speed change rate can be determined in the above manner. At the same time, determine the grid load deviation between adjacent data points in the grid load time series data, and determine the mean value of each grid load deviation to obtain the grid load change. Furthermore, in order to ensure the real-time nature of high-frequency prediction, the grid frequency change rate can be directly determined based on the grid frequency at the current moment and the grid frequency at the previous moment corresponding to the current moment, the grid load change can be determined based on the grid load at the current moment and the grid load at the previous moment corresponding to the current moment, and the wind speed change rate can be determined based on the wind speed at the current moment and the wind speed at the previous moment corresponding to the current moment. Then determine the frequency prediction feature vector as follows :

[0067]

[0068] in, is the grid frequency change rate, is the grid load variation, is the wind speed change rate.

[0069] In another embodiment of the present invention, the method for determining the frequency prediction characteristic vector also includes: performing feature-level cross-processing on the frequency characteristic vector, load characteristic vector, and wind speed characteristic vector to obtain a feature cross-vector; performing element-level cross-processing on the frequency characteristic vector, load characteristic vector, and wind speed characteristic vector to obtain an element cross-vector; performing low-order cross-processing on the frequency characteristic vector, load characteristic vector, and wind speed characteristic vector to obtain a low-order cross-vector; and combining the feature cross-vector, element cross-vector, and low-order cross-vector to obtain the frequency prediction characteristic vector. Specifically, word embedding and other methods are used to respectively determine the frequency feature vector corresponding to the grid frequency change rate, the load feature vector corresponding to the grid load change, and the wind speed feature vector corresponding to the wind speed change rate. Then, in order to make full use of the relationship between the data, extract more implicit features, and take into account both high-order and low-order processing, so that the data can be used more fully and the prediction results obtained later are more accurate to meet the needs of actual application scenarios, it is necessary to cross-process the frequency feature vector, load feature vector, and wind speed feature vector. The specific cross-processing method is as follows: if the frequency feature vector is (a1, a2), the load feature vector is (b1, b2), and the wind speed feature vector is (c1, c2), the specific cross-processing method includes: cross-processing between different feature vectors. Feature-level crossover, that is, after making a Hadamard product on all elements between vectors, a convolution transformation is performed under a certain weight to obtain a feature crossover vector; at the same time, element-level crossover is performed on all feature vector data, that is, after making a Hadamard product on each element between vectors, a different weight value is assigned to the result after each product, and then a linear transformation is performed to obtain an element crossover vector; in addition, all feature vectors are subjected to low-order crossover processing, and the result after the crossover processing is assigned a weight coefficient w, and then a linear transformation is performed to obtain a low-order crossover vector f(w(a1,a2,b1,b2,c1,c2)); finally, the above feature crossover vectors, element crossover vectors, and low-order crossover vectors are combined together, such as horizontal splicing, to obtain a frequency prediction feature vector. It should be noted that the above examples are only illustrative and do not limit the embodiments of the present application. Therefore, by cross-processing the frequency characteristic vector, load characteristic vector, and wind speed characteristic vector, different features can be automatically or explicitly combined to generate new feature combinations. These combined features may contain complex nonlinear relationships between the original features, and can capture more detailed and rich information in the data. That is, they can make full use of the relationship between various data and extract more implicit features. At the same time, they take into account high-order and low-order processing, so that data utilization is more sufficient, and the subsequent grid frequency adjustment is more accurate to meet the stable operation of the grid.

[0070] Furthermore, after determining the frequency prediction feature vector, a preset high-frequency prediction model can be used to predict the high-frequency fluctuation extreme value of the local power grid within a first preset time window. In order to improve the prediction accuracy of the preset high-frequency prediction model, it is first necessary to train and construct the preset high-frequency prediction model. Based on this, the method includes: constructing a preset initial high-frequency prediction model and obtaining a high-frequency sample data set, wherein the high-frequency sample data set includes sample power grid frequency time series data, sample power grid load time series data, and sample wind speed time series data with high-frequency fluctuation extreme value labels of the sample power grid; dividing the high-frequency sample data set into training data and test data, using the training data to train the preset initial high-frequency prediction model, and using the test data to test the trained preset initial high-frequency prediction model, and finally determining the trained preset initial high-frequency prediction model that meets the test conditions as the preset high-frequency prediction model. The test conditions can be the prediction accuracy, prediction error, number of iterative training, etc. of the trained preset initial high-frequency prediction model. For example, if the absolute value of the difference between the predicted result (predicted high-frequency fluctuation extreme value) obtained by inputting the sample frequency prediction feature vector composed of sample power grid frequency time series data, sample power grid load time series data, and sample environmental time series data into the trained preset initial high-frequency prediction model and the actual high-frequency fluctuation extreme value is less than or equal to a preset threshold (wherein the preset threshold is set according to actual needs), then the trained preset initial high-frequency prediction model is determined to meet the test conditions. Finally, the frequency prediction feature vector for each local power grid is respectively input into the constructed preset high-frequency prediction model, and the preset high-frequency prediction model can output the high-frequency fluctuation extreme value of each local power grid within the first preset time window in the future.

[0071] At the same time, in order to be able to adjust the grid frequency in a timely manner, it is also necessary to perform low-frequency prediction on the frequency of each local grid in the second preset time window in the future in real time. Based on this, step 202 specifically includes: inputting the grid frequency time series data in the operating status time series data and the wind speed time series data in the environmental time series data into the preset low-frequency prediction model for frequency prediction, and obtaining the low-frequency trend mean of each local grid in the second preset time window in the future, wherein the second preset time window is larger than the first preset time window, and the preset low-frequency prediction model is pre-trained based on a low-frequency sample data set with a low-frequency trend mean label.

[0072] Specifically, to improve the prediction accuracy of a preset low-frequency prediction model, it is first necessary to train and construct the preset low-frequency prediction model. Based on this, the method includes: constructing a preset initial low-frequency prediction model and obtaining a low-frequency sample dataset, wherein the low-frequency sample dataset includes sample grid frequency time series data and sample wind speed time series data labeled with the low-frequency trend mean of the sample grid; dividing the low-frequency sample dataset into training data and testing data, using the training data to train the preset initial low-frequency prediction model, and using the testing data to test the trained preset initial low-frequency prediction model. Ultimately, the trained preset initial low-frequency prediction model that meets test conditions is determined as the preset low-frequency prediction model. The test conditions may include the prediction accuracy, prediction error, and number of training iterations of the trained preset initial low-frequency prediction model meeting corresponding conditions. The preset low-frequency prediction model is used to capture long-term trends in grid frequency fluctuations and is suitable for low-frequency prediction. The network structure of the preset low-frequency prediction model can employ bidirectional long-short-term memory network layers (e.g., 64 neurons per layer) and an attention mechanism to focus on key time periods in the time series data so as to output the frequency trend mean within a second preset time window in the future. Furthermore, after the preset low-frequency prediction model is constructed, the preset low-frequency prediction model The process of making low-frequency predictions is as follows:

[0073]

[0074] in, is the low-frequency trend mean, For the current moment, is the historical moment (i.e. the start time of data recording for the grid frequency time series data and wind speed time series data), is the grid frequency time series data, is the wind speed time series data.

[0075] 203. Determine the high-frequency prediction error of the high-frequency fluctuation extreme value in the prediction process and the low-frequency prediction error of the low-frequency trend mean in the prediction process, and based on the high-frequency prediction error and the low-frequency prediction error, determine the high-frequency fusion coefficient corresponding to the high-frequency fluctuation extreme value and the low-frequency fusion coefficient corresponding to the low-frequency trend mean, respectively.

[0076] 204. Based on the high-frequency fusion coefficient and the low-frequency fusion coefficient, the high-frequency fluctuation extreme value and the low-frequency trend mean value are fused to obtain a fused grid frequency value.

[0077] Specifically, first determine the variance of the high-frequency prediction error of the high-frequency fluctuation extreme value in the prediction process , and the variance of the low-frequency forecast error of the low-frequency trend mean during the forecast process , and then determine the high-frequency fusion coefficient at the current time t according to the following formula and low-frequency fusion coefficient :

[0078]

[0079]

[0080] Furthermore, the frequency value of the integrated power grid is determined according to the following formula: :

[0081]

[0082] in, is the extreme value of high-frequency fluctuation of the local power grid within the first preset time window, is the low-frequency trend mean of the local power grid within the second preset time window.

[0083] 205. Based on the integrated grid frequency value, determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each local grid.

[0084] In the embodiment of the present invention, after determining the fusion grid frequency value, it is necessary to determine the wind power output power adjustment value and the energy storage output power adjustment value based on the fusion grid frequency value. Based on this, step 205 specifically includes: determining the virtual inertia reference value of the wind power supply device i and the virtual inertia response adjustment factor at the current time t ; Based on the virtual inertia reference value , the virtual inertia response adjustment factor , the fused grid frequency value , determine the wind power supply equipment under each local power grid The wind power output power adjustment value at the current time t ,in, ; Determine the rated power of the energy storage device and the energy storage regulation factor at the current time t ; Based on the stated power rating , the energy storage adjustment factor and the fused grid frequency value , determine the energy storage output power adjustment value of each energy storage device under the local power grid at the current time t ,in, .in, is the rate of change of the integrated grid frequency, and 0.7 is the nonlinear relationship between the grid frequency fluctuation and the energy storage output power regulation value. It can be adjusted dynamically according to the fluctuation of grid frequency, or it can be set to a fixed value according to actual needs. The adjustment is related to the rate of change of the grid frequency. The system adjusts according to the real-time frequency change of the grid. This ensures that wind power supply equipment can adapt to frequency changes in a short period of time, thereby providing appropriate inertia support. This process uses continuous feedback adjustment to ensure that when the grid frequency fluctuates, the energy storage device can respond quickly and achieve precise frequency regulation. The embodiments of the present invention determine the wind power output power adjustment value and the energy storage output power adjustment value by integrating the grid frequency value, which can improve the overall prediction results and ensure that accurate grid regulation decisions can be made in the dual environment of high-frequency fluctuations and low-frequency trends.

[0085] Furthermore, the virtual inertia response adjustment factor at the current time t is determined as follows: : Determine the frequency relationship function between the grid frequency deviation of the local grid at the current time t and the virtual inertia response adjustment factor to be optimized, and determine the optimization constraint condition of the virtual inertia response adjustment factor to be optimized based on the output power constraint of the wind power supply equipment and the power relationship function between the virtual inertia response adjustment factor to be optimized and the output power of the wind power supply equipment; based on the optimization constraint condition, optimize the virtual inertia response adjustment factor to be optimized with the grid frequency deviation meeting the preset condition as the optimization index, and determine the virtual inertia response adjustment factor of the wind power supply equipment at the current time t based on the optimization result. , wherein the preset condition is that the grid frequency deviation is within a preset deviation range.

[0086] Among them, the grid frequency deviation at the current time t is and the virtual inertia response adjustment factor to be optimized for the i-th wind power supply equipment Frequency relationship function between As shown below:

[0087]

[0088] in, 、 Grid frequency deviation and the virtual inertia response adjustment factor to be optimized The corresponding weight coefficients are used to control the grid frequency deviation respectively and the virtual inertia response adjustment factor to be optimized The importance of The virtual inertia response adjustment factor to be optimized At the same time, the output power constraints of wind power supply equipment are as follows:

[0089]

[0090] in, Power supply equipment for wind power The output power, is the minimum output power of wind power supply equipment, is the maximum output power of the wind power supply equipment. Further, the virtual inertia response adjustment factor to be optimized is The optimization constraints are as follows:

[0091]

[0092] in, is the power coefficient, It is the ratio of the blade tip speed of the wind power supply equipment to the wind speed. is the air density, is the cross-sectional area of ​​the wind power supply equipment, is the wind speed. Finally, based on the above optimization constraints, the frequency relationship function The virtual inertia response adjustment factor to be optimized in Continuously iterate the optimization until the grid frequency deviation is within the preset deviation range (the preset deviation range is set according to actual needs), or the iterative optimization is stopped when the grid frequency deviation reaches the minimum value. The optimized virtual inertia response adjustment factor at this time is used as the virtual inertia response adjustment factor that finally participates in the calculation of the wind power output power adjustment value.

[0093] 206. Based on the wind power output power adjustment value, the corresponding wind power supply equipment is coordinated and adjusted in real time to transmit power to the corresponding local power grid in a distributed manner. Based on the energy storage output power adjustment value, the corresponding energy storage equipment is coordinated and controlled in real time to charge and discharge the corresponding local power grid in a distributed manner.

[0094] For the embodiment of the present invention, after determining the wind power output power adjustment value and the energy storage output power adjustment value, it is necessary to implement frequency adjustment of the local power grid based on the above adjustment values. Based on this, step 206 specifically includes: taking any frequency adjustment node in each of the frequency adjustment nodes as a target frequency adjustment node, determining the wind power output power adjustment value and the energy storage output power adjustment value under the target frequency adjustment node as the reference wind power output power adjustment value and the reference energy storage output power adjustment value, respectively, and sending the reference wind power output power adjustment value and the reference energy storage output power adjustment value to other frequency adjustment nodes, so that the other frequency adjustment nodes perform distributed collaborative frequency adjustment on the corresponding local power grid based on the corresponding wind power output power adjustment value, the energy storage output power adjustment value, the reference wind power output power adjustment value, and the reference energy storage output power adjustment value, wherein the other frequency adjustment nodes refer to the nodes in each of the frequency adjustment nodes excluding the target frequency adjustment node.

[0095] Specifically, after calculating the wind power output power adjustment value and the energy storage output power adjustment value under each frequency adjustment node, each frequency adjustment node can control the wind power supply equipment under this node to output the corresponding power to the local power grid based on the wind power output power adjustment value corresponding to this node. At the same time, each frequency adjustment node can control the energy storage equipment under this node to output or absorb the corresponding power to the local power grid based on the energy storage output power adjustment value corresponding to this node, thereby realizing the distributed adjustment of the local power grid corresponding to this node. At the same time, when each frequency adjustment node adjusts the power grid frequency for its own node, it can also send the wind power output power adjustment value and energy storage output power adjustment value of its own node to other frequency adjustment nodes. Therefore, each frequency adjustment node can perform coordinated frequency adjustment of the corresponding local power grid based on the adjustment information such as the wind power output power adjustment value and energy storage output power adjustment value of this node and other nodes.

[0096] According to another grid frequency regulation method based on wind-storage collaborative inertia response provided by the present invention, compared with the current method of regulating the grid frequency based on the grid frequency fluctuations that have already occurred, the present invention uses the operating status time series data of the local grid under different frequency regulation nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each local grid is located to perform high-frequency prediction and low-frequency prediction of the grid frequency at future moments, respectively, and determines the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment based on the predicted high-frequency fluctuation extreme value and low-frequency trend mean value, and finally performs distributed collaborative regulation of the frequency of the local power grid based on the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment. Therefore, by adjusting the grid frequency according to the predicted grid frequency value at a future moment, potential frequency fluctuation trends can be discovered in time, so that preventive measures can be taken in advance, thereby improving the timeliness of frequency adjustment and ensuring the stable operation of the grid; at the same time, combining the high-frequency prediction and low-frequency prediction of the grid frequency to adjust the grid frequency, it is possible to capture both the rapid changes in the grid frequency and the long-term change trends of the grid frequency, thereby realizing comprehensive monitoring and analysis of the grid frequency, thereby improving the adjustment accuracy of the grid frequency; at the same time, the present invention can ensure that when a frequency adjustment node fails, it will not affect the control process of other frequency adjustment nodes by distributedly and collaboratively adjusting the frequency of the corresponding local grid through multiple frequency adjustment nodes.

[0097] Further, as Figure 1 The embodiment of the present invention provides a power grid frequency regulation device based on wind-storage coordinated inertia response, such as Figure 6 As shown, the device includes: an acquisition unit 31, a frequency prediction unit 32, and a frequency adjustment unit 33.

[0098] The acquisition unit 31 can be used to respond to the frequency adjustment signal of the target power grid to obtain the operating status time series data of the local power grid under different frequency adjustment nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each local power grid is located, wherein the target power grid is composed of multiple local power grids, and different local power grids perform frequency adjustment through different frequency adjustment nodes.

[0099] The frequency prediction unit 32 can be used to perform high-frequency prediction on the frequency of each local power grid in a first preset time window in the future based on the operating status time series data and the environmental time series data, so as to obtain the high-frequency fluctuation extreme value of the local power grid frequency; and to perform low-frequency prediction on the frequency of each local power grid in a second preset time window in the future based on the operating status time series data and the environmental time series data, so as to obtain the low-frequency trend mean value of the local power grid frequency.

[0100] The frequency adjustment unit 33 can be used to determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids based on the high-frequency fluctuation extreme value and the low-frequency trend mean value, and to perform real-time distributed collaborative adjustment of the corresponding wind power supply equipment to perform power transmission operations to the corresponding local power grid based on the wind power output power adjustment value, and to perform real-time distributed collaborative control of the corresponding energy storage equipment to perform charging and discharging operations to the corresponding local power grid based on the energy storage output power adjustment value.

[0101] In a specific application scenario, the operating status time series data includes the grid frequency time series data and grid load time series data of the local grid, and the environmental time series data includes wind speed time series data; Figure 7 As shown, in order to perform high frequency prediction on the local power grid, the frequency prediction unit 32 includes a first determination module 321 and a prediction module 322 .

[0102] The first determination module 321 can be used to determine the grid frequency change rate based on the grid frequency time series data, determine the grid load change amount based on the grid load time series data, and determine the wind speed change rate based on the wind speed time series data.

[0103] The first determination module 321 can also be used to respectively determine the frequency characteristic vector corresponding to the grid frequency change rate, the load characteristic vector corresponding to the grid load change, and the wind speed characteristic vector corresponding to the wind speed change rate, and determine the frequency prediction characteristic vector based on the frequency characteristic vector, the load characteristic vector, and the wind speed characteristic vector.

[0104] The prediction module 322 can be used to input the frequency prediction feature vector into a preset high-frequency prediction model to perform frequency prediction, and obtain the high-frequency fluctuation extreme value of each local power grid within a first preset time window in the future, wherein the preset high-frequency prediction model is pre-trained based on a high-frequency sample data set with high-frequency fluctuation extreme value labels.

[0105] In a specific application scenario, in order to perform low-frequency prediction on the local power grid, the prediction module 322 can also be used to input the power grid frequency time series data in the operating status time series data and the wind speed time series data in the environmental time series data into a preset low-frequency prediction model for frequency prediction, and obtain the low-frequency trend mean of each local power grid in the future second preset time window, wherein the second preset time window is larger than the first preset time window, and the preset low-frequency prediction model is pre-trained based on a low-frequency sample data set with a low-frequency trend mean label.

[0106] In a specific application scenario, in order to determine the wind power output power adjustment value and the energy storage output power adjustment value, the frequency adjustment unit 33 includes a second determination module 331 and a fusion module 332 .

[0107] The second determination module 331 can be used to determine the high-frequency prediction error of the high-frequency fluctuation extreme value during the prediction process and the low-frequency prediction error of the low-frequency trend mean during the prediction process, and based on the high-frequency prediction error and the low-frequency prediction error, respectively determine the high-frequency fusion coefficient corresponding to the high-frequency fluctuation extreme value and the low-frequency fusion coefficient corresponding to the low-frequency trend mean.

[0108] The fusion module 332 can be used to fuse the high-frequency fluctuation extreme value and the low-frequency trend mean value based on the high-frequency fusion coefficient and the low-frequency fusion coefficient to obtain a fused grid frequency value. .

[0109] The second determining module 331 can also be used to determine the frequency value of the integrated power grid based on the , determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids.

[0110] In a specific application scenario, in order to determine the wind power output power adjustment value and the energy storage output power adjustment value, the second determination module 331 can be used to determine the virtual inertia reference value of the wind power supply device i. and the virtual inertia response adjustment factor at the current time t ; Based on the virtual inertia reference value , the virtual inertia response adjustment factor , the fused grid frequency value , determine the wind power supply equipment under each local power grid The wind power output power adjustment value at the current time t ,in, ; Determine the rated power of the energy storage device and the energy storage adjustment factor at the current time t ; Based on the stated power rating , the energy storage adjustment factor and the fused grid frequency value , determine the energy storage output power adjustment value of each energy storage device under the local power grid at the current time t ,in, .

[0111] In a specific application scenario, in order to determine the virtual inertia response adjustment factor at the current time t, the second determination module 331 can be specifically used to determine the frequency relationship function between the grid frequency deviation of the local power grid at the current time t and the virtual inertia response adjustment factor to be optimized, and determine the optimization constraint condition of the virtual inertia response adjustment factor to be optimized based on the output power constraint of the wind power supply equipment and the power relationship function between the virtual inertia response adjustment factor to be optimized and the output power of the wind power supply equipment; based on the optimization constraint condition, the virtual inertia response adjustment factor to be optimized is optimized with the grid frequency deviation meeting the preset condition as the optimization index, and the virtual inertia response adjustment factor of the wind power supply equipment at the current time t is determined based on the optimization result. , wherein the preset condition is that the grid frequency deviation is within a preset deviation range.

[0112] In a specific application scenario, in order to perform distributed collaborative frequency regulation on the local power grid, the frequency regulation unit 33 can be specifically used to take any frequency regulation node in each of the frequency regulation nodes as a target frequency regulation node, determine the wind power output power regulation value and the energy storage output power regulation value under the target frequency regulation node as the reference wind power output power regulation value and the reference energy storage output power regulation value, respectively, and send the reference wind power output power regulation value and the reference energy storage output power regulation value to other frequency regulation nodes, so that the other frequency regulation nodes perform distributed collaborative frequency regulation on the corresponding local power grid based on the corresponding wind power output power regulation value, the energy storage output power regulation value, the reference wind power output power regulation value, and the reference energy storage output power regulation value, wherein the other frequency regulation node refers to the node excluding the target frequency regulation node in each of the frequency regulation nodes.

[0113] It should be noted that for other corresponding descriptions of the functional modules involved in the power grid frequency regulation device based on wind-storage coordinated inertia response provided by the embodiment of the present invention, please refer to Figure 1 The corresponding description of the method shown will not be repeated here.

[0114] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the following steps when executed by a processor: in response to a frequency regulation signal of a target power grid, obtaining operation status time series data of a local power grid under different frequency regulation nodes and environmental time series data of the environment in which the wind power supply equipment corresponding to each of the local power grids is located, wherein the target power grid is composed of a plurality of local power grids, and different local power grids perform frequency regulation through different frequency regulation nodes; based on the operation status time series data and the environmental time series data, performing a high-frequency prediction on the frequency of each of the local power grids within a first preset time window in the future in real time to obtain the frequency of the local power grid. High-frequency fluctuation extreme values, and based on the operating status time series data and the environmental time series data, real-time low-frequency prediction of the frequency of each of the local power grids in the second preset time window in the future to obtain the low-frequency trend mean of the local power grid frequency; based on the high-frequency fluctuation extreme values ​​and the low-frequency trend mean, determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids, based on the wind power output power adjustment value, real-time distributed collaborative adjustment of the corresponding wind power supply equipment to the corresponding local power grid for power transmission operations, and based on the energy storage output power adjustment value, real-time distributed collaborative control of the corresponding energy storage equipment to perform charging and discharging operations on the corresponding local power grid.

[0115] Based on the above Figure 1 The method shown and Figure 6 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 8As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, and the processor 41 implements the following steps when executing the program: in response to the frequency regulation signal of the target power grid, obtaining the operating state time series data of the local power grid under different frequency regulation nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each of the local power grids is located, wherein the target power grid is composed of a plurality of local power grids, and different local power grids perform frequency regulation through different frequency regulation nodes; based on the operating state time series data and the environmental time series data, real-time frequency regulation of each of the local power grids within a first preset time window in the future The method comprises the steps of: performing a high-frequency prediction on the frequency of each local power grid to obtain a high-frequency fluctuation extreme value of the local power grid frequency; and performing a low-frequency prediction on the frequency of each local power grid in a second preset time window in the future in real time based on the operating status time series data and the environmental time series data to obtain a low-frequency trend average value of the local power grid frequency; determining a wind power output power adjustment value of the wind power supply equipment and an energy storage output power adjustment value of the energy storage equipment under each local power grid based on the high-frequency fluctuation extreme value and the low-frequency trend average value, and performing a distributed and coordinated adjustment on the corresponding wind power supply equipment to perform power transmission operations to the corresponding local power grid based on the wind power output power adjustment value, and performing a distributed and coordinated control on the corresponding energy storage equipment to perform charging and discharging operations to the corresponding local power grid based on the energy storage output power adjustment value.

[0116] Through the technical solution of the present invention, the present invention performs high-frequency prediction and low-frequency prediction on the grid frequency at future moments respectively through the operating status time series data of the local power grid under different frequency regulation nodes and the environmental time series data of the environment in which the wind power supply equipment corresponding to each local power grid is located, and determines the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment according to the predicted high-frequency fluctuation extreme value and low-frequency trend mean value, and finally performs distributed collaborative regulation of the frequency of the local power grid based on the wind power output power regulation value of the wind power supply equipment and the energy storage output power regulation value of the energy storage equipment. Therefore, by adjusting the grid frequency according to the predicted grid frequency value at a future moment, potential frequency fluctuation trends can be discovered in time, so that preventive measures can be taken in advance, thereby improving the timeliness of frequency adjustment and ensuring the stable operation of the grid; at the same time, combining the high-frequency prediction and low-frequency prediction of the grid frequency to adjust the grid frequency, it is possible to capture both the rapid changes in the grid frequency and the long-term change trends of the grid frequency, thereby realizing comprehensive monitoring and analysis of the grid frequency, thereby improving the adjustment accuracy of the grid frequency; at the same time, the present invention can ensure that when a frequency adjustment node fails, it will not affect the control process of other frequency adjustment nodes by distributedly and collaboratively adjusting the frequency of the corresponding local grid through multiple frequency adjustment nodes.

[0117] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, centralized on a single computing device, or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. In some cases, the steps shown or described can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0118] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A grid frequency regulation method based on wind-storage collaborative inertia response, characterized in that: include: In response to a frequency adjustment signal of a target power grid, obtaining time series data on the operating status of local power grids at different frequency adjustment nodes and time series data on the environment in which the wind power supply equipment corresponding to each of the local power grids is located, wherein the target power grid is composed of multiple local power grids, and different local power grids perform frequency adjustment through different frequency adjustment nodes; Based on the operating status time series data and the environmental time series data, a high-frequency prediction is performed in real time on the frequency of each of the local power grids within a first preset time window in the future to obtain a high-frequency fluctuation extreme value of the local power grid frequency; and based on the operating status time series data and the environmental time series data, a low-frequency prediction is performed in real time on the frequency of each of the local power grids within a second preset time window in the future to obtain a low-frequency trend mean value of the local power grid frequency; Based on the high-frequency fluctuation extreme value and the low-frequency trend mean, determining the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids, and based on the wind power output power adjustment value, real-time distributed collaborative adjustment of the corresponding wind power supply equipment to perform power transmission operations to the corresponding local power grid, and based on the energy storage output power adjustment value, real-time distributed collaborative control of the corresponding energy storage equipment to perform charging and discharging operations to the corresponding local power grid; Wherein, determining the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids based on the high-frequency fluctuation extreme value and the low-frequency trend mean value includes: Determine the high-frequency prediction error of the high-frequency fluctuation extreme value during the prediction process and the low-frequency prediction error of the low-frequency trend mean during the prediction process, and based on the high-frequency prediction error and the low-frequency prediction error, respectively determine the high-frequency fusion coefficient corresponding to the high-frequency fluctuation extreme value and the low-frequency fusion coefficient corresponding to the low-frequency trend mean; based on the high-frequency fusion coefficient and the low-frequency fusion coefficient, fuse the high-frequency fluctuation extreme value and the low-frequency trend mean to obtain a fused grid frequency value ; Based on the fusion grid frequency value , determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids.

2. The method according to claim 1, characterized in that The operating status time series data includes grid frequency time series data and grid load time series data of the local power grid, and the environmental time series data includes wind speed time series data; The method of performing high-frequency prediction on the frequency of each local power grid within a first preset time window in the future based on the operating state time series data and the environmental time series data in real time to obtain a high-frequency fluctuation extreme value of the local power grid frequency includes: Determine the grid frequency change rate based on the grid frequency time series data, determine the grid load change amount based on the grid load time series data, and determine the wind speed change rate based on the wind speed time series data; Respectively determining a frequency characteristic vector corresponding to the grid frequency change rate, a load characteristic vector corresponding to the grid load change amount, and a wind speed characteristic vector corresponding to the wind speed change rate, and determining a frequency prediction characteristic vector based on the frequency characteristic vector, the load characteristic vector, and the wind speed characteristic vector; The frequency prediction feature vector is input into a preset high-frequency prediction model for frequency prediction to obtain the high-frequency fluctuation extreme value of each local power grid within a first preset time window in the future, wherein the preset high-frequency prediction model is pre-trained based on a high-frequency sample data set with high-frequency fluctuation extreme value labels.

3. The method according to claim 1, characterized in that The step of performing a low-frequency prediction on the frequency of each local power grid within a second preset time window in the future based on the operating status time series data and the environmental time series data to obtain a low-frequency trend mean of the local power grid frequency includes: The grid frequency time series data in the operating status time series data and the wind speed time series data in the environmental time series data are input into a preset low-frequency prediction model for frequency prediction to obtain the low-frequency trend mean of each local power grid in a second preset time window in the future, wherein the second preset time window is larger than the first preset time window, and the preset low-frequency prediction model is pre-trained based on a low-frequency sample data set with a low-frequency trend mean label.

4. The method according to claim 1, wherein Based on the fusion grid frequency value , determining the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids, including: Determine the virtual inertia reference value of wind power supply equipment i and the virtual inertia response adjustment factor at the current time t ; Based on the virtual inertia reference value , the virtual inertia response adjustment factor , the fused grid frequency value , determine the wind power supply equipment under each local power grid The wind power output power adjustment value at the current time t ,in, ; Determine the rated power of the energy storage device and the energy storage adjustment factor at the current time t ; Based on the rated power , the energy storage adjustment factor and the fused grid frequency value , determine the energy storage output power adjustment value of each energy storage device under the local power grid at the current time t ,in, .

5. The method according to claim 4, characterized in that Determine the virtual inertia response adjustment factor at the current time t ,include: determining a frequency relationship function between a grid frequency deviation of the local power grid at the current time t and a virtual inertia response adjustment factor to be optimized, and determining an optimization constraint condition for the virtual inertia response adjustment factor to be optimized based on an output power constraint of the wind power supply equipment and a power relationship function between the virtual inertia response adjustment factor to be optimized and the output power of the wind power supply equipment; Based on the optimization constraints, the grid frequency deviation satisfies the preset conditions as the optimization index, the virtual inertia response adjustment factor to be optimized is optimized, and based on the optimization result, the virtual inertia response adjustment factor of the wind power supply equipment at the current time t is determined. , wherein the preset condition is that the grid frequency deviation is within a preset deviation range.

6. The method according to claim 1, wherein The real-time distributed coordinated adjustment of the corresponding wind power supply equipment to perform power transmission operations to the corresponding local power grid based on the wind power output power adjustment value, and the real-time distributed coordinated control of the corresponding energy storage equipment to perform charging and discharging operations to the corresponding local power grid based on the energy storage output power adjustment value, include: Any frequency regulation node in each of the frequency regulation nodes is respectively used as a target frequency regulation node, the wind power output power regulation value and the energy storage output power regulation value under the target frequency regulation node are respectively determined as the reference wind power output power regulation value and the reference energy storage output power regulation value, and the reference wind power output power regulation value and the reference energy storage output power regulation value are respectively sent to other frequency regulation nodes, so that the other frequency regulation nodes perform distributed collaborative frequency regulation on the corresponding local power grid based on the corresponding wind power output power regulation value, the energy storage output power regulation value, the reference wind power output power regulation value, and the reference energy storage output power regulation value, wherein the other frequency regulation nodes refer to the nodes in each of the frequency regulation nodes excluding the target frequency regulation node.

7. A grid frequency regulation device based on wind-storage coordinated inertia response, characterized in that: include: an acquisition unit, configured to acquire, in response to a frequency adjustment signal of a target power grid, time series data of operating states of local power grids under different frequency adjustment nodes and time series data of the environment in which the wind power supply equipment corresponding to each of the local power grids is located, wherein the target power grid is composed of a plurality of local power grids, and frequency adjustment is performed on different local power grids through different frequency adjustment nodes; a frequency prediction unit, configured to perform a high-frequency prediction on the frequency of each of the local power grids in a first preset time window in the future based on the operating status time series data and the environmental time series data, in real time, to obtain a high-frequency fluctuation extreme value of the local power grid frequency; and to perform a low-frequency prediction on the frequency of each of the local power grids in a second preset time window in the future based on the operating status time series data and the environmental time series data, in real time, to obtain a low-frequency trend mean value of the local power grid frequency; A frequency adjustment unit is configured to determine, based on the high-frequency fluctuation extreme value and the low-frequency trend mean value, a wind power output power adjustment value of the wind power supply equipment and an energy storage output power adjustment value of the energy storage equipment under each of the local power grids, and to coordinately adjust the corresponding wind power supply equipment to perform power transmission operations to the corresponding local power grid in real time and in a distributed manner based on the wind power output power adjustment value, and to coordinately control the corresponding energy storage equipment to perform charging and discharging operations to the corresponding local power grid in real time and in a distributed manner based on the energy storage output power adjustment value; wherein, based on the high-frequency fluctuation extreme value and the low-frequency trend mean value, determining the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids comprises: determining a high-frequency prediction error of the high-frequency fluctuation extreme value during the prediction process and a low-frequency prediction error of the low-frequency trend mean during the prediction process, and determining, based on the high-frequency prediction error and the low-frequency prediction error, a high-frequency fusion coefficient corresponding to the high-frequency fluctuation extreme value and a low-frequency fusion coefficient corresponding to the low-frequency trend mean; and fusing the high-frequency fluctuation extreme value and the low-frequency trend mean value based on the high-frequency fusion coefficient and the low-frequency fusion coefficient to obtain a fused power grid frequency value. ; Based on the fusion grid frequency value , determine the wind power output power adjustment value of the wind power supply equipment and the energy storage output power adjustment value of the energy storage equipment under each of the local power grids.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images