Energy storage coordination control method and system based on artificial intelligence

Abstract

The invention relates to the technical field of data processing, in particular to an energy storage coordination control method and system based on artificial intelligence, and the method comprises the steps: calculating the distribution deviation degree of power generation in a power generation sequence, and calculating the gradient change degree of the power generation according to the distribution deviation degree; calculating the optimal cut-off distance of the generating capacity; according to the optimal truncation distance, clustering the generating capacity by using a density peak clustering algorithm to obtain a plurality of clusters, calculating a mean value of Euclidean distances between all data points in the clusters and a cluster center, and marking the data points greater than the mean value in the clusters as abnormal points; eliminating abnormal points in the generating capacity sequence, filling data at the elimination position, and obtaining a generating capacity predicted value at the next moment by using an exponential smoothing method; similarly to the method for obtaining the power generation prediction value, obtaining the power consumption prediction value; and adjusting the power grid frequency according to the difference between the power generation predicted value and the power consumption predicted value. The method has the effect of improving the accuracy of the power grid frequency regulation result.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular to an energy storage coordinated control method and system based on artificial intelligence. Background Art

[0002] With the popularization of renewable energy power generation, especially the rapid development of wind power and photovoltaic power generation, the problems of volatility and instability in energy supply in the power system have become more prominent. As a key tool for regulating grid load fluctuations and balancing grid supply and demand, the energy storage system can effectively improve the stability, reliability and flexibility of the power grid. Frequency regulation is an important function in the power energy storage system, which reflects the balance between power generation and load in the power grid. When the power generation and load do not match, the grid frequency will fluctuate, so regulation is needed to maintain the stable operation of the power grid.

[0003] When adjusting grid data, due to the need for the rapid response of the energy storage system, it is necessary to predict the power generation data and load data in order to achieve the rapid response of the energy storage system according to the prediction results. For example, the Chinese patent application document with the publication number CN115549158A discloses an electrochemical energy storage power station power generation prediction method and system containing time factors, including: determining the power generation prediction type of the electrochemical energy storage power station according to the instructions issued by the grid dispatching center; when the power generation prediction type is daily power generation prediction, determining the actual power of each moment of the energy storage power station on the next day and the time factor corresponding to the actual power according to the power station information, and when the power generation prediction type is mid-day power generation prediction, determining the actual power of the energy storage power station at the next moment and the time factor corresponding to the actual power according to the power station information and the real-time state information of the power station; outputting the determined actual power and the time factor corresponding to the actual power to the grid dispatching center, and using the grid dispatching center to put the energy storage power station into use. This patent application document generates a power generation prediction curve based on the real-time state of the electrochemical energy storage power station, providing a visual power generation curve for dispatching personnel to characterize its capabilities.

[0004] During the prediction process, the data collected may be abnormal due to reasons such as system aging failure and sudden load fluctuations, and the abnormal data will affect the accuracy of the prediction results, further making the grid frequency regulation results inaccurate. Summary of the Invention

[0005] To solve the technical problem of inaccurate grid frequency regulation results caused by abnormal data, this application provides an energy storage coordinated control method and system based on artificial intelligence.

[0006] In the first aspect, this application provides an energy storage coordinated control method and system based on artificial intelligence, adopting the following technical solutions: An energy storage coordinated control method based on artificial intelligence, comprising the steps of: constructing a power generation sequence, calculating the distribution deviation degree of the power generation in the power generation sequence, and calculating the gradient change degree of the power generation according to the distribution deviation degree; calculating the optimal truncation distance of the power generation, and the expression is: , where, represents the optimal truncation distance of the power generation; is a preset truncation distance, represents the gradient change degree of the power generation in the power generation sequence; represents the ceiling function; represents taking as the base exponential function, represents the maximum value function, represents a hyperparameter; according to the optimal truncation distance of the power generation, using the density peak clustering algorithm to cluster the power generation to obtain multiple clustering clusters, calculating the mean of the Euclidean distances between all data points in the clustering cluster and the cluster center, and recording the data points greater than the mean in the clustering as outliers; after removing the outliers in the power generation sequence, filling the data at the removed positions, and using the exponential smoothing method to obtain the predicted value of the power generation at the next moment; in the same way as the method for obtaining the predicted value of the power generation, obtaining the predicted value of the power consumption; adjusting the grid frequency according to the difference between the predicted value of the power generation and the predicted value of the power consumption.

[0007] The beneficial effects are: by combining the gradient change degree in the power generation sequence and the preset truncation distance to dynamically adjust the optimal truncation distance, and avoiding the problem of too small or too large truncation distance by taking the maximum value function. Too small a truncation distance may cause the area with high density to be wrongly segmented, while too large a truncation distance may wrongly classify the area with low density into the area with high density, affecting the accuracy of the clustering result, so as to find the optimal truncation distance; According to the optimal truncation distance, clustering is carried out through the clustering algorithm to obtain multiple clustering clusters, and the data points in the power generation sequence are grouped according to their similarity, so that the data points within the same clustering cluster have high similarity, while the data points between different clustering clusters have large differences. By calculating the mean of the Euclidean distances between all data points in the clustering cluster and the cluster center, and identifying the data points greater than this mean as outliers, the outliers in the power generation sequence can be effectively identified and removed. After removing the outliers, data filling is carried out to achieve the purpose of denoising the data sequence. Then, power generation prediction and power consumption prediction are carried out according to the denoised data sequence, and the power generation is adjusted according to the prediction results to ensure that the grid frequency is maintained within the standard range, so as to ensure the stability and reliable power supply of the power system and improve the accuracy of the grid frequency regulation result.

[0008] Optionally, the expression of the distribution deviation degree of the power generation is: , where, Indicates the degree of deviation of the power generation amount distribution, Indicates the arctangent function, Indicates the median of the power generation amount, Indicates the mean of the power generation amount, Indicates the minimum value of the power generation amount, Indicates the maximum value of the power generation amount.

[0009] The beneficial effects are as follows: A method for quantifying the degree of deviation of the power generation amount distribution is provided, which considers the median, mean, minimum value, and maximum value to comprehensively calculate the degree of deviation of the data point distribution, so as to better capture the skewness of the data, that is, whether the data distribution is symmetric. It is applicable to scenarios that require analyzing the skewness of the power generation amount, especially when the data distribution is uneven or there are extreme values, and this skewness analysis is particularly important.

[0010] Optionally, the expression for the degree of deviation of the power generation amount distribution is: , where, Indicates the degree of deviation of the power generation amount distribution, Indicates the normalization function, Indicates the median of the power generation amount, Indicates the minimum value of the power generation amount, Indicates the maximum value of the power generation amount.

[0011] The beneficial effects are as follows: Another method for quantifying the degree of deviation of the power generation amount distribution is provided, which only considers the median, minimum value, and maximum value, measures the symmetry of the data distribution through the ratio , and then performs normalization processing and subtracts 0.5 to adjust the output range. The calculation is simple and the amount of calculation is small, and it is applicable to scenarios that require simply and quickly evaluating the symmetry of the data distribution.

[0012] Optionally, the expression for the degree of gradient change is: , where in the formula, Indicates the degree of gradient change of the power generation amount; Indicates the degree of deviation of the power generation amount distribution; Indicates the maximum value of the power generation data in the power generation amount sequence; Indicates the minimum value of the power generation data in the power generation amount sequence.

[0013] The beneficial effects are: The larger it is, the higher the degree of deviation of the power generation amount distribution, and vice versa, the lower the degree of deviation. Indicates the range of the power generation amount, that is, the difference between the maximum value and the minimum value. This range is a measure of the data change amplitude and reflects the total change amount of the data from the minimum value to the maximum value. This calculation method of the degree of gradient change can capture the overall change amplitude of the power generation data, especially when there are extreme values in the data, and can well reflect the fluctuation range of the data.

[0014] Optionally, the expression for the degree of gradient change is: , where represents the degree of gradient change of power generation; represents the degree of deviation of the power generation distribution; represents the standard deviation of power generation.

[0015] The beneficial effect is that the standard deviation expresses the degree of dispersion of the power generation data, that is, the volatility of the data points relative to the mean. This calculation method of the degree of gradient change pays more attention to the degree of dispersion of the data, that is, the volatility of the data points relative to the mean, and can capture the local changes and anomalies of the data.

[0016] Optionally, adjusting the grid frequency according to the difference between the power generation prediction value and the power consumption prediction value includes the steps of: obtaining the power generation change rate at the next moment: , where represents the power generation change rate at the next moment, represents the power generation at the next moment; represents the power generation at the current moment; similarly, obtain the power consumption change rate at the next moment; in response to the power generation change rate being less than the load change rate, increase the power generation; in response to the power generation change rate being greater than the load change rate, reduce the power generation.

[0017] Optionally, the method for filling the data at the removal position is the difference method, forward filling, backward filling or mean filling.

[0018] In a second aspect, the present application provides an energy storage coordination control system based on artificial intelligence, adopting the following technical solutions: An energy storage coordination control system based on artificial intelligence includes: a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned energy storage coordination control method based on artificial intelligence is implemented.

[0019] The beneficial effect is that the above-mentioned energy storage coordination control method based on artificial intelligence is generated into a computer program and stored in the memory to be loaded and executed by the processor. Thus, a system is made according to the memory and the processor, which is convenient to use.

[0020] The present application has the following technical effects: 1. Find the optimal truncation distance. Cluster multiple clusters through the clustering algorithm according to the optimal truncation distance. By calculating the mean of the Euclidean distances between all data points in the cluster and the cluster center, and identifying the data points greater than this mean as outliers, the outliers in the power generation sequence can be effectively identified and removed. After removing the outliers, data filling is performed to achieve the purpose of denoising the data sequence. Then, power generation prediction and power consumption prediction are performed based on the denoised data sequence. The power generation is adjusted according to the prediction results to ensure that the grid frequency is maintained within the standard range, so as to ensure the stability and reliable power supply of the power system and improve the accuracy of the grid frequency regulation result.

[0021] 2. Dynamically adjust the optimal truncation distance by combining the degree of gradient change in the power generation sequence and the preset truncation distance. The problem of too small or too large truncation distance is avoided by using the maximum value function. A too small truncation distance may cause regions with high density to be wrongly segmented, while a too large truncation distance may wrongly classify regions with low density into regions with high density, affecting the accuracy of the clustering result, so as to find the optimal truncation distance. Brief Description of the Drawings

[0022] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0023] Figure 1 It is a flowchart of a method for energy storage coordinated control based on artificial intelligence according to an embodiment of the present application. Detailed Embodiments

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts fall within the protection scope of the present application.

[0025] It should be understood that when terms such as "first" and "second" are used in the claims, specifications and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "including" and "comprising" used in the specifications and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0026] The embodiment of the present application discloses an energy storage coordinated control method based on artificial intelligence for regulating the grid frequency. The regulation of the grid frequency plays a very crucial role in the energy storage system. In the power system, the grid frequency usually remains within a fixed range (such as 50Hz or 60Hz), and the grid frequency directly reflects the balance between power generation and load. If the frequency exceeds the normal range, it may cause damage to grid equipment and even trigger large-scale power outages. Therefore, frequency regulation is an important link in grid operation.

[0027] The frequency of the grid reflects the balance between power generation and load in the system. Frequency stability requires that the power generation power and the load power be equal. If the two are not equal or not approximately equal, the frequency will shift, resulting in instability of the grid system and thus triggering large-scale power outage accidents.

[0028] Refer to Figure 1 , the energy storage coordinated control method based on artificial intelligence includes steps S1 - S5, specifically as follows: S1: Construct a power generation sequence, calculate the distribution deviation degree of the power generation in the power generation sequence, and calculate the gradient change degree of the power generation according to the distribution deviation degree.

[0029] Collect power generation data and load data. The preset acquisition frequency of the power generation data and the load data is 0.2Hz.

[0030] The power generation data refers to the power generation of the generator sets in the grid within a unit time, which is collected through the SCADA (Supervisory Control And Data Acquisition) system. The load data refers to the power consumption of the electrical equipment and users within a unit time, which is collected through the AMI system (Advanced Metering Infrastructure). Both the SCADA system and the AMI system are existing technologies and will not be elaborated here.

[0031] In one embodiment, the expression of the distribution deviation degree of the power generation is: , where represents the distribution deviation degree of the power generation, represents the arctangent function, represents the median of the power generation, represents the mean value of the power generation, represents the minimum value of the power generation, represents the maximum value of the power generation.

[0032] Among them, Represents the deviation of power generation with respect to the median, which measures the symmetry of the data distribution. If this ratio is greater than 1, it indicates that the data distribution is skewed to the right; if less than 1, it indicates that the data distribution is skewed to the left; if equal to 1, it indicates that the data distribution is symmetric.

[0033] arctan represents the arctangent function, which maps to the interval of and then maps the result to the interval by multiplying with to quantify the degree of distribution deviation.

[0034] This embodiment provides a method for quantifying the degree of deviation of power generation distribution, which comprehensively calculates the degree of deviation of data points considering the median, mean, minimum, and maximum values to better capture the skewness of the data, that is, whether the data distribution is symmetric. It is applicable to scenarios where the skewness of power generation needs to be analyzed, especially when the data distribution is uneven or there are extreme values, and this skewness analysis is particularly important.

[0035] In one embodiment, the expression for the degree of deviation of power generation distribution is: , where represents the degree of deviation of power generation distribution, represents the normalization function, represents the median of power generation, represents the minimum value of power generation, represents the maximum value of power generation.

[0036] This embodiment provides another method for quantifying the degree of deviation of power generation distribution, which only considers the median, minimum, and maximum values, measures the symmetry of the data distribution through the ratio , and then performs normalization processing and subtracts 0.5 to adjust the output range. The calculation is simple and the computational amount is small, and it is applicable to scenarios where the symmetry of the data distribution needs to be evaluated simply and quickly.

[0037] In one embodiment, the expression for the degree of gradient change is: , where in the formula, represents the degree of gradient change of power generation; represents the degree of deviation of power generation distribution; represents the maximum value of power generation data in the power generation sequence; represents the minimum value of power generation data in the power generation sequence.

[0038] The larger ​It represents the range of power generation, that is, the difference between the maximum value and the minimum value. This range is a measure of the data variation amplitude, reflecting the total variation of the data from the minimum value to the maximum value. This embodiment can capture the overall variation amplitude of the power generation data. Especially when there are extreme values in the data, it can well reflect the fluctuation range of the data.

[0039] In one embodiment, the expression of the gradient change degree is: , where, represents the gradient change degree of the power generation; represents the distribution deviation degree of the power generation; represents the standard deviation of the power generation. The standard deviation expresses the dispersion degree of the power generation data, that is, the volatility of the data points relative to the mean value. The calculation of the standard deviation is a prior art and will not be elaborated here. This embodiment pays more attention to the dispersion degree of the data, that is, the volatility of the data points relative to the mean value, and can capture the local changes and anomalies of the data.

[0040] S2: Calculate the optimal truncation distance of the power generation; according to the optimal truncation distance of the power generation, use the density peak clustering algorithm to cluster the power generation to obtain multiple clustering clusters, calculate the mean value of the Euclidean distances between all data points in the clustering cluster and the cluster center, and mark the data points greater than the mean value in the clustering as outliers.

[0041] When predicting the power generation and load, if there are anomalies in the power generation or load of the power grid, the prediction system may misjudge the load demand or power generation capacity of the power grid. For example, during a sudden abnormal load surge at certain moments, the system may mistakenly think that the demand of the power grid is at a high level for a long time, resulting in excessive start-stop of the generating units and affecting the stable operation of the power grid. Therefore, this application needs to perform anomaly detection on the power generation data and load.

[0042] Among them, in the power generation and load of the power grid, anomalies often appear in the form of local sparsity or mutation. For example, a sudden load surge. The density peak clustering algorithm can efficiently identify the sparse outliers by focusing on the local density of the data.

[0043] In the density peak clustering algorithm, the calculation of the local density is a very important step, and the size of the local density usually depends on the choice of the truncation distance. The truncation distance refers to the size of the neighborhood considered when calculating the local density of a certain data point.

[0044] Different truncation distances will calculate different local densities, thus affecting the clustering results. If the truncation distance is too small, only a small number of data points will be considered when calculating the local density, resulting in the region with a high density being divided into multiple parts for calculation, making the clustering results inaccurate. If the truncation distance is too large, a large number of data points will be considered when calculating the local density, so that the region with a low density will be included in the clustering cluster where the region with a high density is located, making the clustering results inaccurate. Therefore, this application needs to calculate the corresponding optimal truncation distance according to the distribution of power generation or load.

[0045] The expression for the optimal truncation distance corresponding to power generation is: , where represents the optimal truncation distance of power generation; is a preset truncation distance, represents the degree of gradient change of power generation in the power generation sequence; represents the ceiling function; represents taking as the base exponential function, represents the maximum value function, indicating taking the and maximum value of the two; represents a hyperparameter. Exemplarily, takes 2, can be set according to the actual application scenario and will not be elaborated here.

[0046] This expression dynamically adjusts the optimal truncation distance by combining the degree of gradient change in the power generation sequence and the preset truncation distance . By taking the maximum value function , the problem of too small or too large truncation distance is avoided. A too small truncation distance may cause the region with a high density to be wrongly segmented, while a too large truncation distance may wrongly classify the region with a low density into the region with a high density, affecting the accuracy of the clustering results.

[0047] According to the optimal truncation distance, the power generation is clustered using the density peak clustering algorithm to obtain multiple clustering clusters. This part is the prior art and will not be elaborated here. Calculate the mean of the Euclidean distances between all data points in the clustering cluster and the cluster center, and mark the data points in the clustering that are greater than the mean as outliers. The calculation of the Euclidean distance is the prior art and will not be elaborated here.

[0048] S3: After removing the outliers in the power generation sequence, fill the data at the removed positions, and use the exponential smoothing method to obtain the power generation prediction value for the next moment; S4: In the same way as the method for obtaining the power generation prediction value, obtain the power consumption prediction value.

[0049] For the generated power, eliminate all the abnormal points, which may be caused by measurement errors, equipment failures, or other abnormal factors. Use interpolation methods (such as linear interpolation, spline interpolation, etc.) to fill in the data points. Or use other time series filling methods (such as forward filling, backward filling, mean filling, etc.) to fill in the data points.

[0050] After completing the data filling, the exponential smoothing method can be used to predict the generated power and power consumption at future moments. The exponential smoothing method is a time series prediction technique that assigns exponentially decreasing weights to past observations to smooth the past data and predict future values.

[0051] Thus, the predicted value of the generated power is obtained. Similarly, the predicted value of the power consumption is obtained by the same method as obtaining the predicted value of the generated power.

[0052] S5: Adjust the grid frequency according to the difference between the predicted value of the generated power and the predicted value of the power consumption.

[0053] For the generated power, obtain the change rate of the generated power at the next moment: , where represents the change rate of the generated power at the next moment, represents the generated power at the next moment; represents the generated power at the current moment.

[0054] Similarly, the change rate of the load at the next moment can be calculated.

[0055] If the change rate of the generated power is greater than the change rate of the load, it means that the generated power is greater than the load at this time, and the grid frequency will rise. At this time, it is necessary to use the energy storage system to absorb the excess power through charging, reduce the generated power, and thus relieve the frequency rise; If the change rate of the generated power is less than the change rate of the load, it means that the generated power is less than the load at this time, and the grid frequency will fall. At this time, it is necessary to use the energy storage system to supplement the power through discharging, help increase the generated power, and thus relieve the frequency fall.

[0056] If the change rate of the generated power is equal to the change rate of the load, it means that the generated power and the load change in proportion at this time, and there is no need to use the energy storage system for charging and discharging operations.

[0057] Ensure that the grid frequency is maintained within the standard range through the generated power to ensure the stability and reliable power supply of the power system.

[0058] The embodiment of the present application also discloses an energy storage coordination control system based on artificial intelligence, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the energy storage coordination control method based on the present application is implemented.

[0059] The above system further includes other components well-known to those skilled in the art, such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be described in detail herein.

[0060] In the present application, the aforementioned memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, a module, or both. Any such computer storage medium can be part of the device or accessible or connectable to the device.

[0061] Although this specification has shown and described multiple embodiments of the present application, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and idea of the present application. It should be understood that various alternative solutions to the embodiments of the present application described herein can be adopted in the process of practicing the present application.

[0062] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present application shall be covered within the protection scope of the present application.

Claims

1. An energy storage coordination control method based on artificial intelligence, characterized in that: Includes steps: Construct a power generation sequence, calculate the distribution deviation of the power generation in the power generation sequence, and calculate the gradient change degree of the power generation according to the distribution deviation degree; Calculate the optimal cutoff distance of power generation, the expression is: , where represents the optimal cutoff distance for power generation; is the preset cutoff distance, Indicates the degree of gradient change of power generation in the power generation sequence; represents the ceiling function; Indicates The exponential function with base , represents the maximum value function, represents a hyperparameter; According to the optimal cutoff distance of power generation, the power generation is clustered using the density peak clustering algorithm to obtain multiple clusters, the mean of the Euclidean distance between all data points in the cluster and the cluster center is calculated, and the data points in the cluster that are greater than the mean are recorded as abnormal points; After removing the abnormal points in the power generation sequence, fill the data at the removed positions and use the exponential smoothing method to obtain the power generation forecast value at the next moment; The power consumption forecast value is obtained in the same way as the power generation forecast value; The grid frequency is adjusted according to the difference between the predicted power generation and the predicted power consumption.

2. The energy storage coordination control method based on artificial intelligence according to claim 1 is characterized in that: The expression of the distribution deviation degree of power generation is: ,in, Indicates the degree of deviation of the distribution of power generation, represents the inverse tangent function, represents the median power generation, represents the mean value of power generation, Indicates the minimum value of power generation, Indicates the maximum value of power generation.

3. The energy storage coordination control method based on artificial intelligence according to claim 1 is characterized in that: The expression of the distribution deviation degree of power generation is: ,in, Indicates the degree of deviation of the distribution of power generation, represents the normalization function, represents the median power generation, Indicates the minimum value of power generation, Indicates the maximum value of power generation.

4. The energy storage coordination control method based on artificial intelligence according to claim 1 is characterized in that: The expression of gradient change degree is: , where Indicates the degree of gradient change in power generation; Indicates the degree of deviation in the distribution of power generation; Indicates the maximum value of the power generation data in the power generation sequence; Indicates the minimum value of the power generation data in the power generation series.

5. The energy storage coordination control method based on artificial intelligence according to claim 1 is characterized in that: The expression of gradient change degree is: , where Indicates the degree of gradient change in power generation; Indicates the degree of deviation in the distribution of power generation; Represents the standard deviation of power generation.

6. The energy storage coordination control method based on artificial intelligence according to claim 1 is characterized in that: The grid frequency is adjusted according to the difference between the power generation forecast value and the power consumption forecast value, including the following steps: Get the power generation change rate at the next moment: ,in, Indicates the rate of change of power generation at the next moment, Indicates the power generation at the next moment; Indicates the power generation at the current moment; similarly, obtains the rate of change of power consumption at the next moment; In response to the power generation change rate being less than the load change rate, the power generation is increased; in response to the power generation change rate being greater than the load change rate, the power generation is reduced.

7. The energy storage coordination control method based on artificial intelligence according to claim 1 is characterized in that: The method for filling the data at the removed position is the difference method, forward filling, backward filling or mean filling.

8. An energy storage coordination control system based on artificial intelligence, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the energy storage coordination control method based on artificial intelligence according to any one of claims 1 to 7 is implemented.

Images