An energy storage coordinated control method and system based on artificial intelligence

Abstract

The present application relates to the field of data processing technology, and in particular to an artificial intelligence-based energy storage coordinated control method and system, the method comprising: calculating the degree of distribution deviation of power generation in a power generation sequence, and calculating the degree of gradient change of power generation based on the degree of distribution deviation; calculating the optimal cutoff distance of power generation; clustering the power generation using a density peak clustering algorithm based on the optimal cutoff distance to obtain multiple clusters, calculating the mean of the Euclidean distance between all data points in the cluster and the cluster center, and recording data points in the cluster that are greater than the mean as outliers; removing outliers from the power generation sequence and filling the data at the removed positions, and using an exponential smoothing method to obtain a power generation forecast value at the next moment; obtaining a power consumption forecast value similarly to the method for obtaining the power generation forecast value; and adjusting the grid frequency based on the difference between the power generation forecast value and the power consumption forecast value. The present application has the effect of improving the accuracy of the grid frequency regulation results.

Description

Technical Field

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

[0002] With the increasing prevalence of renewable energy generation, particularly the rapid development of wind and photovoltaic power generation, the volatility and instability of energy supply in power systems have become increasingly prominent. Energy storage systems, as a key tool for regulating grid load fluctuations and balancing supply and demand, can effectively improve grid stability, reliability, and flexibility. Frequency regulation is a crucial function in power storage systems, reflecting the balance between power generation and load on the grid. When power generation and load do not match, grid frequency fluctuates, requiring frequency regulation to maintain stable grid operation.

[0003] When adjusting grid data, the energy storage system needs to respond quickly, so it is necessary to predict power generation data and load data so that the energy storage system can respond quickly based on the prediction results. For example, Chinese patent application document with publication number CN115549158A discloses a method and system for predicting power generation of an electrochemical energy storage power station with a time factor, 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 a day-ahead power generation prediction, determining the actual power of the energy storage power station at each moment of the next day and the time factor corresponding to the actual power based on the power station information; when the power generation prediction type is a 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 based on the power station information and the real-time status information of the power station; outputting the determined actual power and the time factor corresponding to the actual power to the grid dispatching center, which then uses the grid dispatching center to put the energy storage power station into operation. This patent application document generates a power generation prediction curve based on the real-time status of the electrochemical energy storage power station, providing dispatchers with a power generation curve that intuitively represents its capabilities.

[0004] During the prediction process, the collected data may be abnormal due to reasons such as system aging failure, sudden load fluctuations, etc., 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] In order to solve the technical problem of inaccurate grid frequency regulation results caused by abnormal data, the present application provides an artificial intelligence-based energy storage coordination control method and system.

[0006] In a first aspect, the present application provides an artificial intelligence-based energy storage coordinated control method and system, which adopts the following technical solutions:

[0007] An artificial intelligence-based energy storage coordinated control method includes the following steps: constructing a power generation sequence, calculating the distribution deviation of the power generation in the power generation sequence, and calculating the gradient change of the power generation based on the distribution deviation; and calculating the optimal cutoff distance of the power generation, which is expressed as:

[0008] , 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 function, represents a hyperparameter; based on the optimal cutoff distance of power generation, the density peak clustering algorithm is used to cluster the power generation 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 outliers; after removing the outliers in the power generation sequence, the data at the removed positions are filled, and the power generation forecast value at the next moment is obtained using the exponential smoothing method; 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 power generation forecast value and the power consumption forecast value.

[0009] The beneficial effects are: by combining the degree of gradient change in the power generation sequence with the preset truncation distance to dynamically adjust the optimal truncation distance, and by taking the maximum function to avoid the problem of too small or too large truncation distance. Too small truncation distance may cause high-density areas to be incorrectly segmented, while too large truncation distance may mistakenly classify low-density areas into high-density areas, affecting the accuracy of clustering results, so as to find the optimal truncation distance;

[0010] Clustering is performed using a clustering algorithm based on the optimal cutoff distance to obtain multiple clusters. Data points in the power generation sequence are grouped according to their similarity, so that data points within the same cluster have high similarity, while data points between different clusters have large differences. By calculating the mean of the Euclidean distance between all data points in the cluster and the cluster center, and identifying data points greater than this mean as outliers, outliers in the power generation sequence can be effectively identified and removed. After the outliers are removed, data padding is performed to achieve the purpose of denoising the data sequence. Power generation and power consumption forecasts are then made based on the denoised data sequence. Based on the forecast results, power generation is adjusted to ensure that the grid frequency remains within the standard range, thereby ensuring stable and reliable power supply of the power system and improving the accuracy of the grid frequency regulation results.

[0011] Optionally, the expression for the degree of deviation of the power generation distribution is:

[0012] ,in, Indicates the degree of deviation of the distribution of power generation, represents the inverse tangent function, represents the median of power generation, represents the mean value of power generation, Indicates the minimum value of power generation, Indicates the maximum power generation amount.

[0013] The beneficial effect is that it provides a method for quantifying the degree of deviation in power generation distribution. It considers the median, mean, minimum, and maximum values ​​to comprehensively calculate the distribution deviation of data points, thereby better capturing the skewness of the data, that is, whether the data distribution is symmetrical. This is suitable for scenarios where the skewness of power generation needs to be analyzed, especially when the data distribution is uneven or contains extreme values. This skewness analysis is particularly important.

[0014] Optionally, the expression for the degree of deviation of the power generation distribution is: ,in, Indicates the degree of deviation of the distribution of power generation, represents the normalization function, represents the median of power generation, Indicates the minimum value of power generation, Indicates the maximum power generation amount.

[0015] The beneficial effect is: it provides another method to quantify the degree of deviation of power generation distribution, considering only the median, minimum and maximum values, and To measure the symmetry of the data distribution, the symmetry factor is then normalized and 0.5 is subtracted to adjust the output range. This method is simple and computationally inefficient, making it suitable for scenarios where the symmetry of a data distribution needs to be assessed quickly and easily.

[0016] Optionally, the expression for the degree of gradient change 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 power generation data in the power generation series; Indicates the minimum value of power generation data in the power generation series.

[0017] The beneficial effects are: The larger the value is, the higher the degree of deviation of power generation distribution is; on the contrary, the lower the degree of deviation is. This represents the range of power generation, the difference between the maximum and minimum values. This range measures the magnitude of data variation, reflecting the total change from the minimum to the maximum value. This gradient calculation method captures the overall magnitude of power generation data variation, particularly when extreme values ​​are present, effectively reflecting the data's fluctuation range.

[0018] Optionally, the expression for the degree of gradient change is: , where Indicates the degree of gradient change in power generation; Indicates the degree of deviation in the distribution of power generation; Indicates the standard deviation of power generation.

[0019] The beneficial effect is that the standard deviation expresses the degree of dispersion of power generation data, that is, the volatility of data points relative to the mean. This gradient change calculation method focuses more on the degree of dispersion of data, that is, the volatility of data points relative to the mean, and can capture local changes and anomalies in the data.

[0020] Optionally, adjusting the grid frequency according to the difference between the power generation forecast value and the power consumption forecast value includes the following steps: obtaining 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 rate of change of power generation being less than the rate of change of load, increases the power generation; in response to the rate of change of power generation being greater than the rate of change of load, decreases the power generation.

[0021] Optionally, a method for filling the data at the removed position is interpolation, forward filling, backward filling or mean filling.

[0022] In a second aspect, the present application provides an artificial intelligence-based energy storage coordination control system, which adopts the following technical solutions:

[0023] An energy storage coordination control system based on artificial intelligence includes: 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 is implemented.

[0024] The beneficial effect is that the above-mentioned artificial intelligence-based energy storage coordinated control method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a system based on the memory and the processor for easy use.

[0025] This application has the following technical effects:

[0026] 1. Find the optimal cutoff distance, and cluster the data using a clustering algorithm based on the optimal cutoff distance to obtain multiple clusters. By calculating the mean of the Euclidean distance between all data points in the cluster and the cluster center, and identifying data points greater than this mean as outliers, 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 and power consumption are predicted 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, thereby ensuring the stability and reliable power supply of the power system and improving the accuracy of the grid frequency regulation results.

[0027] 2. The optimal cutoff distance is dynamically adjusted by combining the gradient change in the power generation sequence with the preset cutoff distance. By taking the maximum function, the problem of a cutoff distance that is too small or too large is avoided. A cutoff distance that is too small may cause high-density areas to be incorrectly segmented, while a cutoff distance that is too large may mistakenly classify low-density areas as high-density areas, affecting the accuracy of the clustering results. The optimal cutoff distance is found. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] By reading the detailed description below 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 accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding numbers represent the same or corresponding parts.

[0029] Figure 1 This is a method flow chart of an energy storage coordination control method based on artificial intelligence in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0031] It should be understood that when the terms "first," "second," etc. are used in the claims, specification, and drawings of this application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "comprise" and "comprising" used in the specification and claims of this application indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0032] The present application discloses an artificial intelligence-based energy storage coordinated control method for regulating grid frequency. Grid frequency regulation plays a critical role in energy storage systems. In power systems, grid frequency typically remains within a fixed range (e.g., 50 Hz or 60 Hz), directly reflecting the balance between power generation and load. Exceeding this range can damage grid equipment and even trigger large-scale power outages. Therefore, frequency regulation is a crucial component of grid operation.

[0033] The frequency of a power grid reflects the balance between power generation and load in the system. Frequency stability requires that the generated power and the load power be equal. If the two are not equal, or not nearly equal, the frequency will shift, leading to grid instability and potentially causing large-scale power outages.

[0034] Reference Figure 1 The energy storage coordinated control method based on artificial intelligence includes steps S1 to S5, which are specifically as follows:

[0035] S1: 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 based on the distribution deviation degree.

[0036] Collect power generation data and load data. The default collection frequency of power generation data and load data is 0.2Hz.

[0037] Generation data refers to the amount of power generated by generators in the power grid per unit time, collected through SCADA (Supervisory Control and Data Acquisition) systems. Load data refers to the amount of power consumed by electrical equipment and users per unit time, collected through AMI (Advanced Metering Infrastructure) systems. Both SCADA and AMI systems are existing technologies and will not be discussed in detail here.

[0038] In one embodiment, the expression for the degree of deviation of the distribution of power generation is:

[0039] ,in, Indicates the degree of deviation of the distribution of power generation, represents the inverse tangent function, represents the median of power generation, represents the mean value of power generation, Indicates the minimum value of power generation, Indicates the maximum power generation amount.

[0040] in, The ratio represents the deviation of power generation from the median, which measures the symmetry of the data distribution. If this ratio is greater than 1, it means that the data distribution is skewed to the right; if it is less than 1, it means that the data distribution is skewed to the left; if it is equal to 1, it means that the data distribution is symmetric.

[0041] Arctan represents the inverse tangent function, which Map to In the interval, then by multiplying Map the result to an interval to quantify the degree of deviation from the distribution.

[0042] This embodiment provides a method for quantifying the degree of deviation in power generation distribution. This method considers the median, mean, minimum, and maximum values ​​to comprehensively calculate the degree of deviation in the distribution of data points. This method better captures the skewness of the data, specifically whether the data distribution is symmetrical. This method is suitable for scenarios where power generation skewness analysis is required, especially when the data distribution is uneven or contains extreme values. This skewness analysis is particularly important.

[0043] In one embodiment, the expression for the degree of deviation of the distribution of power generation is:

[0044] ,in, Indicates the degree of deviation of the distribution of power generation, represents the normalization function, represents the median of power generation, Indicates the minimum value of power generation, Indicates the maximum power generation amount.

[0045] This embodiment provides another method for quantifying the degree of deviation of power generation distribution, which only considers the median, minimum and maximum values, and uses the ratio To measure the symmetry of the data distribution, the symmetry factor is then normalized and 0.5 is subtracted to adjust the output range. This method is simple and computationally inefficient, making it suitable for scenarios where the symmetry of a data distribution needs to be assessed quickly and easily.

[0046] In one embodiment, the expression for the degree of gradient change 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 power generation data in the power generation series; Indicates the minimum value of power generation data in the power generation series.

[0047] The larger the value is, the higher the degree of deviation of power generation distribution is; on the contrary, the lower the degree of deviation is. This represents the range of power generation, i.e., the difference between the maximum and minimum values. This range measures the magnitude of data variation, reflecting the total change from the minimum to the maximum value. This embodiment captures the overall magnitude of power generation data variation, particularly when extreme values ​​are present, effectively reflecting the data's fluctuation range.

[0048] In one embodiment, the expression for the degree of gradient change 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. The standard deviation expresses the dispersion of power generation data, that is, the volatility of data points relative to the mean. The calculation of standard deviation is well-known and will not be detailed here. This embodiment focuses on the dispersion of data, that is, the volatility of data points relative to the mean, which can capture local changes and anomalies in the data.

[0049] S2: Calculate the optimal cutoff distance of power generation; based on the optimal cutoff distance of power generation, use the density peak clustering algorithm to cluster the power generation to obtain multiple clusters, calculate the mean of the Euclidean distance between all data points in the cluster and the cluster center, and mark the data points in the cluster that are greater than the mean as outliers.

[0050] When forecasting power generation and load, if the power grid's power generation or load is abnormal, the forecasting system may misjudge the grid's load demand or power generation capacity. For example, when there is an abnormal load surge at a certain moment, the system may mistakenly believe that the grid demand is at a high level for a long time, resulting in excessive startup and shutdown of generator sets, affecting the stable operation of the grid. Therefore, this application requires anomaly detection of power generation data and load.

[0051] Anomalies in power generation and load often occur in a localized, sparse manner or in abrupt, sudden changes, such as a sudden load surge. The density peak clustering algorithm, by focusing on the local density of data, can effectively identify sparsely distributed anomalies.

[0052] In the density peak clustering algorithm, the calculation of local density is a very important step, and the size of the local density usually depends on the choice of the cutoff distance. The cutoff distance refers to the size of the neighborhood considered when calculating the local density of a data point.

[0053] Different cutoff distances will calculate different local densities, thus affecting the clustering results. If the cutoff distance is too small, only a few data points will be considered when calculating the local density, which will cause the high-density area to be divided into multiple parts for calculation, making the clustering results inaccurate; if the cutoff distance is too large, more data points will be considered when calculating the local density, so that the high-density area will include the low-density area in its cluster, making the clustering results inaccurate. Therefore, this application needs to calculate the corresponding optimal cutoff distance based on the distribution of power generation or load.

[0054] The expression of the optimal cutoff distance corresponding to power generation is:

[0055] , 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, which means taking and The maximum value of the two; represents a hyperparameter, for example, Take 2, The value can be set according to the actual application scenario and will not be described here.

[0056] This expression is obtained by combining the degree of gradient change in the power generation series. and preset cutoff distance To dynamically adjust the optimal truncation distance, by taking the maximum function , avoiding the problem of too small or too large cutoff distance. Too small cutoff distance may cause high-density areas to be incorrectly segmented, while too large cutoff distance may mistakenly classify low-density areas into high-density areas, affecting the accuracy of clustering results.

[0057] Based on the optimal cutoff distance, the power generation is clustered using the density peak clustering algorithm to obtain multiple clusters. This is conventional technology and will not be described in detail here. The mean of the Euclidean distance between all data points in the cluster and the cluster center is calculated, and data points in the cluster with a value greater than the mean are marked as outliers. The calculation of the Euclidean distance is conventional technology and will not be described in detail here.

[0058] S3: 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;

[0059] S4: The power consumption forecast value is obtained in the same way as the power generation forecast value.

[0060] For power generation, remove all outliers, which may be caused by measurement errors, equipment failures, or other abnormal factors. Use interpolation methods (such as linear interpolation and spline interpolation) to fill in the data points. Alternatively, use other time series filling methods (such as forward filling, backward filling, and mean filling) to fill in the data points.

[0061] After completing the data filling, exponential smoothing can be used to predict future power generation and consumption. Exponential smoothing is a time series forecasting technique that assigns exponentially decreasing weights to past observations to smooth past data and predict future values.

[0062] At this point, the power generation forecast value is obtained, and the power consumption forecast value is obtained in the same way as the power generation forecast value.

[0063] S5: Adjust the grid frequency according to the difference between the power generation forecast value and the power consumption forecast value.

[0064] For power generation, obtain the rate of change of power generation at the next moment: ,in, Indicates the rate of change of power generation at the next moment, Indicates the amount of electricity generated at the next moment; Indicates the power generation at the current moment.

[0065] Similarly, the rate of change of the load at the next moment can be calculated.

[0066] If the rate of change of power generation is greater than the rate of change of load, it means that the power generation is greater than the load, and the frequency of the power grid will increase. At this time, the energy storage system needs to absorb excess power through charging, reduce power generation, and thus alleviate the frequency increase;

[0067] If the rate of change of power generation is smaller than the rate of change of load, it means that the power generation is smaller than the load and the grid frequency will decrease. At this time, the energy storage system needs to be used to supplement electricity through discharge to help increase power generation and thus alleviate the frequency decrease.

[0068] If the rate of change of power generation is equal to the rate of change of load, it means that the power generation and load change in equal proportions, and there is no need to use the energy storage system for charging and discharging operations.

[0069] The power generation is used to ensure that the grid frequency is maintained within the standard range to ensure the stability and reliable power supply of the power system.

[0070] An embodiment of the present application also discloses an artificial intelligence-based energy storage coordination control system, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the artificial intelligence-based energy storage coordination control method according to the present application is implemented.

[0071] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0072] In this application, the aforementioned memory can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High Bandwidth Memory (HBM), 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, module, or both. Any such computer storage medium can be part of, accessible to, or connected to the device.

[0073] Although this specification has shown and described a number of embodiments of the present application, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, variations, and alternatives without departing from the spirit and scope of the present application. It should be understood that in practicing the present application, various alternatives to the embodiments of the present application described herein may be employed.

[0074] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. An energy storage coordinated control method based on artificial intelligence, characterized in that: Including 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 based on the distribution deviation degree; The optimal cutoff distance for calculating power generation is expressed as: , 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 function, represents a hyperparameter; According to the optimal cutoff distance of power generation, the density peak clustering algorithm is used to cluster the power generation 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 outliers. 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; Adjust the grid frequency based on the difference between the power generation forecast and the power consumption forecast; The expression of the 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 power generation data in the power generation series; Indicates the minimum value of power generation data in the power generation series; Or the expression of the degree of gradient change is: , where Indicates the degree of gradient change in power generation; Indicates the degree of deviation in the distribution of power generation; Indicates the standard deviation of power generation.

2. The energy storage coordinated 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 of power generation, represents the mean value of power generation, Indicates the minimum value of power generation, Indicates the maximum power generation amount.

3. The energy storage coordinated 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 of power generation, Indicates the minimum value of power generation, Indicates the maximum power generation amount.

4. The energy storage coordinated control method based on artificial intelligence according to claim 1 is characterized in that: Adjusting the grid frequency according to the difference between the power generation forecast value and the power consumption forecast value includes 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.

5. The energy storage coordinated 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.

6. 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 coordinated control method based on artificial intelligence according to any one of claims 1 to 5 is implemented.

Images