An alternative energy storage control system based on power grid operation optimization data analysis

Abstract

The present invention relates to the technical field of power system optimization and control, and specifically to an alternative energy storage control system based on power grid operation optimization data analysis. The system includes: a power grid data acquisition module for acquiring various types of power data; a power grid data processing module for determining the fluctuation coefficient of each substation, and combining the correlation between different types of power data to determine the power stability factor of each substation; based on the discrete degree of all peak values ​​corresponding to the acquisition time, and the average distribution of all elements in each cluster, and combined with the power stability factor, the dynamic stability index of each substation is determined; an energy storage control module for controlling the alternative energy storage control system. The present application improves the control accuracy of the alternative energy storage control system by analyzing the uncertainty of the power grid load behavior.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization control, and in particular to an alternative energy storage control system based on power grid operation optimization data analysis. Background Art

[0002] With the transformation of the global energy structure, alternative energy storage control systems based on grid operation optimization have emerged. This system optimizes the allocation of energy storage resources by analyzing grid operation data to cope with the volatility and uncertainty of renewable energy. The development of alternative energy storage control systems has benefited from the rapid advancement of information technology, especially the application of big data and artificial intelligence technologies. These technologies enable the system to monitor the status of the grid in real time, predict changes in energy supply and demand, and optimize the charging and discharging strategies of energy storage equipment through intelligent algorithms. The significance of the alternative energy storage control system is that it not only improves the operating efficiency and reliability of the grid, but also helps reduce dependence on fossil fuels, reduce greenhouse gas emissions, and promote energy transformation and sustainable development. In addition, the alternative energy storage control system also provides more flexibility for the electricity market, making electricity supply more economical and efficient, while also providing users and power operators with more choices and control capabilities.

[0003] During grid operation, the uncertainty of electricity demand mainly stems from the randomness and unpredictability of users' electricity consumption behavior, including changes in industrial production, fluctuations in commercial activities, irregularities in residents' electricity consumption, and the impact of extreme weather conditions on electricity demand. These factors lead to deviations between actual electricity demand and predicted values, reducing the control accuracy of alternative energy storage control systems. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an alternative energy storage control system based on power grid operation optimization data analysis. The technical solutions adopted are as follows:

[0005] The present invention proposes an alternative energy storage control system based on power grid operation optimization data analysis, the system comprising:

[0006] The power grid data acquisition module is used to obtain all the electrical data of each substation in the power grid operation at each acquisition time within a preset time period before the current time, wherein all the electrical data are current data and electric energy data;

[0007] The power grid data processing module is used to fit the binary data consisting of the current and power data of each substation at all collection moments to obtain a fitting curve. Based on the degree of disorder of all power data of each substation and the difference between all power data and the corresponding fitting value on the fitting curve, the fluctuation coefficient of each substation is determined. In addition, the power stability factor of each substation is determined by combining the correlation between different types of power data.

[0008] A baseline correction algorithm is used based on various types of electrical data of each substation to obtain various types of electrical data to be studied for each substation, and fitting curves of various types of electrical data to be studied are obtained by fitting the various types of electrical data to be studied. All peak values ​​of the fitting curves of various types of electrical data are extracted, and based on the discrete degree of all peak values ​​corresponding to the acquisition time, a change random index of each substation is determined; the various types of electrical data to be studied for each substation are clustered to obtain multiple clusters, and based on the average distribution of all elements in each cluster, a dispersion index of each substation is determined, and the dynamic stability index of each substation is determined by combining the change random index and the power stability factor.

[0009] The energy storage control module is used to determine the adaptability index of the power grid at the current moment based on the average distribution of the dynamic stability index of all substations in the power grid at the current moment; based on the average distribution of the power energy data of all substations in the power grid at each collection moment, combined with the adaptability index and the time series prediction model, all predicted power values ​​of the power grid at the current moment are obtained to control the alternative energy storage control system.

[0010] Preferably, the method for determining the fluctuation coefficient of each substation is:

[0011] Analyze the mean square error between all the electric energy data of each substation and the corresponding fitting value on the fitting curve;

[0012] Analyze the information entropy of various types of electrical data at each substation and calculate the difference in information entropy between different types of electrical data;

[0013] The fluctuation coefficient of each substation is the result of the fusion of the mean square error and information entropy difference of each substation.

[0014] Preferably, the expression of the power stability factor of each substation is: Where A i represents the power stability factor of substation i; a i represents the correlation coefficient between all current data and all electric energy data of substation i; b i represents the fluctuation coefficient of substation i; ε represents a constant preset to be greater than 0.

[0015] Preferably, the method for acquiring various types of electrical data to be studied for each substation is:

[0016] The various types of electrical data of each substation are used as inputs of the baseline correction algorithm, and the baselines of various types of electrical data of each substation are output;

[0017] All electrical data that are greater than the maximum value of the baseline in each type of electrical data are taken as the various types of electrical data to be studied for each substation.

[0018] Preferably, the random index of change of each substation is the average value of the discrete degree of the peak value corresponding to the collection time of all types of to-be-studied electrical data of each substation.

[0019] Preferably, the method for determining the dispersion index of each substation is:

[0020] Analyze the mean of all elements in each cluster of various types of electrical data to be studied for each substation;

[0021] The product of the dispersion degree of the element mean of all clusters of various types of electrical data to be studied of each substation and the total number of clusters is analyzed, and the dispersion index of each substation is the mean of the product of all types of electrical data to be studied of each substation.

[0022] Preferably, the expression of the dynamic stability index of each substation is: Where B i represents the dynamic stability index of substation i; C i represents the random index of substation i; D i represents the dispersion index of substation i; σ represents a constant preset to be greater than 0.

[0023] Preferably, the adaptability index of the power grid at the current moment is the average of the dynamic stability indexes of all substations in the power grid at the current moment.

[0024] Preferably, the method for determining all predicted electric energy values ​​of the power grid at the current moment is:

[0025] The average of the electric energy data of all substations at each collection time before the current time is used as the actual electric energy value at each collection time;

[0026] All actual electric energy values ​​of the power grid at the current moment are used as the input of the time series prediction model, in which the adaptability index of the power grid is used as an exogenous variable to obtain all predicted electric energy values ​​of the power grid.

[0027] Preferably, the controlling of the alternative energy storage control system includes:

[0028] Analyze the mean of all actual electric energy values ​​of the power grid at the current moment and the mean of all predicted electric energy values, and determine the ratio of the mean of the predicted electric energy values ​​to the mean of the actual electric energy values. If the ratio is greater than a preset charging threshold and less than a preset discharging threshold, the alternative energy storage control system maintains the current state. If the ratio is greater than the preset discharging threshold, the alternative energy storage control system discharges. If the ratio is less than the preset charging threshold, the alternative energy storage control system charges, where the preset discharging threshold is always greater than the preset charging threshold.

[0029] The present invention has the following beneficial effects:

[0030] The present application obtains a fitting curve by fitting a binary group consisting of current and electric energy data at each collection moment of each substation. Based on the degree of disorder of all electric energy data of each substation and the difference between all electric energy data and the corresponding fitting value on the fitting curve, and combined with the correlation between different types of electric data, the electric energy stability factor of each substation is determined. The beneficial effect is that the accuracy of the prediction of the load behavior of the power grid can be improved. The present application determines the random index of change of each substation by the degree of dispersion of all peak values ​​in various types of electric data to be studied of each substation. The various types of electric data to be studied of each substation are clustered to obtain multiple clusters. Based on the average distribution of all elements in each cluster, the dispersion index of each substation is determined. In combination with the random change index and the power stability factor, the dynamic stability index of each substation is determined, which has the beneficial effect of reducing the impact of the randomness of load changes on the control accuracy of the alternative energy storage control system; this application determines the adaptability index of the power grid at the current moment by analyzing the average distribution of the dynamic stability index of all substations in the power grid at the current moment; based on the average distribution of the power data of all substations at each acquisition moment in the power grid, combined with the adaptability index and the time series prediction model, all predicted power values ​​of the power grid at the current moment are obtained, and the alternative energy storage control system is controlled, which has the beneficial effect of accurately predicting power demand and improving the control accuracy of the alternative energy storage control system. This application improves the accuracy of the prediction of power grid load behavior and the accuracy of the prediction of power demand by analyzing the uncertainty of power grid load behavior, and improves the control accuracy of the alternative energy storage control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 A block diagram of an alternative energy storage control system based on power grid operation optimization data analysis provided in one embodiment of the present application;

[0033] Figure 2 A schematic diagram of a process for obtaining a dynamic stability index according to an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a process for extracting an adaptability index of a power grid provided in one embodiment of the present application;

[0035] Figure 4A schematic diagram of the control process of an alternative energy storage control system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0036] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of an alternative energy storage control system based on grid operation optimization data analysis proposed by the present invention. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0037] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0038] The following describes in detail a specific solution of an alternative energy storage control system based on power grid operation optimization data analysis provided by the present invention with reference to the accompanying drawings.

[0039] See also Figure 1 , which shows a block diagram of an alternative energy storage control system based on power grid operation optimization data analysis provided by an embodiment of the present invention. The system includes: a power grid data acquisition module 101, a power grid data processing module 102, and an energy storage control module 103.

[0040] The power grid data collection module 101 is used to obtain all electrical data of each substation in the power grid operation at each collection moment within a preset time period before the current moment, wherein all electrical data are current data and electric energy data.

[0041] Each substation in the power grid is responsible for substation operations in a specific area, including voltage regulation, power distribution, and control. Ammeters and energy meters are installed at the output terminals of each substation to collect all electrical data at each time point within a preset time period, t. This data is comprised of current and energy data, collected at a frequency of f. To eliminate dimensionless data, all collected electrical data is normalized.

[0042] It should be noted that there are many commonly used normalization methods. In this embodiment, the z-score normalization method is used to normalize the data. The implementer can also use other normalization methods such as the maximum and minimum value normalization method to normalize the data. This embodiment does not impose any special restrictions on the selection of the normalization method.

[0043] Among them, the z-score normalization method is a well-known technology, and its specific process of data normalization processing is not repeated here.

[0044] The power grid data processing module 102 is used to fit the binary group consisting of the current and electric energy data of each substation at all collection moments to obtain a fitting curve. Based on the degree of chaos of all electric energy data of each substation and the difference between all electric energy data and the corresponding fitting values ​​on the fitting curve, the fluctuation coefficient of each substation is determined, and the electric energy stability factor of each substation is determined based on the correlation between different types of electric data.

[0045] Step S1: Fit the binary group consisting of current and electric energy data of each substation at each collection moment to obtain a fitting curve. Based on the degree of chaos of all electric energy data of each substation and the difference between all electric energy data and the corresponding fitting value on the fitting curve, determine the fluctuation coefficient of each substation, and combine the correlation between different types of electric data to determine the electric energy stability factor of each substation.

[0046] The relationship between the power and current of the substation load is complex. It not only depends on the power factor and characteristics of the load, but is also affected by factors such as grid voltage stability, frequency, and harmonics generated by nonlinear loads. Therefore, the relationship between the power and current of the substation load is not a simple linear relationship. When nonlinear fluctuations occur in the substation load, it will affect the power quality of the grid.

[0047] Therefore, to avoid poor power quality caused by substation load changes, which in turn may cause the energy storage system's regulatory response to differ from actual demand, leading to a decrease in the control accuracy of the alternative energy storage control system, this embodiment monitors changes in power data in real time and analyzes the differences and correlations between current and power to determine whether power quality has deteriorated. This allows for flexible adjustment of charging and discharging strategies, timely response to grid load changes, and avoidance of resource waste. Specifically:

[0048] S101: Fit the binary data consisting of the current and electric energy data of each substation at each collection moment to obtain a fitting curve. Based on the degree of chaos of all electric energy data of each substation and the difference between all electric energy data and the corresponding fitting value on the fitting curve, determine the fluctuation coefficient of each substation.

[0049] (1) The current data and electric energy data of each substation at each collection moment are combined into two tuples at each collection moment, and all the two tuples of each substation are fitted to obtain the fitting curve of each substation. In the fitting process, the current data is the independent variable and the electric energy data is the dependent variable.

[0050] It should be noted that there are many commonly used fitting methods. In this embodiment, polynomial regression is used to fit the current data and the electric energy data. The implementer may also use other fitting methods. This embodiment does not impose any special restrictions on the selection of the fitting method.

[0051] Among them, polynomial regression is a well-known technology, and the specific process of fitting the data is not described in detail.

[0052] (2) Analyze the mean square error between all the electric energy data of each substation and the corresponding fitting value on the fitting curve;

[0053] Furthermore, the information entropy of each type of electrical data of each substation is analyzed, and the difference between the information entropy of different types of electrical data is calculated;

[0054] It should be noted that there are many methods for measuring the differences between data. In this embodiment, the difference between the information entropy of different types of electrical data is measured by calculating the absolute value of the difference between the information entropy of different types of electrical data. The implementer may also use other methods for measuring data differences such as ratios. This embodiment does not impose any special restrictions on the selection of methods for measuring data differences.

[0055] The calculation processes of mean square error and information entropy are both well-known technologies, and their specific calculation processes will not be repeated here.

[0056] (3) Based on the mean square error and the information entropy difference, the fluctuation coefficient of each substation is determined, and the fluctuation coefficient of each substation is the result of the fusion of the mean square error and the information entropy difference of each substation.

[0057] It should be understood that fusion refers to the result of combining two or more indicators through positive fusion, that is, combining two or more indicators through methods such as addition or multiplication to obtain a comprehensive indicator, thereby more comprehensively and accurately evaluating a phenomenon or problem. This fusion method is not limited to simple arithmetic operations and can also include more complex statistical models and analysis methods. Implementers can choose according to their specific circumstances and this embodiment does not impose any special restrictions.

[0058] Preferably, in this embodiment, the fluctuation coefficient of each substation is the product of the mean square error of each substation and the information entropy difference; in actual application, as other implementation methods, the fluctuation coefficient of each substation is an exponential function value with a natural constant as the base and the sum of the mean square error of each substation and the information entropy difference as the independent variable.

[0059] Furthermore, according to the fluctuation coefficient of each substation, it can be understood that the fluctuation coefficient of the substation combines the error of the regression model and the randomness of the data distribution. The mean square error reflects the accuracy of the linear regression model prediction, and the information entropy difference reflects the randomness of the probability distribution of current and electric energy. The higher the information entropy, the greater the uncertainty of the data, and the larger the mean square error, the greater the prediction error of the regression model under this uncertainty. Therefore, the greater the fluctuation coefficient of the substation, the worse the stability of the electric energy in the power grid; conversely, the smaller the information entropy, the smaller the uncertainty of the data, and the smaller the mean square error, the smaller the prediction error of the regression model under this uncertainty. Therefore, the smaller the fluctuation coefficient of the substation, the better the stability of the electric energy in the power grid.

[0060] S102: Based on the fluctuation coefficient of each substation and in combination with the correlation between different types of electricity data, determine the power stability factor of each substation.

[0061] To assess the quality of power in the grid, the power stability factor for each substation is determined by integrating the fluctuation coefficient of the substation and the correlation between current and power data. This allows for timely regulation of the charge and discharge status of the alternative energy storage control system. Specifically,

[0062] Power stability factor A of substation i i The expression is: Where a i represents the correlation coefficient between all current data and all electric energy data of substation i; b i represents the fluctuation coefficient of substation i; ε represents a preset constant greater than 0, which is used to prevent the denominator from being 0. The value of ε is set manually. In this embodiment, the value of ε is 0.01. Under the premise of ensuring that the denominator is not 0 and does not excessively affect the calculation results, the implementer can set it according to the specific situation. This embodiment does not impose any special restrictions.

[0063] It should be noted that there are many methods for calculating the correlation coefficient between data groups. In this embodiment, the correlation between the current data and the electric energy data of each substation is measured by calculating the Pearson correlation coefficient between all current data and all electric energy data of each substation. The implementer may also use other methods for calculating the correlation coefficient, such as the Kendall rank correlation coefficient or the Spearman correlation coefficient. This embodiment does not impose any special restrictions on the selection of the method for calculating the correlation coefficient.

[0064] Furthermore, according to the power stability factor of each substation, it can be understood that in the power system, the correlation coefficient of all current data and all power data of the substation reflects the degree of correlation between current and power. The larger the correlation coefficient, the more the fluctuations between current and power tend to be synchronized, indicating that the stability of power quality is better. The fluctuation coefficient of the substation combines the error of the regression model and the randomness of the data distribution. The mean square error reflects the accuracy of the linear regression model prediction, while the information entropy difference reflects the randomness of the probability distribution of current and power. The fluctuation coefficient indicates the comprehensive measure of the uncertainty of the grid load behavior and the prediction error. The smaller the fluctuation coefficient, the smaller the uncertainty of the grid load behavior and the prediction error, resulting in better stability of power in the grid. Therefore, if the correlation coefficient of the substation is larger and the fluctuation coefficient is smaller, the power stability factor of the substation is larger, indicating that the stability of power in the grid is better. Conversely, if the correlation coefficient of the substation is smaller and the fluctuation coefficient is larger, the power stability factor of the substation is smaller, indicating that the power in the grid is more unstable.

[0065] Step S2: Based on various types of electrical data of each substation, a baseline correction algorithm is used to obtain various types of electrical data to be studied of each substation, and the various types of electrical data to be studied are fitted to obtain fitting curves of various types of electrical data, and all peaks of the fitting curves of various types of electrical data are extracted. Based on the discrete degree of all peaks corresponding to the collection time, the change random index of each substation is determined; the various types of electrical data to be studied of each substation are clustered to obtain multiple clusters, and the dispersion index of each substation is determined based on the average distribution of all elements in each cluster, and the dynamic stability index of each substation is determined by combining the change random index and the power stability factor.

[0066] When analyzing the load behavior of substation output, the impact of user electricity consumption and fixed electricity consumption patterns on the analysis is very significant. The changes in electricity load data on the user side are unstable. This instability requires alternative energy storage control systems to take into account extreme conditions of peak load and minimum load during planning and operation to ensure the stability and reliability of the power grid. In contrast, fixed electricity consumption patterns, such as traffic lights or street lights, have relatively stable electricity consumption time and quantity, which facilitates load forecasting and power distribution in substations. Fixed electricity consumption usually does not cause sudden load changes on the power grid, allowing alternative energy storage control systems to more accurately perform power scheduling and resource allocation.

[0067] Therefore, in order to improve the control accuracy of alternative energy storage control systems and achieve a balance between power supply and demand, the changes in current and energy used by users can be analyzed to more accurately dispatch power and allocate resources. Specifically:

[0068] (1) The various types of electrical data of each substation are used as input to the baseline correction algorithm, and the baseline of each type of electrical data of each substation is output.

[0069] (2) Furthermore, all the electrical data that are greater than the maximum value of the baseline in each type of electrical data are taken as the various types of electrical data to be studied for each substation.

[0070] (3) Furthermore, the mean of the discrete degrees of the peak values ​​of all the types of to-be-studied electrical data of each substation corresponding to the collection time is recorded as the random index of change of each substation.

[0071] (4) Further, clustering is performed on various types of electrical data to be studied for each substation to obtain multiple clusters of various types of electrical data to be studied for each substation, and the mean values ​​of all elements in each cluster of various types of electrical data to be studied for each substation are analyzed.

[0072] It should be noted that there are many commonly used data clustering algorithms. In this embodiment, the DBSCAN density clustering algorithm is used to cluster point data. The implementer can also use other clustering algorithms such as the k-means clustering algorithm or mean shift clustering. This embodiment does not impose any special restrictions on the selection of clustering algorithms.

[0073] Among them, the DBSCAN density clustering algorithm is a well-known technology, and its specific process of clustering data is not described in detail.

[0074] (5) Analyze the product of the dispersion degree of the element mean of all clusters of various types of electrical data to be studied for each substation and the total number of clusters, and take the mean of the product of all types of electrical data to be studied for each substation as the dispersion index of each substation.

[0075] (6) Based on the dispersion index, the random change index, and the power stability factor, the dynamic stability index of each substation is determined, specifically:

[0076] Dynamic stability index B of substation i i The expression is: Where C i represents the random index of substation i; D i represents the dispersion index of substation i; σ represents a preset constant greater than 0, which is used to prevent the denominator from being 0. The value of σ is set manually. In this embodiment, the value of σ is 0.01. Under the premise of ensuring that the denominator is not 0 and does not excessively affect the calculation results, the implementer can set it according to the specific situation. This embodiment does not impose any special restrictions.

[0077] Furthermore, according to the dynamic stability index of each substation, it can be understood that in the power grid system, the power stability factor represents the stability of the power quality. The larger the power stability factor, the more stable the relationship between current and power, the better the power quality of the power grid, the better the adaptability of the power grid, and the larger the dynamic stability index; the random variation index reflects the degree of dispersion of the peak distribution. The smaller the random variation index, the smaller the randomness of the power grid load change, the higher the predictability of the power grid load change, and the larger the dynamic stability index; the dispersion index represents the stability of the power grid load pattern. The smaller the dispersion index, the more concentrated the clusters, the better the stability of the power grid load pattern, and the larger the dynamic stability index. large; therefore, if the power stability factor is larger, the variation random index is smaller and the dispersion index is smaller, the dynamic stability index is larger; conversely, the smaller the power stability factor is, the worse the stability between current and power is, the worse the power quality of the power grid is, the worse the adaptability of the power grid is, and the smaller the dynamic stability index is; the larger the variation random index is, the greater the randomness of the power grid load change is, the lower the predictability of the power grid load change is, and the smaller the dynamic stability index is; the larger the dispersion index is, the more dispersed the clusters are, the worse the stability of the power grid load pattern is, and the smaller the dynamic stability index is; therefore, if the power stability factor is smaller, the variation random index is larger and the dispersion index is larger, the dynamic stability index is smaller.

[0078] Preferably, the schematic diagram of the dynamic stability index acquisition process provided in this embodiment is as follows: Figure 2 shown.

[0079] The energy storage control module 103 is used to analyze the average distribution of the dynamic stability index of all substations in the power grid at the current moment and determine the adaptability index of the power grid at the current moment; based on the average distribution of the power energy data of all substations at each collection moment in the power grid, combined with the adaptability index and the time series prediction model, all predicted power values ​​of the power grid at the current moment are obtained, and the alternative energy storage control system is controlled.

[0080] (1) The average value of the dynamic stability index of all substations in the power grid at the current moment is used as the adaptability index of the power grid at the current moment.

[0081] Preferably, the schematic diagram of the process of extracting the adaptability index of the power grid provided in this embodiment is as follows: Figure 3 shown.

[0082] (2) Further, in the power grid, the average value of the electric energy data of all substations at each collection time before the current time is used as the actual electric energy value at each collection time;

[0083] All actual electric energy values ​​of the power grid at the current moment are used as the input of the differential integrated moving average autoregressive ARIMA model, in which the adaptability index of the power grid is used as an exogenous variable to obtain the predicted electric energy value of the power grid.

[0084] The differential integrated moving average autoregressive model is a well-known technique, and the specific principles of its data prediction are not elaborated here. The mean of all actual power values ​​and the mean of all predicted power values ​​of the power grid at the current moment are analyzed, and the ratio of the predicted power value mean to the actual power value mean is determined. If the ratio is greater than a preset charging threshold and less than a preset discharging threshold, the alternative energy storage control system maintains its current state. If the ratio is greater than the preset discharging threshold, the alternative energy storage control system is controlled to discharge. If the ratio is less than the preset charging threshold, the alternative energy storage control system is controlled to charge. The preset discharging threshold is always greater than the preset charging threshold.

[0085] It should be noted that the values ​​of the preset discharge threshold and the preset charge threshold are both manually set. In this embodiment, the value of the preset discharge threshold is 1.2, and the value of the preset charge threshold is 0.8. The implementer can set them according to the specific situation, and this embodiment does not impose any special restrictions.

[0086] Thus, this embodiment addresses the uncertainty and prediction error issues of grid load behavior. By analyzing the impact of the uncertainty of grid load changes on the power quality in the grid, the certainty of grid load behavior prediction is improved. By analyzing the impact of the randomness of grid load changes and the stability of load patterns on the accuracy of grid demand allocation, the negative impact of the randomness of load changes on grid demand allocation is reduced, and the accuracy of resource regulation and allocation of alternative energy storage control systems is improved.

[0087] Preferably, the control process diagram of the alternative energy storage control system provided in this embodiment is as follows: Figure 4 shown.

[0088] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An alternative energy storage control system based on power grid operation optimization data analysis, characterized in that: The system comprises: The power grid data acquisition module is used to obtain all the electrical data of each substation in the power grid operation at each acquisition time within a preset time period before the current time, wherein all the electrical data are current data and electric energy data; The power grid data processing module is used to fit the binary data consisting of the current and power data of each substation at all collection moments to obtain a fitting curve. Based on the degree of disorder of all power data of each substation and the difference between all power data and the corresponding fitting value on the fitting curve, the fluctuation coefficient of each substation is determined. In addition, the power stability factor of each substation is determined by combining the correlation between different types of power data. A baseline correction algorithm is used based on various types of electrical data of each substation to obtain various types of electrical data to be studied for each substation, and fitting curves of various types of electrical data to be studied are obtained by fitting the various types of electrical data to be studied. All peak values ​​of the fitting curves of various types of electrical data are extracted, and based on the discrete degree of all peak values ​​corresponding to the acquisition time, a change random index of each substation is determined; the various types of electrical data to be studied for each substation are clustered to obtain multiple clusters, and based on the average distribution of all elements in each cluster, a dispersion index of each substation is determined, and the dynamic stability index of each substation is determined by combining the change random index and the power stability factor. The energy storage control module is used to determine the adaptability index of the power grid at the current moment based on the average distribution of the dynamic stability index of all substations in the power grid at the current moment; based on the average distribution of the power energy data of all substations in the power grid at each collection moment, combined with the adaptability index and the time series prediction model, all predicted power values ​​of the power grid at the current moment are obtained to control the alternative energy storage control system.

2. An alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The method for determining the fluctuation coefficient of each substation is: Analyze the mean square error between all the electric energy data of each substation and the corresponding fitting value on the fitting curve; Analyze the information entropy of various types of electrical data at each substation and calculate the difference in information entropy between different types of electrical data; The fluctuation coefficient of each substation is the result of the fusion of the mean square error and information entropy difference of each substation.

3. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The expression of the power stability factor of each substation is: Where A i represents the power stability factor of substation i; a i represents the correlation coefficient between all current data and all electric energy data of substation i; b i represents the fluctuation coefficient of substation i; ε represents a constant preset to be greater than 0.

4. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The method for obtaining various types of electrical data to be studied for each substation is as follows: The various types of electrical data of each substation are used as inputs of the baseline correction algorithm, and the baselines of various types of electrical data of each substation are output; All electrical data that are greater than the maximum value of the baseline in each type of electrical data are taken as the various types of electrical data to be studied for each substation.

5. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The random index of change of each substation is the average value of the discrete degree of the peak value corresponding to the collection time of all types of to-be-studied electrical data of each substation.

6. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The method for determining the dispersion index of each substation is as follows: Analyze the mean of all elements in each cluster of various types of electrical data to be studied for each substation; The product of the dispersion degree of the element mean of all clusters of various types of electrical data to be studied of each substation and the total number of clusters is analyzed, and the dispersion index of each substation is the mean of the product of all types of electrical data to be studied of each substation.

7. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 3, characterized in that: The expression of the dynamic stability index of each substation is: Where B i represents the dynamic stability index of substation i; C i represents the random index of substation i; D i represents the dispersion index of substation i; σ represents a constant preset to be greater than 0.

8. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The adaptability index of the power grid at the current moment is the average value of the dynamic stability indexes of all substations in the power grid at the current moment.

9. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The method for determining all predicted electric energy values ​​of the power grid at the current moment is: The average of the electric energy data of all substations at each collection time before the current time is used as the actual electric energy value at each collection time; All actual electric energy values ​​of the power grid at the current moment are used as the input of the time series prediction model, in which the adaptability index of the power grid is used as an exogenous variable to obtain all predicted electric energy values ​​of the power grid.

10. The alternative energy storage control system based on power grid operation optimization data analysis according to claim 1, characterized in that: The controlling of the alternative energy storage control system includes: Analyze the mean of all actual electric energy values ​​of the power grid at the current moment and the mean of all predicted electric energy values, and determine the ratio of the mean of the predicted electric energy values ​​to the mean of the actual electric energy values. If the ratio is greater than a preset charging threshold and less than a preset discharging threshold, the alternative energy storage control system maintains the current state. If the ratio is greater than the preset discharging threshold, the alternative energy storage control system discharges. If the ratio is less than the preset charging threshold, the alternative energy storage control system charges, where the preset discharging threshold is always greater than the preset charging threshold.

Images