Energy storage equipment grid-connected control method based on distributed energy storage

Abstract

The invention discloses an energy storage equipment grid-connected control method based on distributed energy storage, and relates to the field of energy storage equipment control, and the method comprises the steps: calculating an attenuation coefficient through charging data, and obtaining the charging power of energy storage equipment; predicting the generating capacity of the generating equipment according to the environmental data, and accumulating to obtain the estimated total generating capacity of the analysis interval; training a random forest model by using historical data, and obtaining estimated power consumption in combination with the power consumption data; determining the operation state of the power grid according to the estimated power consumption and the estimated total power generation amount, and classifying the energy storage equipment based on the attenuation coefficient and the existing power; according to different power grid operation states, the adjustment scheme of the energy storage equipment is customized, efficient cooperation of the energy storage equipment and the power grid is realized, stable operation of the power grid is guaranteed, and the hysteresis of power grid adjustment is reduced.

Description

Technical Field

[0001] The present invention relates to the field of energy storage device control, and specifically to a grid connection control method for energy storage devices based on distributed energy storage. Background Art

[0002] With the continuous growth of global energy demand and the increasing emphasis on environmental protection, the proportion of renewable energy in the energy field has been continuously increasing. Distributed energy sources such as solar energy and wind energy have become an important direction for energy development due to their clean and sustainable advantages. However, these distributed energy sources have the characteristics of intermittency and volatility. For example, solar energy depends on sunlight and its power generation capacity is limited at night or on cloudy days; wind energy is greatly affected by wind speed and direction, and its unstable output makes it face many challenges in large-scale grid connection, easily causing problems such as grid voltage fluctuations and frequency instability, seriously affecting the safe and stable operation of the power grid; At the same time, energy storage technology, as a key means to solve the problem of distributed energy consumption, has received extensive attention. Distributed energy storage devices can store electrical energy when energy is in excess and release electrical energy when energy is in short supply, playing a role in regulating the balance between energy supply and demand and stabilizing the operation of the power grid. However, at present, there are still the following defects in the grid connection process of energy storage devices: On the one hand, for energy storage devices of different types and different degrees of aging, their charge and discharge performances vary greatly. The existing adjustment strategies for energy storage devices are the same for charging and discharging, without considering the individual differences of different devices, which causes great damage to the energy storage devices and seriously affects the service life of the energy storage devices; On the other hand, the power generation of power generation devices and the power consumption of the target area are not predicted. When using energy storage devices to adjust the power grid, it is carried out when the power grid power supply is unbalanced, resulting in a lag in adjustment; Reducing the lag of adjustment and formulating personalized energy storage solutions are the problems we need to solve. For this reason, a grid connection control method for energy storage devices based on distributed energy storage is provided. Summary of the Invention

[0003] The purpose of the present invention is to provide a grid connection control method for energy storage devices based on distributed energy storage.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A grid connection control method for energy storage devices based on distributed energy storage, including: During the operation of the power grid, set a number of analysis intervals, obtain the power generation data and power consumption data of various types of power generation devices within the analysis intervals; use N analysis intervals as attenuation intervals, N>150, and obtain the charging data of each energy storage device within the attenuation intervals; at the same time, obtain the historical data of the target area; Analyze the charging data of each energy storage device within the attenuation interval to obtain the attenuation coefficient of each energy storage device in the corresponding attenuation interval, and based on the attenuation coefficient of the energy storage device, obtain the charging power of the energy storage device; Analyze the environmental data to obtain the predicted power generation of each type of power generation device in the analysis interval and the estimated total power generation in the analysis interval; Based on the historical data of the target area, train the random forest model to obtain a verified random forest model, and according to the electricity consumption data and the verified random forest model, obtain the estimated electricity consumption in the corresponding analysis interval; Determine the operating state of the power grid according to the estimated electricity consumption and the estimated total power generation in the analysis interval; Obtain the existing power of the energy storage device, and divide the energy storage device according to the attenuation coefficient and the existing power; Formulate the charging and discharging strategies of the energy storage device under different operating states of the power grid.

[0005] Preferably, the charging data is the charging power, the time-stored power curve, and the charging power, the time-temperature curve when the power grid charges the energy storage device; The various types of power generation devices include: solar power generation devices and wind power generation devices; The power generation data includes: wind speed, wind direction, air density, light intensity, temperature, and light direction; The electricity consumption data includes: the highest temperature, the lowest temperature, the average temperature, air humidity, whether it is a holiday, and the air quality index; The historical data is: divide the historical time according to the analysis interval to obtain a historical analysis interval, and obtain the highest temperature, the lowest temperature, the average temperature, air humidity, whether it is a holiday, the air quality index, and the electricity consumption in each historical analysis interval.

[0006] Preferably, the process of obtaining the attenuation coefficient of each energy storage device in the corresponding attenuation interval is as follows: Take the mean value of the energy storage value of the energy storage device at each charging power as the energy mean value corresponding to the charging power; Draw a curve of the energy mean value changing with the charging power as the energy curve of the energy storage device, and extract the energy experimental curve from the preset database; Calculate the Pearson correlation coefficient between the energy curve and the energy experimental curve as the power characteristic value of the energy storage device; Take the mean value of the temperature change rate of the energy storage device at each charging power as the temperature mean value corresponding to the charging power; Draw a curve of the temperature mean value changing with the charging power as the temperature curve, and extract the temperature experimental curve from the preset database; Calculate the Pearson correlation coefficient between the calculated temperature curve and the temperature experimental curve as the temperature eigenvalue of the energy storage device; Fuse the temperature eigenvalue and the power eigenvalue to obtain the attenuation coefficient of the energy storage device.

[0007] Preferably, the process of analyzing environmental data to obtain the predicted power generation of each type of power generation device in the analysis interval and the estimated total power generation in the analysis interval is as follows: Obtain the predicted power generation of each wind turbine according to the wind speed, wind direction, and air density; Obtain the predicted power generation of each solar power generation device according to the light intensity, temperature, and light direction; Accumulate the predicted power generation of all power generation devices, and use the obtained result as the estimated total power generation in the analysis interval.

[0008] Preferably, the process of obtaining the estimated power consumption corresponding to the analysis interval is as follows: Preprocess the historical data to obtain the cleaned data, and divide the cleaned data into a training set and a validation set; Initialize the random forest model, and use the training set to train the random forest model to obtain a pre-used model; Use the validation set to validate the pre-used model. If the validation passes, obtain the validated random forest model; if the validation fails, continue to use the training set to train the random forest model until the validation passes; Input the power consumption data into the validated random forest model to obtain the estimated power consumption corresponding to the analysis interval.

[0009] Preferably, the process of determining the operating state of the power grid according to the estimated power consumption and the estimated total power generation in the analysis interval is as follows: The operating state of the power grid includes: over-power state, power shortage state, and balanced state; If the estimated power consumption > the estimated total power generation, determine that the operating state of the power grid is the power shortage state and obtain the power shortage amount; If the estimated power consumption < the estimated total power generation, determine that the operating state of the power grid is the over-power state and obtain the over-power amount; If the estimated power consumption = the estimated total power generation, determine that the operating state of the power grid is the balanced state.

[0010] Preferably, the process of classifying the energy storage device according to the attenuation coefficient and the existing power is as follows: Obtain the actual storage capacity of the energy storage device according to the attenuation coefficient and the rated storage capacity of the energy storage device; Obtain the storage percentage according to the existing power and the actual storage capacity; Preset a power threshold, and classify the storage device according to the power threshold and the storage percentage.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention processes historical data to obtain a verified random forest model, combines power consumption data to obtain an estimated power consumption, and analyzes environmental data to obtain an estimated total power generation; determines the grid operation state based on the magnitude relationship between the estimated power consumption and the estimated total power generation; classifies energy storage devices using an attenuation coefficient and the existing power, and obtains a charging priority value and a discharging priority value, thereby determining the adjustment strategies of each energy storage device under different grid operation states and reducing the hysteresis of grid regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0013] Figure 1 It is the schematic diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] As Figure 1 shown, a grid connection control method for energy storage devices based on distributed energy storage includes: During the operation of the grid, set several analysis intervals, and obtain the power generation data and power consumption data of each type of power generation device within the analysis intervals; use N analysis intervals as attenuation intervals, where N>150, and obtain the charging data of each energy storage device within the attenuation intervals; at the same time, obtain the historical data of the target area; The charging data is the charging power, time-stored power curve, and charging power, time-temperature curve when the grid charges the energy storage device; Each type of power generation device includes: a solar power generation device and a wind power generation device; The power generation data includes: wind speed, wind direction, air density, light intensity, temperature, and light direction; The power consumption data includes: the highest temperature, the lowest temperature, the average temperature, air humidity, whether it is a holiday, and the air quality index; The historical data is: divide the historical time according to the analysis intervals to obtain historical analysis intervals, and obtain the highest temperature, the lowest temperature, the average temperature, air humidity, whether it is a holiday, the air quality index, and the power consumption on each historical analysis interval; Specifically, the analysis interval is enclosed by two adjacent analysis nodes. The selection of the analysis nodes is carried out according to the 24-hour system, with the whole hour selected as the analysis node, and the time length between adjacent analysis nodes remains the same. For example, if four analysis nodes are selected every day, 3 o'clock, 9 o'clock, 15 o'clock, and 21 o'clock can be chosen, and the corresponding analysis intervals are [3, 9], [9, 15], [15, 21], [21, 3].

[0015] Analyze the charging data of each energy storage device in the attenuation interval to obtain the attenuation coefficient of each energy storage device in the corresponding attenuation interval. Based on the attenuation coefficient of the energy storage device, obtain the charging power of the energy storage device; Take the average value of the energy storage values of the energy storage device at each charging power as the energy average value corresponding to the charging power; Specifically, the energy storage value at a certain charging power represents the degree of change in the electricity stored by the energy storage device per unit time. When the power grid charges the energy storage device, the power of each charge may be different, and the power received by different energy storage devices is also different. Therefore, the impact on the energy storage device is also different. Under normal circumstances, as the efficiency of the energy storage device decays, at the same charging power, the energy storage value will also continuously decay. Therefore, the energy storage value can be used to evaluate the aging degree of an energy storage device; Specifically, calculate the energy storage value according to the charging power and the time-electricity storage curve. Energy storage value = growth value of electricity stored within time t / t; Draw a curve of the energy average value changing with the charging power as the energy curve of the energy storage device, and extract the energy experimental curve from the preset database; Specifically, the energy experimental curve refers to the curve of the energy average value of a functional intact energy storage device that has not been used changing with the charging power; Calculate the Pearson correlation coefficient between the energy curve and the energy experimental curve as the power characteristic value of the energy storage device; Take the average value of the temperature change rate of the energy storage device at each charging power as the temperature average value corresponding to the charging power; Specifically, the temperature change rate at a certain charging power represents the degree of change in the temperature of the energy storage device per unit time when the power grid charges the energy storage device at the corresponding power; as the aging degree of the energy storage device increases, at the same charging power, the temperature change rate will also show an upward trend; Draw a curve of the temperature average value changing with the charging power as the temperature curve, and extract the temperature experimental curve from the preset database; Specifically, the temperature experimental curve refers to the curve of the temperature average value of a functional intact energy storage device that has not been used changing with the charging power; Calculate the Pearson correlation coefficient between the temperature curve and the temperature experimental curve as the temperature characteristic value of the energy storage device; Fuse the temperature eigenvalue and the power eigenvalue to obtain the attenuation coefficient of the energy storage device; Specifically, the fusion process refers to a data processing method used to combine two-dimensional data into one data to obtain more representative data and avoid the contingency caused by single data; Specifically, different weight influence factors can be set for the temperature eigenvalue and the power eigenvalue, and they are fused through a weighted processing method to obtain the attenuation coefficient; Specifically, according to the formula: ; The charging power corresponding to each energy storage device is obtained, where represents the charging power, represents the initial charging power of the energy storage device, A represents the attenuation coefficient, and m and n are parameters obtained by experimental fitting; Specifically, the attenuation coefficient obtained from the charging data within an attenuation interval is used as the attenuation coefficient for the next attenuation interval.

[0016] Analyze the environmental data to obtain the predicted power generation of each type of power generation device in the analysis interval and the estimated total power generation in the analysis interval; According to the wind speed 、wind direction and air density , the predicted power generation of each wind turbine is obtained ; where: ; Among them, represents the swept area of the wind turbine, represents the wind energy utilization coefficient, represents the time length of the analysis interval, represents the angle formed by the wind direction and the fan blades of the wind turbine; According to the light intensity 、temperature and the light direction, the predicted power generation of each solar power generation device is obtained , where: ; Among them, represents the light energy conversion efficiency of the solar power generation device, represents the temperature coefficient of the solar power generation device, represents the standard test temperature, which is a constant, represents the swept area of the solar device, is the angle according to the solar device and the light ray defense line, represents the time length of the analysis interval; Accumulate the predicted power generation of all power generation equipment, and use the obtained result as the estimated total power generation in the analysis interval.

[0017] Based on the historical data of the target area, train the random forest model to obtain a verified random forest model. According to the electricity consumption data and the verified random forest model, obtain the estimated electricity consumption in the corresponding analysis interval. Preprocess the historical data to obtain cleaned data, and divide the cleaned data into a training set and a validation set. Specifically, the preprocessing includes duplicate removal and data standardization. Duplicate removal means removing duplicate data in the historical data and only keeping one. Data standardization means unifying the data format. Specifically, the cleaned data can be divided according to 8:2, and the group with a proportion of 8 is used as the training set. Initialize the random forest model, and use the training set to train the random forest model to obtain a pre-used model. Use the validation set to verify the pre-used model. If the verification passes, obtain the verified random forest model; if the verification fails, continue to use the training set to train the random forest model until the verification passes. Specifically, verify the pre-used model by calculating the evaluation coefficients of the verified random forest model and comparing them with thresholds. Specifically, the evaluation coefficients include the mean squared error and the coefficient of determination. Thresholds for the mean squared error and the coefficient of determination can be set. Only when the mean squared error is less than the mean squared error threshold and the coefficient of determination is greater than the absolute coefficient threshold, it is determined that the verification passes. Input the electricity consumption data into the verified random forest model to obtain the estimated electricity consumption in the corresponding analysis interval.

[0018] Determine the operating state of the power grid according to the estimated electricity consumption and the estimated total power generation in the analysis interval. The operating state of the power grid includes: over-power state, power shortage state, and balanced state. If the estimated electricity consumption > the estimated total power generation, determine that the operating state of the power grid is the power shortage state, and obtain the power shortage amount. Specifically, the power shortage amount = the estimated electricity consumption - the estimated total power generation. If the estimated electricity consumption < the estimated total power generation, determine that the operating state of the power grid is the over-power state, and obtain the over-power amount. Specifically, the over-power amount = the estimated total power generation - the estimated electricity consumption. If the estimated electricity consumption = the estimated total power generation, determine that the operating state of the power grid is the balanced state.

[0019] Obtain the existing electricity of the energy storage device, and classify the energy storage device according to the attenuation coefficient and the existing electricity. Obtain the actual storage capacity of the energy storage device based on the attenuation coefficient and the rated storage capacity of the energy storage device; Specifically, the actual storage capacity = rated storage capacity * attenuation coefficient; Based on the existing power and the actual storage capacity, obtain the storage percentage, Specifically, divide the existing power by the actual storage capacity to obtain the storage percentage; Preset a power threshold, and classify the energy storage device according to the power threshold and the storage percentage; Specifically, the power threshold includes an upper power limit value and a lower power limit value; if the storage percentage is greater than the upper power limit value, mark the energy storage device as an output device; if the storage percentage is less than the lower power limit value, mark the energy storage device as an input device; if the storage percentage is between the lower power limit value and the upper power limit value, mark the energy storage device as a conversion device.

[0020] Formulate the charge and discharge strategies of the energy storage device under different operating states of the power grid; Under the overcharged state: classify according to whether the number of input devices is 0: S1: If the number of input devices is not 0, multiply the charging power of the input device by the time length of the analysis interval to obtain the charging amount corresponding to the input device, accumulate the charging amounts of all input devices to obtain the missing value power, compare the missing value power with the overcharged power, and perform classification processing according to the comparison result: S101: If the overcharged power > missing value power, then according to the attenuation coefficient of the conversion device and the existing power obtain the charging priority value , where: where, and are the weight influence factors corresponding to the attenuation coefficient and the existing power respectively; Multiply the charging power of the conversion device by the time length of the analysis interval to obtain the charging amount of the conversion device; accumulate the charging amounts of the conversion devices one by one in descending order according to the charging priority value. When the accumulated result is greater than or equal to the value of (overcharged power - missing value power) for the first time, stop the accumulation, and mark all the conversion devices and all the input devices currently undergoing the accumulation calculation as charging devices, and charge the charging devices according to their corresponding charging powers; S102: If the overcharged power < missing value power, then further divide according to whether the number of output devices is 0; S102-1: If the number of output devices is 0, calculate the charging priority value of each input device according to the attenuation value and the existing power of the input device, add the charging amounts of each input device one by one in descending order of the charging priority value. When the added result is greater than or equal to the overcharge amount for the first time, stop adding, mark all input devices participating in the addition calculation as charging devices, and charge the charging devices according to their corresponding charging powers; S102-2: If the number of output devices is not 0, then according to the attenuation coefficient of the output device , the existing power of the output device and the shortage difference , obtain the output power of the output device ; Shortage difference = shortage power - overcharge amount; ; Among them, and are respectively the weight influence factors corresponding to the existing power and the attenuation coefficient ; Multiply the output power of the output device by the time length of the analysis interval to obtain the output amount of the output device; accumulate the output amounts of each output device to obtain the available output amount, compare the available output amount with the shortage difference, and perform classification processing according to the comparison result: If the available output amount is less than the shortage difference, add the overcharge amount and the available output amount, and use the obtained result as the updated overcharge amount, then charge the input device according to step S102-1; If the available output amount is greater than the shortage difference, accumulate the charging amounts of each output device one by one. When the accumulated result is greater than or equal to the shortage difference for the first time, mark the output device participating in the accumulation calculation as the estimated output device, transmit power to the power grid by the estimated output device according to its corresponding output power, and charge all input devices according to their corresponding charging powers at the same time; If the available output amount is equal to the shortage difference, charge all output devices to the power grid according to their corresponding output powers, and charge all input devices according to their corresponding charging powers at the same time; S103: If the overcharge amount = the shortage power, charge all input devices according to their corresponding charging powers; S2: If the number of input devices is 0, calculate the power demand in the analysis interval. If the power demand is less than the excess power, charge all conversion devices according to their corresponding charging powers; if the power demand is greater than or equal to the excess power, calculate the charging priorities of the conversion devices, and accumulate the charging amounts of the conversion devices in descending order of their priorities. When the accumulated result first exceeds the excess power, mark the conversion devices participating in the accumulation calculation as charging devices and charge the charging devices according to their corresponding charging powers. Specifically, the power demand refers to the sum of the charging amounts of all conversion devices. Under the power shortage state: classify according to whether the number of output devices is 0. D1: If the number of output devices is not 0, calculate the discharge power of each output device according to the attenuation coefficient , the power shortage , and the existing power , where: ; Among them, and represent the weight influence factors of the existing power and the attenuation coefficient respectively; According to the discharge power of each output device , obtain the discharge amounts of each output device, accumulate the discharge amounts of each output device, obtain the estimated discharge value, and further divide according to the comparison result between the estimated discharge value and the power shortage: D101: If the estimated discharge amount > the power shortage, calculate the discharge priority value of each output device, accumulate the discharge amounts of the output devices in descending order of the discharge priority value. When the accumulated result first exceeds the discharge difference, mark all the output devices participating in the accumulation as discharge devices and charge the power grid with the corresponding discharge power of the discharge devices; Specifically, the discharge priority value is the reciprocal of the charging priority value; the discharge difference = the estimated discharge amount - the power shortage; D102: If the estimated discharge amount < the power shortage, calculate the discharge priority value of each conversion device and the discharge power of each conversion device , and according to the discharge power of each conversion device , obtain the discharge amounts of each conversion device, accumulate the discharge amounts of each conversion device in descending order of the discharge priority value of each conversion device. When the accumulated result first exceeds the discharge gap , mark all the conversion devices participating in the accumulation and all the output devices as discharge devices and charge the power grid with the corresponding discharge power of the discharge devices; Specifically, ; Specifically, the discharge gap = the amount of power shortage - the estimated discharge amount; D103: The estimated discharge amount = the amount of power shortage; Charge the power grid with each output device according to the discharge power; D2: If the number of output devices is 0, calculate the discharge amounts of each conversion device and accumulate them; If the accumulated result value is greater than or equal to the amount of power shortage, accumulate the discharge amounts of each conversion device one by one in descending order according to the discharge priority value of each conversion device. When the accumulated result first exceeds the amount of power shortage, mark all the conversion devices participating in the accumulation as discharge devices, and charge the power grid with the discharge devices according to the corresponding discharge power; If the accumulated result is less than the amount of power shortage, charge the power grid with all the conversion devices according to the corresponding power; Under the balanced state: All energy storage devices do not perform any discharge and charge operations.

[0021] As described above, it is only a preferred embodiment of the present invention and does not impose any formal restrictions on the present invention. Although the present invention has been disclosed above with the preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments with equivalent changes within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any modification or equivalent replacement made to the above embodiments based on the technical essence of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A grid-connected control method for energy storage devices based on distributed energy storage, characterized in that, Including: During the operation of the power grid, several analysis intervals are set, and the power generation data and power consumption data of various types of power generation equipment within the analysis intervals are obtained; N analysis intervals are used as attenuation intervals, where N > 150, and the charging data of each energy storage device within the attenuation intervals is obtained; meanwhile, the historical data of the target area is obtained; Analyze the charging data of each energy storage device within the attenuation intervals to obtain the attenuation coefficient of each energy storage device in the corresponding attenuation interval, and based on the attenuation coefficient of the energy storage device, obtain the charging power of the energy storage device; Analyze the environmental data to obtain the predicted power generation of various types of power generation equipment in the analysis intervals and the estimated total power generation in the analysis intervals; Based on the historical data of the target area, train the random forest model to obtain a verified random forest model, and according to the power consumption data and the verified random forest model, obtain the estimated power consumption in the corresponding analysis intervals; Determine the operating state of the power grid according to the estimated power consumption and the estimated total power generation in the analysis intervals; Obtain the existing power of the energy storage device, and divide the energy storage device according to the attenuation coefficient and the existing power; Formulate the charge and discharge strategies of the energy storage device under different operating states of the power grid.

2. The grid connection control method of an energy storage device based on distributed energy storage according to claim 1, characterized in that, The charging data is the charging power, time-stored power curve, and charging power, time-temperature curve when the power grid charges the energy storage device; The various types of power generation equipment include: solar power generation equipment and wind power generation equipment; The power generation data includes: wind speed, wind direction, air density, light intensity, temperature, and light direction; The power consumption data includes: maximum temperature, minimum temperature, average temperature, air humidity, whether it is a holiday, and air quality index; The historical data is: divide the historical time according to the analysis intervals to obtain historical analysis intervals, and obtain the maximum temperature, minimum temperature, average temperature, air humidity, whether it is a holiday, air quality index, and power consumption on each historical analysis interval.

3. A grid connection control method for an energy storage device based on distributed energy storage according to claim 2, characterized in that, The process of obtaining the attenuation coefficient of each energy storage device in the corresponding attenuation interval is: Take the average value of the energy storage values of the energy storage device at each charging power as the energy average value corresponding to the charging power; Draw a curve of the energy average value changing with the charging power as the energy curve of the energy storage device, and extract the energy experimental curve from a preset database; Calculate the Pearson correlation coefficient between the energy curve and the energy experimental curve as the power characteristic value of the energy storage device; Take the average value of the temperature change rate of the energy storage device at each charging power as the temperature average value corresponding to the charging power; Draw a curve of the temperature average value changing with the charging power as the temperature curve, and extract the temperature experimental curve from a preset database; Calculate the Pearson correlation coefficient between the temperature curve and the temperature experimental curve as the temperature characteristic value of the energy storage device; Perform fusion processing on the temperature characteristic value and the power characteristic value to obtain the attenuation coefficient of the energy storage device.

4. A grid connection control method for an energy storage device based on distributed energy storage according to claim 3, characterized in that, The process of analyzing the environmental data to obtain the predicted power generation of various types of power generation equipment in the analysis intervals and the estimated total power generation in the analysis intervals is: Obtain the predicted power generation of each wind turbine according to the wind speed, wind direction, and air density; Obtain the predicted power generation of each solar power generation device according to the light intensity, temperature, and light direction; Accumulate the predicted power generation of all power generation equipment, and use the obtained result as the estimated total power generation for the analysis interval.

5. A grid connection control method for an energy storage device based on distributed energy storage according to claim 4, characterized in that, The process of obtaining the estimated power consumption for the corresponding analysis interval is as follows: Preprocess the historical data to obtain cleaned data, and divide the cleaned data into a training set and a validation set; Initialize the random forest model, and use the training set to train the random forest model to obtain a pre-used model; Use the validation set to validate the pre-used model. If the validation passes, obtain the validated random forest model; if the validation fails, continue to use the training set to train the random forest model until the validation passes; Input the power consumption data into the validated random forest model to obtain the estimated power consumption for the corresponding analysis interval.

6. The grid connection control method of an energy storage device based on distributed energy storage according to claim 5, wherein, The process of determining the operating state of the power grid based on the estimated power consumption and the estimated total power generation for the analysis interval is as follows: The operating state of the power grid includes: over-power state, power shortage state, and balanced state; If the estimated power consumption > the estimated total power generation, determine that the operating state of the power grid is a power shortage state and obtain the power shortage amount; If the estimated power consumption < the estimated total power generation, determine that the operating state of the power grid is an over-power state and obtain the over-power amount; If the estimated power consumption = the estimated total power generation, determine that the operating state of the power grid is a balanced state.

7. A grid connection control method for an energy storage device based on distributed energy storage according to claim 6, characterized in that, The process of classifying energy storage devices according to the attenuation coefficient and the existing power is as follows: Obtain the actual storage capacity of the energy storage device according to the attenuation coefficient and the rated storage capacity of the energy storage device; Obtain the storage percentage according to the existing power and the actual storage capacity; Preset a power threshold, and classify the storage device according to the power threshold and the storage percentage.

Images