Energy storage system load prediction method

Abstract

The invention relates to an energy storage system load prediction method, and the method comprises the steps: generating a sample time-power curve based on sample operation time information and sample operation power information in sample operation data; marking the sample time-power curve according to the sample operation weather information so as to obtain a sample time-power curve marked for the first time, and marking the sample time-power curve marked for the first time according to the sample operation temperature information so as to obtain a sample time-power curve marked for the second time; and finally, marking the sample time-power curve marked for the second time by using the sample operation humidity information so as to obtain a sample time-power curve marked for the third time, and combining the influence of different operation information on the sample time-power curve so as to obtain the influence of the different operation information on the power supply quantity in the sample data. And an electric quantity demand prediction model is constructed.

Description

Technical Field

[0001] The present application relates to the field of energy storage technology, and in particular to a method for load prediction of an energy storage system. Background Art

[0002] Under the current background of power system transformation and with the widespread popularization of renewable energy, the operating characteristics of the power system have changed significantly, especially the intensification of peak-valley price differences, which has provided strong impetus for the development of industrial and commercial energy storage.

[0003] However, this development has also brought new challenges. In the context of a two-part electricity price, industrial and commercial energy storage systems face the problem of supply and demand imbalance in the process of achieving peak shaving and valley filling due to the uncertainty and volatility of the load, which may trigger a situation where the maximum demand exceeds the maximum demand. Summary of the invention

[0004] Based on this, it is necessary to provide a load forecasting method for energy storage systems to address the problem of unbalanced supply and demand in traditional energy storage systems during the discharge process.

[0005] The present application provides a method for predicting load of an energy storage system, comprising: Acquire sample data of a plurality of samples, wherein the sample data includes sample operation data; Parse the sample operation data to obtain the sample operation time information, sample operation power information, sample operation weather information, sample operation temperature information, and sample operation humidity information in the sample operation data; Generate a sample time-power curve for each sample data based on the sample operation time information and the sample operation power information for each sample data; Marking a sample time-power curve of each sample data based on sample operating weather information of each sample data to obtain a sample time-power curve of each sample data after the first marking; Marking the sample time-power curve after the first marking of each sample data based on the sample operating temperature information of each sample data to obtain the sample time-power curve after the second marking of each sample data; Marking the sample time-power curve after the second marking of each sample data based on the sample running humidity information of each sample data, to obtain the sample time-power curve after the third marking of each sample data; A power demand prediction model is constructed based on each sample running time information, each sample running power information, each sample running weather information, each sample running temperature information, each sample running humidity information, each sample time-power curve after the first marking, each sample time-power curve after the second marking, and each sample time-power curve after the third marking; Get a sample data to be tested; Parsing the sample data to be tested to obtain the running time information of the sample to be tested, the running power information of the sample to be tested, the running weather information of the sample to be tested, the running temperature information of the sample to be tested, and the running humidity information of the sample to be tested in the sample data to be tested; The obtained running time information of the samples to be tested, the running power information of the samples to be tested, the running weather information of the samples to be tested, the running temperature information of the samples to be tested, and the running humidity information of the samples to be tested are input into the power demand prediction model, the power demand prediction model is started, and the predicted power demand output by the power demand prediction model is obtained.

[0006] The present application relates to a method for load prediction of an energy storage system, which generates a sample time-power curve based on sample operation time information and sample operation power information in sample operation data, then marks the sample time-power curve with sample operation weather information to obtain the sample time-power curve after the first marking, then marks the sample time-power curve after the first marking with sample operation temperature information to obtain the sample time-power curve after the second marking, and finally marks the sample time-power curve after the second marking with sample operation humidity information to obtain the sample time-power curve after the third marking, combines the influence of different operation information on the sample time-power curve to obtain the influence of different operation information on the power supply in the sample data, and then constructs an electricity demand prediction model, and performs a large amount of data training on the electricity demand prediction model so that the electricity demand prediction model has the function of predicting the required electricity. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A flow chart of a method for predicting energy storage system load provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0009] like Figure 1 As shown, in one embodiment of the present application, the energy storage system load prediction method includes the following S001 to S010: S001, obtaining sample data of a plurality of samples, wherein the sample data includes sample operation data.

[0010] Specifically, the sample operation data refers to the data of the energy storage system during the historical discharge process.

[0011] S002, parsing the sample operation data to obtain the sample operation time information, sample operation power information, sample operation weather information, sample operation temperature information, and sample operation humidity information in the sample operation data.

[0012] S003 , generating a sample time-power curve for each sample data based on the sample operation time information and the sample operation power information of each sample data.

[0013] Specifically, the sample time-power curve may refer to a curve showing the power variation of the energy storage system during operation within a unit time, and the unit time may be in units of hours, days, weeks, etc. The area enclosed by the curve and the time axis in the sample time-power curve is the amount of electricity output by the energy storage system.

[0014] S004, marking the sample time-power curve of each sample data based on the sample operating weather information of each sample data, to obtain the sample time-power curve of each sample data after the first marking.

[0015] S005 , marking the sample time-power curve after the first marking of each sample data based on the sample operating temperature information of each sample data, to obtain the sample time-power curve after the second marking of each sample data.

[0016] S006, marking the sample time-power curve after the second marking of each sample data based on the sample running humidity information of each sample data, to obtain the sample time-power curve after the third marking of each sample data.

[0017] S007, build a power demand prediction model based on each sample operation time information, each sample operation power information, each sample operation weather information, each sample operation temperature information, each sample operation humidity information, each sample time-power curve after the first marking, each sample time-power curve after the second marking, and each sample time-power curve after the third marking.

[0018] S008, obtaining a sample data to be tested.

[0019] S009, parse the sample data to be tested, and obtain the running time information of the sample to be tested, the running power information of the sample to be tested, the running weather information of the sample to be tested, the running temperature information of the sample to be tested, and the running humidity information of the sample to be tested.

[0020] S010, input the obtained running time information of the sample to be tested, the running power information of the sample to be tested, the running weather information of the sample to be tested, the running temperature information of the sample to be tested, and the running humidity information of the sample to be tested into the power demand prediction model, start the power demand prediction model, and obtain the predicted power demand output by the power demand prediction model.

[0021] In this embodiment, a sample time-power curve is first generated based on the sample operation time information and the sample operation power information in the sample operation data, and then the sample time-power curve is marked with the sample operation weather information to obtain the sample time-power curve after the first marking, and then the sample time-power curve after the first marking is marked with the sample operation temperature information to obtain the sample time-power curve after the second marking, and finally the sample time-power curve after the second marking is marked with the sample operation humidity information to obtain the sample time-power curve after the third marking, and the influence of different operation information on the sample time-power curve is combined to obtain the influence of different operation information on the power supply in the sample data, and then a power demand prediction model is constructed, and a large amount of data training is performed on the power demand prediction model so that the power demand prediction model has the function of predicting the required power.

[0022] In one embodiment of the present application, the sample time-power curve of each sample data is generated based on the sample operation time information and the sample operation power information of each sample data, including the following S003a to S003e: S003a, select a sample running data.

[0023] S003b, obtaining sample operation time information and sample operation power information in the sample operation data.

[0024] S003c, create a two-dimensional coordinate system.

[0025] S003d, based on the sample operation time information, the sample operation power information is incorporated into a two-dimensional coordinate system to obtain a sample time-power curve.

[0026] S003e, returning to the step of selecting a sample running data until each sample running data has been selected once.

[0027] Specifically, a two-dimensional coordinate system is created with time as the unit of one coordinate axis and power as the unit of another coordinate axis.

[0028] In this embodiment, the power information corresponding to different moments in the sample operation data is correspondingly incorporated into a two-dimensional coordinate system to obtain a sample time-power curve. In the sample time-power curve, the area of ​​the figure enclosed by the curve and the time coordinate axis is the power value within that period of time, or a shorter period of time.

[0029] In one embodiment of the present application, the sample time-power curve of each sample data is marked based on the sample operating weather information of each sample data to obtain the sample time-power curve of each sample data after the first marking, including the following S004a to S004e: S004a, select a sample running data.

[0030] S004b, obtaining a sample time-power curve in the sample operation data.

[0031] S004c, obtaining sample operation weather information in the sample operation data, wherein the sample operation weather information includes multiple weather types, and the weather types include sunny, cloudy, overcast, light rain, moderate rain and heavy rain.

[0032] S004d, marking the sample time-power curve based on each weather type and the time period corresponding to each weather type, to obtain the sample time-power curve after the first marking.

[0033] S004e, returning to the step of selecting a sample running data until each sample running data has been selected once.

[0034] Specifically, the sample time-power curve is marked based on each weather type and the time period corresponding to each weather type, and the sample time-power curve after the first marking includes: Select a weather type; Parse the weather type and obtain all time intervals corresponding to the weather type; Mark the curve segments corresponding to all time intervals in the sample time-power curve as the weather type; Return to selecting a weather type until each weather type has been selected once.

[0035] In this embodiment, the time intervals of different weather types are obtained, and the corresponding time intervals are mapped to the sample time-power curve of the corresponding time, thereby obtaining multiple sample time-power curves of the weather type, so as to distinguish different weather types to increase the accuracy of the discharge prediction.

[0036] In one embodiment of the present application, the sample time-power curve of each sample data is marked based on the sample operating weather information of each sample data to obtain the sample time-power curve of each sample data after the first marking, and then further includes the following S004f to S004l: S004f, select a weather type.

[0037] S004g, parsing the weather type to obtain at least one sample time-power curve after the first marking in the weather type.

[0038] S004h, select a sample time-power curve after the first marking.

[0039] S004i, parsing the sample time-power curve after the first marking to obtain an actual power supply value in the sample time-power curve after the first marking.

[0040] S004j, returning to the step of selecting a sample time-power curve after the first marking, until each sample time-power curve after the first marking has been selected once, to obtain a plurality of actual power supply values.

[0041] S004k, taking the largest actual power supply value among the multiple actual power supply values ​​obtained as the maximum boundary value of the first prediction range; taking the smallest actual power supply value among the multiple actual power supply values ​​obtained as the minimum boundary value of the first prediction range, to obtain the first prediction range.

[0042] S0041, return to select a weather type, until each weather type has been selected once.

[0043] Specifically, the actual power supply value in the sample time-power curve after the first marking refers to the power value of at least one unit time contained in a multi-segment curve of a weather type in the sample time-power curve after the first marking, and each curve contains at least one unit time.

[0044] In this embodiment, by counting the actual power supply of the same weather type within a unit time, the range of actual power supply values ​​that appear within a unit time under the conditions of the weather type is obtained. This is used as the underlying logic to calculate the range of actual power supply values ​​for different weather types, and the actual power supply values ​​within a unit time corresponding to different weather types are obtained.

[0045] In one embodiment of the present application, the step of marking the sample time-power curve after the first marking of each sample data based on the sample operating temperature information of each sample data to obtain the sample time-power curve after the second marking of each sample data includes the following S005a to S005e: S005a, select a sample running data.

[0046] S005b, obtaining a sample time-power curve after the first marking in the sample operation data.

[0047] S005c, obtaining sample operation temperature information in the sample operation data, where the sample operation temperature information includes at least one temperature value.

[0048] S005d, marking the sample time-power curve after the first marking based on all temperature values ​​in the sample operation temperature information, to obtain the sample time-power curve after the second marking.

[0049] S005e, returning to the step of selecting a sample running data until each sample running data has been selected once.

[0050] Specifically, the sample time-power curve after the first marking is marked based on all temperature values ​​in the sample operating temperature information, and the sample time-power curve after the second marking is obtained includes: Select a temperature value; Analyze the temperature value to obtain all time intervals corresponding to the temperature value; Mark the curve segments corresponding to all time intervals in the sample time-power curve as the temperature value; Return to selecting a temperature value until each temperature value has been selected once.

[0051] In this embodiment, the time intervals of different temperature values ​​are obtained, and the corresponding time intervals are mapped to the sample time-power curve of the corresponding time, thereby obtaining multiple sample time-power curves of the temperature value, so that different temperature values ​​can be used as a distinction to further increase the accuracy of the discharge amount prediction.

[0052] In one embodiment of the present application, the sample time-power curve after the first marking of each sample data is marked based on the sample operating temperature information of each sample data to obtain the sample time-power curve after the second marking of each sample data, and then further includes the following S005f to S005l: S005f, select a temperature value.

[0053] S005g, analyzing the temperature value to obtain at least one sample time-power curve of the temperature value after the second marking.

[0054] S005h, selecting a sample time-power curve after the second marking.

[0055] S005i, analyzing the sample time-power curve after the second marking to obtain an actual power supply value in the sample time-power curve after the second marking.

[0056] S005j, returning to the step of selecting a sample time-power curve after the second marking, until each sample time-power curve after the second marking has been selected once, to obtain a plurality of actual power supply values.

[0057] S005k, taking the largest actual power supply value among the multiple actual power supply values ​​obtained as the maximum boundary value of the second prediction range; taking the smallest actual power supply value among the multiple actual power supply values ​​obtained as the minimum boundary value of the second prediction range, to obtain the second prediction range.

[0058] S0051, return to select a temperature value until each temperature value has been selected once.

[0059] Specifically, the actual power supply value in the sample time-power curve after the second marking refers to the power value of at least one unit time contained in a multi-segment curve of a temperature value in the sample time-power curve after the second marking, and each segment of the curve contains at least one unit time.

[0060] In this embodiment, by counting the actual power supply of the same temperature value per unit time, the range of actual power supply values ​​that appear per unit time under the condition of the temperature value is obtained. This is used as the underlying logic to calculate the range of actual power supply values ​​for different temperature values, and the actual power supply values ​​per unit time corresponding to different temperature values ​​are obtained.

[0061] In one embodiment of the present application, the sample time-power curve after the second marking of each sample data is marked based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data, including the following S006a to S006e: S006a, select a sample running data; S006b, obtaining a sample time-power curve after the second marking in the sample operation data; S006c, obtaining sample operation humidity information in the sample operation data, wherein the sample operation humidity information includes at least a humidity value; S006d, marking the sample time-power curve after the second marking based on all humidity values ​​in the sample running humidity information, to obtain the sample time-power curve after the third marking; S006e, returning to the step of selecting a sample running data until each sample running data has been selected once.

[0062] Specifically, the sample time-power curve after the second marking is marked based on all humidity values ​​in the sample running humidity information, and the sample time-power curve after the third marking is obtained, including: Select a humidity value; Analyze the humidity value to obtain all time intervals corresponding to the humidity value; Mark the curve segments corresponding to all time intervals in the sample time-power curve as the humidity value; Return to selecting a humidity value until each humidity value has been selected once.

[0063] In this embodiment, the time intervals of different humidity values ​​are obtained, and the corresponding time intervals are mapped to the sample time-power curve of the corresponding time, thereby obtaining multiple sample time-power curves of the humidity value, so that different humidity values ​​can be used as a distinction to further increase the accuracy of the discharge prediction.

[0064] In one embodiment of the present application, the sample time-power curve after the second marking of each sample data is marked based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data, and then further includes the following S006f to S006l: S006f, select a humidity value.

[0065] S006g, analyzing the humidity value to obtain at least one sample time-power curve of the humidity value after the third marking.

[0066] S006h, selecting a sample time-power curve after the third marking.

[0067] S006i, analyzing the sample time-power curve after the third marking to obtain an actual power supply value in the sample time-power curve after the third marking.

[0068] S006j, returning to the step of selecting a sample time-power curve after the third marking, until each sample time-power curve after the third marking has been selected once, to obtain a plurality of actual power supply values.

[0069] S006k, taking the largest actual power supply value among the multiple actual power supply values ​​obtained as the maximum boundary value of the third prediction range; taking the smallest actual power supply value among the multiple actual power supply values ​​obtained as the minimum boundary value of the third prediction range, to obtain the third prediction range.

[0070] S0061, return to select a humidity value until each humidity value has been selected once.

[0071] Specifically, the actual power supply value in the sample time-power curve after the second marking refers to the power value of at least one unit time contained in a multi-segment curve of a humidity value in the sample time-power curve after the second marking, and each segment of the curve contains at least one unit time.

[0072] In this embodiment, by counting the actual power supply of the same humidity value per unit time, the range of actual power supply values ​​that appear per unit time under the condition of the humidity value is obtained. This is used as the underlying logic to calculate the range of actual power supply values ​​for different humidity values, and the actual power supply values ​​per unit time corresponding to different humidity values ​​are obtained.

[0073] In one embodiment of the present application, the sample time-power curve after the second marking of each sample data is marked based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data, and then further includes the following S016 to S116: S016, determining whether the first prediction range and the second prediction range have an intersection.

[0074] S026: If the first prediction range and the second prediction range have an intersection, determine whether the intersection of the first prediction range and the second prediction range has an intersection with the third prediction range.

[0075] S036: If the intersection of the first prediction range and the second prediction range intersects with the third prediction range, the average value of the intersection of the first prediction range and the second prediction range and the intersection of the third prediction range is calculated, and the obtained average value is used as the target required power.

[0076] S046: If the intersection of the first prediction range and the second prediction range does not intersect with the third prediction range, then the average value between the average value of the intersection of the first prediction range and the second prediction range and the average value of the third prediction range is calculated, and the obtained average value is used as the target demand power.

[0077] S056: If there is no intersection between the first prediction range and the second prediction range, determine whether there is an intersection between the first prediction range and the third prediction range.

[0078] S066: If the first prediction range and the third prediction range have an intersection, determine whether the second prediction range and the third prediction range have an intersection.

[0079] S076: If the second prediction range and the third prediction range have an intersection, then the average value of the intersection of the first prediction range and the third prediction range and the average value of the intersection of the second prediction range and the third prediction range are calculated, and the obtained average value is used as the target demand power.

[0080] S086: If there is no intersection between the second prediction range and the third prediction range, the average of the intersection of the first prediction range and the third prediction range and the average of the third prediction range are calculated, and the obtained average is used as the target power demand.

[0081] S096: If there is no intersection between the first prediction range and the third prediction range, determine whether there is an intersection between the second prediction range and the third prediction range.

[0082] S106: If the second prediction range and the third prediction range have an intersection, calculate the average of the average value of the first prediction range and the average value of the intersection of the second prediction range and the third prediction range, and use the obtained average value as the target required power.

[0083] S116, if the second prediction range does not have an intersection with the third prediction range, calculate the average value of the first prediction range, the average value of the second prediction range, and the average value of the third prediction range, and use the obtained average value as the target required power.

[0084] Specifically, multiple limiting conditions such as peak electricity consumption period and valley electricity consumption period can be added to the existing conditions such as sample operation time information, sample operation power information, sample operation weather information, sample operation temperature information, sample operation humidity information, etc.

[0085] In this embodiment, multiple power consumption ranges are established under sample operating time information, sample operating power information, sample operating weather information, sample operating temperature information, and sample operating humidity information, and corresponding matching power consumption ranges are obtained by limiting different conditions. The intersection of the power consumption ranges is further calculated, and the intersections of the power consumption ranges are calculated to infer the target power demand under the limitations of different conditions.

[0086] In one embodiment of the present application, the sample time-power curve after the second marking of each sample data is marked based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data, and then further includes the following S126 to SS146: S126, obtaining target required power.

[0087] S136, calculating the sum of the target power demand and the target power demand multiplied by N%, and defining the obtained sum as the compensated target power demand.

[0088] S146, outputting the compensated target power demand.

[0089] Specifically, the sum of the target demand electricity and the target demand electricity multiplied by N% is calculated, and the obtained sum is defined as the compensated target demand electricity, which refers to the target demand electricity obtained by increasing or decreasing a certain amount of electricity on the basis of the target demand electricity. For example, if the target demand electricity is in the peak period of electricity consumption, a certain amount of electricity is added to the target demand electricity; if the target demand electricity is in the high and low periods of electricity consumption, a certain amount of electricity is reduced on the basis of the target demand electricity; the direction and amount of compensation are further adjusted in different seasons.

[0090] In this embodiment, the target power demand is increased or decreased by a certain percentage based on the target power demand to obtain the compensated target power demand, so as to increase the fault tolerance rate for emergencies.

[0091] The technical features of the above-described embodiments may be arbitrarily combined, and the execution order of the method steps is not limited. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0092] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting energy storage system load, characterized in that: The energy storage system load prediction method comprises: Acquire sample data of a plurality of samples, wherein the sample data includes sample operation data; Parse the sample operation data to obtain sample operation time information, sample operation power information, sample operation weather information, sample operation temperature information, and sample operation humidity information in the sample operation data; Generate a sample time-power curve for each sample data based on the sample operation time information and the sample operation power information for each sample data; Marking a sample time-power curve of each sample data based on sample operating weather information of each sample data to obtain a sample time-power curve of each sample data after the first marking; Marking the sample time-power curve after the first marking of each sample data based on the sample operating temperature information of each sample data to obtain the sample time-power curve after the second marking of each sample data; Marking the sample time-power curve after the second marking of each sample data based on the sample running humidity information of each sample data, to obtain the sample time-power curve after the third marking of each sample data; A power demand prediction model is constructed based on each sample running time information, each sample running power information, each sample running weather information, each sample running temperature information, each sample running humidity information, each sample time-power curve after the first marking, each sample time-power curve after the second marking, and each sample time-power curve after the third marking; Get a sample data to be tested; Parsing the sample data to be tested to obtain the running time information of the sample to be tested, the running power information of the sample to be tested, the running weather information of the sample to be tested, the running temperature information of the sample to be tested, and the running humidity information of the sample to be tested in the sample data to be tested; The obtained running time information of the samples to be tested, the running power information of the samples to be tested, the running weather information of the samples to be tested, the running temperature information of the samples to be tested, and the running humidity information of the samples to be tested are input into the power demand prediction model, the power demand prediction model is started, and the predicted power demand output by the power demand prediction model is obtained.

2. The energy storage system load prediction method according to claim 1, characterized in that: The step of generating a sample time-power curve for each sample data based on the sample operation time information and the sample operation power information for each sample data comprises: Select a sample running data; Obtaining sample operation time information and sample operation power information in the sample operation data; Create a two-dimensional coordinate system; Based on the sample operation time information, the sample operation power information is incorporated into a two-dimensional coordinate system to obtain a sample time-power curve; Return to the step of selecting a sample running data until each sample running data has been selected once.

3. The energy storage system load prediction method according to claim 2, characterized in that: The step of marking the sample time-power curve of each sample data based on the sample operation weather information of each sample data to obtain the sample time-power curve of each sample data after the first marking includes: Select a sample running data; Obtaining a sample time-power curve in the sample operation data; Acquire sample operation weather information in the sample operation data, wherein the sample operation weather information includes multiple weather types, and the weather types include sunny, cloudy, overcast, light rain, moderate rain and heavy rain; Marking the sample time-power curve based on each weather type and the time period corresponding to each weather type to obtain the sample time-power curve after the first marking; Return to the step of selecting a sample running data until each sample running data has been selected once.

4. The energy storage system load prediction method according to claim 3, characterized in that: The sample time-power curve of each sample data is marked based on the sample operation weather information of each sample data to obtain the sample time-power curve of each sample data after the first marking, and then further includes: Select a weather type; Parsing the weather type, obtaining a time-power curve of at least one sample after the first marking in the weather type; Select a sample time-power curve after the first marking; Analyze the sample time-power curve after the first marking to obtain the actual power supply value in the sample time-power curve after the first marking; Returning the sample time-power curve after selecting a first mark, until each sample time-power curve after the first mark has been selected once, to obtain multiple actual power supply values; The largest actual power supply value among the obtained multiple actual power supply values ​​is used as the maximum boundary value of the first prediction range; the smallest actual power supply value among the obtained multiple actual power supply values ​​is used as the minimum boundary value of the first prediction range to obtain the first prediction range; Return to selecting a weather type until each weather type has been selected once.

5. The energy storage system load prediction method according to claim 4, characterized in that: The step of marking the sample time-power curve after the first marking of each sample data based on the sample operating temperature information of each sample data to obtain the sample time-power curve after the second marking of each sample data includes: Select a sample running data; Obtain a sample time-power curve after the first mark in the sample running data; Acquire sample operation temperature information in the sample operation data, wherein the sample operation temperature information includes at least one temperature value; Marking the sample time-power curve after the first marking based on all temperature values ​​in the sample running temperature information to obtain the sample time-power curve after the second marking; Return to the step of selecting a sample running data until each sample running data has been selected once.

6. The energy storage system load prediction method according to claim 5, characterized in that: The step of marking the sample time-power curve after the first marking of each sample data based on the sample operating temperature information of each sample data to obtain the sample time-power curve after the second marking of each sample data further includes: Select a temperature value; Analyze the temperature value to obtain at least one sample time-power curve after the second marking of the temperature value; Select a sample time-power curve after the second marking; Analyze the sample time-power curve after the second marking to obtain the actual power supply value in the sample time-power curve after the second marking; Returning to the selection of a sample time-power curve after the second marking, until each sample time-power curve after the second marking has been selected once, to obtain a plurality of actual power supply values; The maximum actual power supply value among the obtained multiple actual power supply values ​​is used as the maximum boundary value of the second prediction range; the minimum actual power supply value among the obtained multiple actual power supply values ​​is used as the minimum boundary value of the second prediction range to obtain the second prediction range; Return to selecting a temperature value until each temperature value has been selected once.

7. The energy storage system load prediction method according to claim 6, characterized in that: The step of marking the sample time-power curve after the second marking of each sample data based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data includes: Select a sample running data; Obtaining a sample time-power curve after the second marking in the sample running data; Acquire sample operation humidity information in the sample operation data, wherein the sample operation humidity information includes at least a humidity value; Marking the sample time-power curve after the second marking based on all humidity values ​​in the sample running humidity information to obtain the sample time-power curve after the third marking; Return to the step of selecting a sample running data until each sample running data has been selected once.

8. The energy storage system load prediction method according to claim 7, characterized in that: The sample time-power curve after the second marking of each sample data is marked based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data, and then further includes: Select a humidity value; Analyze the humidity value to obtain a sample time-power curve of at least one humidity value after the third marking; Select a sample time-power curve after the third marking; Analyze the sample time-power curve after the third marking to obtain the actual power supply value in the sample time-power curve after the third marking; Returning the sample time-power curve selected after the third marking, until each sample time-power curve after the third marking has been selected once, to obtain multiple actual power supply values; The largest actual power supply value among the obtained multiple actual power supply values ​​is used as the maximum boundary value of the third prediction range; the smallest actual power supply value among the obtained multiple actual power supply values ​​is used as the minimum boundary value of the third prediction range to obtain the third prediction range; Return to selecting a humidity value until each humidity value has been selected once.

9. The energy storage system load prediction method according to claim 8, characterized in that: The sample time-power curve after the second marking of each sample data is marked based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data, and then further includes: Determine whether the first prediction range and the second prediction range have an intersection; If the first prediction range and the second prediction range have an intersection, then determine whether the intersection of the first prediction range and the second prediction range has an intersection with the third prediction range; If the intersection of the first prediction range and the second prediction range intersects with the third prediction range, then the average value of the intersection of the first prediction range and the second prediction range and the intersection of the third prediction range is calculated, and the obtained average value is used as the target power demand; If the intersection of the first prediction range and the second prediction range does not have an intersection with the third prediction range, then the average value between the average value of the intersection of the first prediction range and the second prediction range and the average value of the third prediction range is calculated, and the obtained average value is used as the target power demand; If the first prediction range and the second prediction range do not have an intersection, then determining whether the first prediction range and the third prediction range have an intersection; If the first prediction range and the third prediction range have an intersection, then determine whether the second prediction range and the third prediction range have an intersection; If the second prediction range and the third prediction range have an intersection, then the average of the average value of the intersection of the first prediction range and the third prediction range and the average value of the intersection of the second prediction range and the third prediction range is calculated, and the obtained average value is used as the target power demand; If the second prediction range does not have an intersection with the third prediction range, the average of the intersection of the first prediction range and the third prediction range and the average of the third prediction range are calculated, and the obtained average is used as the target power demand; If the first prediction range and the third prediction range do not have an intersection, then determining whether the second prediction range and the third prediction range have an intersection; If the second prediction range and the third prediction range have an intersection, then the average of the average value of the first prediction range and the average value of the intersection of the second prediction range and the third prediction range is calculated, and the obtained average value is used as the target power demand; If the second prediction range does not have an intersection with the third prediction range, the average value of the first prediction range, the average value of the second prediction range, and the average value of the third prediction range are calculated, and the obtained average value is used as the target required power.

10. The energy storage system load prediction method according to claim 9, characterized in that: The sample time-power curve after the second marking of each sample data is marked based on the sample running humidity information of each sample data to obtain the sample time-power curve after the third marking of each sample data, and then further includes: Obtain target power demand; Calculate the sum of the target power demand and the target power demand multiplied by N%, and define the sum as the target power demand after compensation; Output the target power demand after compensation.

Images