Energy control method and system based on source network load storage power supply and storage medium

Abstract

The application belongs to the technical field of power supply, and discloses an energy control method and system based on source-grid-load-storage power supply and a storage medium, which comprises the following steps: determining a first photovoltaic power generation amount and a first power demand amount of a predicted day based on first historical data and prediction data at a set time, calculating a difference between the first available power amount and the first power demand amount, and when the difference is greater than a first preset value, establishing a cost objective function based on the capacity of an energy storage device, the difference, the operation loss and maintenance loss of the energy storage device, and the electricity price cost of each time period in the predicted day, charging the energy storage device based on the charging time and charging power obtained by solving the cost objective function, periodically determining a second photovoltaic power generation amount and a second power demand amount in each set time period, and controlling the charging and discharging of the energy storage device according to a source-grid-load-storage collaborative power supply mechanism. The application can comprehensively optimize the source-grid-load-storage power supply system through accurate prediction and control.

Description

Technical Field

[0001] The present invention belongs to the field of electric power supply technology, and specifically relates to an energy control method, system and storage medium based on source-grid-load-storage power supply. Background Art

[0002] With the acceleration of urbanization, rail transit systems, as a vital component of urban transportation, are facing increasing energy demand and consumption. Traditional energy management methods struggle to adapt to the challenges of load fluctuations and the uncertainty of renewable energy output. Therefore, developing a method that can accurately predict load and photovoltaic output and optimize energy scheduling is crucial for improving the energy efficiency and cost-effectiveness of rail transit systems.

[0003] Similar prior art includes Chinese patent application publication number CN118523329A, which discloses a source-grid-vehicle-storage integrated rail transit collaborative energy supply method. Using constructed photovoltaic power generation models, lighting system energy consumption models, and air conditioning system energy consumption models, the method obtains the total energy generated by the photovoltaic power generation device and the lighting system energy consumption and air conditioning system energy consumption during train operation. An objective function is constructed, including the total system operating cost and energy loss. Constraints for the objective function are established. Each objective function is normalized and preprocessed. Multiple objective functions are converted into single objective functions. An improved vulture search algorithm is used to solve the single objective function, achieving the goals of minimizing system operating cost and energy loss. Based on the photovoltaic output time and time-of-use electricity price mechanism, the scheduling strategy for the source, grid, vehicle, and storage is determined for the optimal solution of the single objective function. This method only predicts the energy consumption of the lighting system and the air conditioning system during train operation, which is not comprehensive and leads to inaccurate scheduling strategies. There is also a Chinese patent application with publication number CN115528681A, which discloses a real-time energy management and control method for rail transit "grid-source-storage-vehicle" coordination. The method collects power information of each unit of the "grid-source-storage-vehicle" coordinated power supply system in real time; determines the current operating state and operating mode of the "grid-source-storage-vehicle" coordinated power supply system based on the traction load requirements of the trains on the left and right sides of the traction network, the photovoltaic power generation, and the energy storage charge state; determines the reference power of the controllable quantity of each unit of the "grid-source-storage-vehicle" coordinated power supply system in the current operating state and operating mode based on the operating mechanism of the "grid-source-storage-vehicle" coordinated power supply system, generates corresponding power instructions, and adjusts the output power of the controllable quantity of each unit in real time. This method relies on real-time collected data for energy management and control, and lacks foresight.

[0004] Therefore, it is an urgent problem to provide an energy control method, system and storage medium based on source-grid-load-storage power supply, so as to optimize the use of power resources through accurate prediction and control, and improve energy utilization efficiency and economy. Summary of the Invention

[0005] In response to the technical problems raised above, the present invention provides an energy control method, system and storage medium based on source-grid-load-storage power supply.

[0006] In a first aspect, the present invention provides an energy control method based on source-grid-load-storage power supply, the method comprising the following steps:

[0007] Step 1: obtaining first historical data and forecast data of the traction substation area at a set time on the current date;

[0008] Step 2: Determine a first photovoltaic power generation and a first electricity demand on a forecast day based on the first historical data and the forecast data, wherein the forecast day is the day after the current date;

[0009] Step 3: Obtain the amount of stored electricity in the energy storage device, and calculate the difference between the first available electricity and the first electricity demand, where the first available electricity is the sum of the first photovoltaic power generation and the stored electricity;

[0010] Step 4: Determine whether the difference is less than or equal to a first preset value. If so, proceed to step 7; if not, proceed to step 5.

[0011] Step 5: Establish a cost objective function based on the capacity of the energy storage device, the difference, and the electricity price cost for each time period within the forecast day, and solve the cost objective function to obtain the charging time and charging power for charging the energy storage device;

[0012] Step 6: charging the energy storage device based on the charging time and the charging amount;

[0013] Step 7: During the forecast day, the power consumption of all electrical devices and the power generation of photovoltaic power generation equipment are periodically collected, and the second photovoltaic power generation and second power demand in each set time period are periodically determined. The charging and discharging of the energy storage device is controlled according to the source-grid-load-storage coordinated power supply mechanism.

[0014] Specifically, the first historical data includes actual photovoltaic power generation and predicted photovoltaic power generation for each day within a first preset time period before the prediction day, and the prediction data includes predicted weather data and predicted sunlight data. In step 2, determining the first photovoltaic power generation for the prediction day based on the first historical data and the prediction data includes:

[0015] Step 211: Determine whether the current date is a specific date. If so, proceed to step 222; if not, proceed to step 215.

[0016] Step 222: Calculate the sum of the actual photovoltaic power generation on all dates within the first preset time period and define it as a first value. Then calculate the ratio of the first value to the first adjustment parameter and define it as a first ratio.

[0017] Step 213: Determine whether the first ratio is greater than or equal to a preset reference value. If so, proceed to step 214; if not, proceed to step 215.

[0018] Step 214: Calculate the sum of the predicted photovoltaic power generation for all dates within the first preset time period and define it as a second value. Generate a second adjustment parameter based on the first value, the second value, and the first adjustment parameter. Then define the second adjustment parameter as the first adjustment parameter. The calculation formula for the second adjustment parameter is:

[0019] ,

[0020] Among them, AP1 is the second adjustment parameter, E A is the first value, E P is the second value, AP1 is the first adjustment parameter;

[0021] Step 215: Input the prediction data into the preset model to obtain the second photovoltaic power generation on the prediction day, calculate the product of the second photovoltaic power generation and the first adjustment parameter, and define it as the first photovoltaic power generation.

[0022] Specifically, step 213, when the first ratio is less than a preset reference value, includes:

[0023] Extending the specific date by a third preset time to generate a new specific date;

[0024] And all specific dates are updated based on the first preset time period and the new specific date.

[0025] Specifically, after step 214, the following steps are further included:

[0026] Calculating a ratio of the first value to the second value and defining the ratio as a second ratio;

[0027] It is determined whether the second ratio is within a preset range. If not, it is determined whether the specific date is a first-category specific date. If not, a reminder message is sent to the staff.

[0028] Specifically, the first historical data includes a first actual power consumption and a first actual temperature value in each preset time period of each day within a second preset time period before the prediction day, and the prediction data includes predicted weather data. In step 2, determining the first power demand on the prediction day based on the first historical data and the prediction data includes:

[0029] Step 221: Determine the date type, air conditioner operation mode, and predicted temperature values ​​for each preset time period of the predicted day, where the date type is weekday, weekend, or statutory holiday, and the air conditioner operation mode is cooling, heating, or off.

[0030] Step 222: Calculate the average value of the first actual power consumption corresponding to any preset time period within the second preset time period, which is defined as the first power average value; and calculate the average value of the first actual temperature value corresponding to any preset time period within the second preset time period, which is defined as the first temperature average value;

[0031] Step 223: Based on the date type and the air conditioner operation mode, a corresponding power forecasting model is selected for any preset time period within the forecast day. Subsequently, the date type, the predicted temperature value, the first average power value, and the first average temperature value corresponding to any preset time period are input into the power forecasting model corresponding to any preset time period to obtain the power demand corresponding to any preset time period within the forecast day.

[0032] Step 224 : Repeat step 223 , and after traversing all preset time periods, define the sum of the power demand amounts corresponding to all preset time periods as the first power demand amount.

[0033] Specifically, in step 223, the method for constructing the power prediction model is:

[0034] Step 2231: Extract the second historical data within the third preset time, pre-process the second historical data, and generate third historical data, wherein the second historical data includes the date type and air conditioner operation mode corresponding to each day within the third preset time, and the second actual power consumption and the second actual temperature value within each preset time period of each day;

[0035] Step 2232: For any day within the third preset time period, calculate the average value of the second actual power usage corresponding to any preset time period within the second preset time period before any day, defining it as the second average power consumption value, and calculate the average value of the second actual temperature corresponding to any preset time period within the second preset time period before any day, defining it as the second average temperature value. Then, store the second average power consumption value and the second average temperature value in correspondence with the data of any day.

[0036] Step 2233: After traversing all dates within the third preset time, generate fourth historical data, and then divide the fourth historical data into N data sets based on the date type, the air conditioner operation mode, and the preset time period;

[0037] Step 2234: Use the actual power consumption as the dependent variable, the actual temperature value, the m-th power of the actual temperature value, the date type, the second average power consumption, and the second average temperature value as independent variables to construct a linear equation containing a constant parameter.

[0038] Step 2235: extract any data set, use any data set to fit the linear equation, determine the weight coefficient corresponding to each independent variable, and substitute it into the linear equation to generate the power prediction model corresponding to any data set.

[0039] Specifically, in step 7, periodically determining the second photovoltaic power generation and the second electricity demand in each set time period includes:

[0040] Step 71: Determine whether the current time is the end time of any set time period. If so, extract all power values ​​within any set time period to generate a first power time series, where the power is photovoltaic power generation or power demand.

[0041] Step 72: With the prediction day as the center point, set a first time window, and search the first historical data for a second power time series whose Euclidean distance to the first power time series is less than or equal to a second preset value based on the first time window. The number of data in any second power time series is the same as the number of data in the second power time series, and the prediction day is represented by month and day.

[0042] Step 73: Determine whether the number of all second electric energy time series is greater than or equal to a third preset value. If so, proceed to step 74; if not, adjust the first time window according to the first preset rule, and then return to step 72.

[0043] Step 74: Filter out a third electric power time series from all second electric power time series based on a second preset rule;

[0044] Step 75: Calculate a fourth electric power time series within a set time period next to any set time period based on the third electric power time series;

[0045] Step 76: Calculate the second power amount for the next set time period based on the fourth power amount time series.

[0046] Specifically, step 74 includes:

[0047] Step 741: Filter out all the second power time series corresponding to the date with the same average temperature as the forecast day, and define them as the first candidate time series. The first candidate time series does not include the power time series of the forecast day.

[0048] Step 742: Set a second time window with the forecast day as the center point, and select a candidate time series within the second time window from the first candidate time series based on the second time window, defining the second candidate time series as the second candidate time series.

[0049] Step 743: Set a third time window with the current time as the center point, and obtain a pending time series within the third time window from the second candidate time series based on the third time window, defining it as a third candidate time series.

[0050] Step 744, judging whether the number of the third pending time sequences is greater than or equal to a fourth preset value, if yes, defining the third pending time sequence as a third electric power time sequence, if not, entering step 745;

[0051] Step 745, judging whether the width of the third time window is a preset threshold, if yes, adjusting the second time window according to a second preset rule, then returning to step 742, if not, adjusting the third time window according to a third preset rule, then returning to step 743.

[0052] Specifically, step 75 includes:

[0053] obtaining a fifth electric power time sequence corresponding to a next set time period of each third electric power time sequence;

[0054] taking a weighted average value of an i-th value in all fifth electric power time sequences as a value of an i-th electric power in the fourth electric power time sequence, wherein i is a positive integer from 1 to I, and I is a total number of electric power data in the fourth electric power time sequence.

[0055] In a second aspect, the present application further provides an energy control system based on source network load storage power supply, which comprises:

[0056] a data acquisition module, a first prediction module, a first control module, a second prediction module and a second control module;

[0057] the data acquisition module is configured to acquire first historical data and prediction data of the traction substation area at a set time of a current date;

[0058] the first prediction module is configured to determine a first photovoltaic power generation amount and a first power demand amount of a prediction day based on the first historical data and the prediction data, wherein the prediction day is a next day of the current date;

[0059] the first control module is configured to acquire a storage power in the energy storage device, calculate a difference between a first available power and the first power demand amount, when the difference is less than or equal to a first preset value, establish a cost objective function based on a capacity of the energy storage device, the difference, an operation loss and a maintenance loss of the energy storage device, and a cost of electricity price in each time period of the prediction day, solve the cost objective function to obtain a charging time and a charging power for charging the energy storage device, and charge the energy storage device based on the charging time and the charging power, wherein the first available power is a sum of the first photovoltaic power generation amount and the storage power;

[0060] the second prediction module is configured to periodically collect power consumptions of all power consuming devices and power generations of photovoltaic power generation devices in the prediction day, and periodically determine a second photovoltaic power generation amount and a second power demand amount in each set time period;

[0061] The second control module is used to control the charging and discharging of the energy storage device according to the source-grid-load-storage coordinated power supply mechanism.

[0062] In a third aspect, the present invention provides a computer storage medium storing program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute any one of the above-mentioned energy control methods based on source-grid-load-storage power supply.

[0063] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0064] 1. Accurately predict photovoltaic power generation and power demand. When the difference between the first available power and the first power demand is greater than a threshold, a cost objective function is established. Based on the charging time and charging power obtained from solving the cost objective function, the energy storage device is charged and the charging and discharging strategy of the energy storage device is optimized. Charging can be performed during periods with lower electricity prices, reducing operating costs and ensuring the stability of power supply.

[0065] 2. Flexibly adjust energy dispatch strategies based on real-time data and forecast results to adapt to the ever-changing energy supply and demand situation, and make timely adjustments when there is excess or insufficient power supply, thereby enhancing the stability and reliability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0067] Figure 1 This is a flow chart of the energy control method based on source-grid-load-storage power supply of the present invention;

[0068] Figure 2 This is a modular schematic diagram of the energy control system based on source-grid-load-storage power supply of the present invention. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the specific embodiments described herein are only used to explain the present invention and are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0070] It should be noted that if there are descriptions involving "first," "second," etc. in the embodiments of the present invention, such descriptions are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the technical features indicated. Therefore, features specified as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions of the various embodiments may be combined with each other, but this must be based on the premise that they can be implemented by a person of ordinary skill in the art. If the combination of technical solutions is mutually inconsistent or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0071] Figure 1 FIG. 1 is a flow chart of an embodiment of an energy control method based on source-grid-load-storage power supply provided by the present invention, which specifically includes the following steps:

[0072] Step 1: Obtain first historical data and forecast data of the traction substation area at a set time on the current date.

[0073] The set time is set according to the experience of those skilled in the art or according to the actual application scenario, and the embodiments of the present application are not limited thereto. For example, the set time is set to a preset time after the end of the train operation. For example, at 8 p.m. every night, all trains stop operating, and the set time is set to 9:00 p.m.

[0074] Step 2: Determine a first photovoltaic power generation and a first electricity demand on a forecast day based on the first historical data and the forecast data, wherein the forecast day is the day after the current date.

[0075] At a set time each day, the next day's photovoltaic power generation and electricity demand are predicted in advance by combining historical data and forecast data, providing a more comprehensive perspective to evaluate future energy supply and demand, providing a basis for energy scheduling and energy storage management, and helping to formulate reasonable energy scheduling plans.

[0076] Specifically, the first historical data includes actual photovoltaic power generation and predicted photovoltaic power generation for each day within a first preset time period before the prediction day, and the prediction data includes predicted weather data and predicted sunlight data. In step 2, determining the first photovoltaic power generation for the prediction day based on the first historical data and the prediction data includes:

[0077] Step 211 , determine whether the current date is a specific date, if so, proceed to step 222 , if not, proceed to step 215 .

[0078] Step 222: Calculate the sum of the actual photovoltaic power generation on all dates within the first preset time period and define it as a first value. Then calculate the ratio of the first value to the first adjustment parameter and define it as a first ratio.

[0079] Step 213, judge whether the first ratio is greater than or equal to the preset reference value, if yes, go to step 214, if no, go to step 215.

[0080] Step 214, calculate the sum of the predicted photovoltaic power generation of all dates in the first preset time period, and define it as the second value, generate the second adjustment parameter based on the first value, the second value and the first adjustment parameter, then define the second adjustment parameter as the first adjustment parameter, the second adjustment parameter calculation formula is:

[0081]

[0082] Wherein, AP1 is the second adjustment parameter, E A is the first value, E P is the second value, and AP1 is the first adjustment parameter.

[0083] Step 215, input the prediction data into the preset model to obtain the second photovoltaic power generation of the prediction day, calculate the product of the second photovoltaic power generation and the first adjustment parameter, and define it as the first photovoltaic power generation.

[0084] The first preset time period and the preset reference value are set according to the experience of those skilled in the art or according to the actual application scene, and the embodiments of the application are not limited thereto. Illustratively, the first preset time period is 15 days, 30 days or 60 days.

[0085] The predicted weather data includes temperature, humidity, sunrise time, sunset time, sunny day, cloudy day, overcast day and / or rainy day, and the predicted light data includes light intensity, light amount and / or light effective area.

[0086] The specific date is the date for updating the adjustment parameter, which is set in advance based on the first preset time period. Illustratively, the first preset time period is 15 days, and the photovoltaic power generation equipment is put into use on April 1, 2021, then April 15, April 30, May 15, May 30... are set as the specific date.

[0087] The first ratio is less than the preset reference value, which means that the data is missing due to equipment failure, data transmission error, etc. in the first preset time period, or the data quality is poor due to abnormal value, error record, environmental change, etc., resulting in insufficient historical data to support the reset of the adjustment parameter. If the adjustment parameter is updated based on limited data, the value of the adjustment parameter may be unstable, further affecting the accuracy of subsequent prediction. In order to ensure the accuracy of the adjustment parameter and the photovoltaic power generation prediction, the adjustment parameter reset is not performed when the data is insufficient.

[0088] ​The preset model is trained in advance based on historical data of photovoltaic power generation equipment. However, due to the aging of photovoltaic power generation equipment, the decline in panel efficiency, dust accumulation on the equipment, climate change, environmental changes, etc., the prediction accuracy may change. According to the technical solution of the present invention, the adjustment parameters are periodically reset, and the prediction results of the preset model are adjusted based on the adjustment parameters, which helps to reduce prediction errors and improve prediction accuracy.

[0089] Specifically, step 213, when the first ratio is less than a preset reference value, includes:

[0090] Extending the specific date by a third preset time to generate a new specific date;

[0091] And all specific dates are updated based on the first preset time period and the new specific date.

[0092] The third preset time is set according to the experience of those skilled in the art or according to the actual application scenario, and is not limited in the embodiments of the present application. For example, the third preset time is 2 days or 3 days, and can also be determined based on the amount of the first historical data within the first preset time period.

[0093] If it is not appropriate to adjust the first adjustment parameter, wait until the third preset time has passed before adjusting the first adjustment parameter. For example, if the current date is April 1st and the third preset time is April 2nd, the new specific date is April 3rd. Subsequently, based on the first preset time period (e.g., April 15th), subsequent specific dates are updated to April 18th, May 3rd, and so on.

[0094] Preferably, the specific date may not be updated, and the first adjustment parameter may be adjusted on the next specific date.

[0095] Specifically, after step 214, the following steps are further included:

[0096] Calculating a ratio of the first value to the second value and defining the ratio as a second ratio;

[0097] It is determined whether the second ratio is within a preset range. If not, it is determined whether the specific date is a first-category specific date. If not, a reminder message is sent to the staff.

[0098] The preset interval is used to determine whether the deviation between the actual power generation and the predicted power generation is too large. The value of the preset interval is set based on the experience of those skilled in the art or based on the actual application scenario, and the embodiments of this application do not limit this.

[0099] When the second ratio is less than the lower limit of the above-mentioned preset interval, it indicates that the predicted power generation is too high and the actual photovoltaic power generation is far lower than the predicted photovoltaic power generation. When the second ratio is greater than the upper limit of the above-mentioned preset interval, it indicates that the predicted power generation is too low and the actual photovoltaic power generation is far higher than the predicted photovoltaic power generation. That is, when the second ratio is not within the preset interval, the actual photovoltaic power generation fluctuates greatly compared with the predicted photovoltaic power generation. It is necessary to remind the staff to pay attention to possible failures of the photovoltaic power generation equipment or changes in the environment around the photovoltaic power generation equipment, so as to take measures to make adjustments.

[0100] Specific dates include first-category specific dates and second-category specific dates. First-category specific dates are for initial adjustments, while second-category specific dates are for regular adjustments. For example, if the photovoltaic power generation equipment is commissioned on March 25, **, April 1 is set as the initial adjustment date. When the first preset time period is 30 days, May 1, May 31, June 30, and so on are set as regular adjustment dates. When the photovoltaic power generation equipment is first commissioned, the adjustment parameters are quickly adapted and adjusted. After the initial adjustment, the first adjustment parameters are regularly adjusted according to the first preset time period to continuously optimize the prediction accuracy of photovoltaic power generation.

[0101] Specifically, the first historical data includes a first actual power consumption and a first actual temperature value in each preset time period of each day within a second preset time period before the prediction day, and the prediction data includes predicted weather data. In step 2, determining the first power demand on the prediction day based on the first historical data and the prediction data includes:

[0102] Step 221: Determine the date type of the predicted day, the air conditioning operation mode, and the predicted temperature value for each preset time period, wherein the date type is weekday, weekend, or statutory holiday, and the air conditioning operation mode is cooling, heating, or off.

[0103] Step 222: Calculate the average value of the first actual power consumption corresponding to any preset time period within the second preset time, which is defined as the first power average value, and calculate the average value of the first actual temperature value corresponding to any preset time period within the second preset time, which is defined as the first temperature average value.

[0104] Step 223: Based on the date type and the air conditioning operation mode, a corresponding power forecasting model is selected for any preset time period within the forecast day. Then, the date type, predicted temperature value, first average power value, and first average temperature value corresponding to any preset time period are input into the power forecasting model corresponding to any preset time period to obtain the power demand corresponding to any preset time period within the forecast day.

[0105] Step 224 : Repeat step 223 , and after traversing all preset time periods, define the sum of the power demand amounts corresponding to all preset time periods as the first power demand amount.

[0106] The second preset time and preset time period are set according to the experience of those skilled in the art or according to the actual application scenario, and are not limited in the embodiments of the present application. For example, the second preset time is 10 days or 20 days. The preset time period is a time period generated by dividing the 24 hours of a day, which can be divided evenly or unevenly, such as 24:00 to 5:00, 5:00 to 8:00, 8:00 to 11:00, 11:00 to 14:00, 14:00 to 17:00, 17:00 to 20:00, and 20:00 to 24:00.

[0107] Specifically, in step 223, the method for constructing the power prediction model is:

[0108] Step 2231: Extract the second historical data within the third preset time, preprocess the second historical data, and generate third historical data, wherein the second historical data is the date type corresponding to each day within the third preset time, the air conditioning operation mode, and the second actual power consumption and the second actual temperature value in each preset time period of each day.

[0109] Step 2232: For any day within the third preset time, calculate the average value of the second actual electricity consumption corresponding to any preset time period within the second preset time period before any day, and define it as the second average value of electricity consumption; and calculate the average value of the second actual temperature value corresponding to any preset time period within the second preset time period before any day, and define it as the second average value of temperature; then store the second average value of electricity consumption and the second average value of temperature in correspondence with the data of any day.

[0110] Step 2233: After traversing all dates within the third preset time, generate fourth historical data, and then divide the fourth historical data into N data sets based on the date type, air conditioner operation mode and preset time period.

[0111] Step 2234: Use the actual power consumption as the dependent variable, the actual temperature value, the m-th power of the actual temperature value, the date type, the second average power consumption, and the second average temperature value as independent variables to construct a linear equation containing a constant parameter.

[0112] Step 2235: extract any data set, use any data set to fit the linear equation, determine the weight coefficient corresponding to each independent variable, and substitute it into the linear equation to generate the power prediction model corresponding to any data set.

[0113] The third preset time, the value of N, and the value of m are set according to the experience of those skilled in the art or according to actual application scenarios, and are not limited in the present embodiment.

[0114] The preprocessing includes identifying and processing missing values, outliers or error data, such as filling in missing values, modifying outliers or error data, etc.

[0115] The value of N is related to the number of date types, air conditioner running modes, and preset time periods, and exemplarily, the value of N is 84 when the number of date types is 4, the number of air conditioner running modes is 3, and the number of preset time periods is 7.

[0116] The date types are classified mainly because the power consumption is different due to different passenger flows on weekdays and non-weekdays, and different passenger flows on weekends or statutory holidays in non-weekdays, resulting in different power consumption; the air conditioner running modes are classified because the power demand of air conditioner devices among all power equipment is greatly changed based on the change of air temperature, and the power demand mode is different when the air conditioner is cooling, heating, ventilating or off; the preset time periods are classified because the passenger flow and power consumption are different at different time periods. Different power consumption prediction models are generated for different date types, air conditioner running modes and preset time periods, which can more accurately reflect the power demand changes of different date types, different air conditioner running modes and different preset time periods, make the power consumption prediction model more refined and personalized, and improve the accuracy and reliability of the prediction.

[0117] The linear equation constructed in step 2234 is a basic equation, and exemplarily, the linear equation is: wherein PE is the actual power consumption, TA is the actual temperature value, D T is the date type, E A2 is the second power average value, T A2 is the second temperature average value, is the weight coefficient.

[0118] The linear equation is fitted (such as the least square method) by using any data combination, the value of each weight coefficient corresponding to the any data set is determined, the value of each weight coefficient is input into the linear equation, and the power consumption prediction equation (i.e., the power consumption prediction model) corresponding to the date type, the air conditioner running mode and the preset time period of the any data set is obtained.

[0119] According to the technical scheme of the application, when the power consumption is predicted, multiple independent variables are considered, a data expression capable of representing the correlation between the dependent variable and the multiple independent variables is determined based on mathematical optimization technology, the mathematical expression is taken as the power consumption prediction model, the power consumption prediction accuracy and efficiency can be improved, the power demand prediction is more objective and standardized, different power consumption prediction models are generated for different date types, different air conditioner running modes and different preset time periods, different power demand modes can be adapted, and the power consumption prediction accuracy is improved.

[0120] Preferably, the power consumption prediction model is periodically updated.

[0121] Step 3, obtain the storage capacity in the energy storage device, and calculate the difference between the first available power and the first power demand, wherein the first available power is the sum of the first photovoltaic power generation and the storage capacity.

[0122] Step 4, determine whether the difference is less than or equal to the first preset value, if yes, go to step 7, if no, go to step 5.

[0123] The first preset value is set according to the experience of a person skilled in the art or according to the actual application scene, and the embodiments of the present application do not limit this.

[0124] Before the prediction day, it is determined whether the photovoltaic power supply demand balance can be realized based on the prediction information, if the difference is less than or equal to the first preset value, it means that the photovoltaic power supply is risk-free, less risky or controllable, and no early treatment is needed, if the difference is greater than the first preset value, it means that the risk of insufficient photovoltaic power supply is large, and the energy storage device needs to be charged in advance to ensure the stability and safety of energy supply.

[0125] Through prediction and comparison, potential energy supply shortage problems can be identified in advance, and preventive measures can be taken, such as adjusting the charging strategy, to ensure the continuity and reliability of energy supply.

[0126] Step 5, based on the capacity of the energy storage device, the difference and the electricity price cost of each period in the prediction day, a cost objective function is established, and the charging time and charging capacity of the energy storage device are obtained by solving the cost objective function.

[0127] Exemplarily, the cost objective function is Min , wherein C is the total charging cost, c t is the electricity price of period t, p ch,t is the charging power of the energy storage device in period t, h t is the charging time of period t.

[0128] The constraint condition is: ,

[0129] , wherein E t is the power of the energy storage device at the end of period t, E min and E max are the minimum capacity and maximum capacity of the energy storage device respectively, pch,max is the maximum charging power of the energy storage device, η ch and η dis are the charging efficiency and discharging efficiency respectively, p dis,t represents the discharging power of the energy storage device in period t

[0130] The objective function and constraints are solved through linear programming, mixed integer programming or other optimization algorithms to determine the optimal charging time and charging capacity.

[0131] Based on this, energy storage resources can be effectively managed, electricity costs can be optimized, and the economy and reliability of the energy system can be improved.

[0132] Step 6: Charge the energy storage device based on the charging time and the charging amount.

[0133] Preferably, step 5 may not be performed, and the energy storage device may be charged during the low electricity price period based on the capacity of the energy storage device and the difference, thereby reducing the purchase of electricity during the peak electricity price period and thus reducing electricity costs.

[0134] Step 7: During the forecast day, the power consumption of all electrical devices and the power generation of photovoltaic power generation equipment are periodically collected, and the second photovoltaic power generation and second power demand in each set time period are periodically determined. The charging and discharging of the energy storage device is controlled according to the source-grid-load-storage coordinated power supply mechanism.

[0135] The time period is set according to the experience of those skilled in the art or according to actual application scenarios, and the embodiments of the present application are not limited to this.

[0136] Preferably, the time for periodically collecting electricity consumption and power generation is set during the train operation period, and the second photovoltaic power generation and the second electricity demand are also determined during the train operation period. The period of the set time period is set to 10 minutes, 30 minutes, 1 hour or 2 hours, etc.

[0137] The photovoltaic power generation and electricity demand are predicted on the day before the forecast day using historical data and forecast data. Due to the instability of the forecast data, there will be deviations between the forecast results and the actual photovoltaic power generation and electricity demand. To ensure the normal operation of trains and stations and the stability of the power system, it is necessary to pay real-time attention to photovoltaic power generation and electricity demand on the forecast day.

[0138] By periodically collecting real-time data from power-consuming equipment and photovoltaic power generation equipment and conducting intelligent forecasting, flexible adjustments can be made based on the actual energy supply and demand situation, improving the efficiency and response speed of energy scheduling, ensuring the balance between power supply and demand, reducing the risk of power outages caused by supply and demand mismatch, and ensuring the stability and economy of power supply.

[0139] Exemplarily, the above-mentioned source-grid-load-storage coordinated power supply mechanism is as follows: in the power supply link, photovoltaic power generation is used first, followed by energy storage devices. When photovoltaic power generation and energy storage devices cannot meet the power demand of trains and stations, electricity is obtained from the grid through traction substations; in the power consumption link, the energy storage device will only consume excess electricity through charging if there is still surplus electricity after the power demand of trains and stations is met.

[0140] Specifically, in step 7, periodically determining the second photovoltaic power generation and the second electricity demand in each set time period includes:

[0141] Step 71: Determine whether the current time is the end time of any set time period. If so, extract all power values ​​within any set time period to generate a first power time series, where the power is photovoltaic power generation or power demand.

[0142] Step 72: With the prediction day as the center point, set a first time window, and search the first historical data for a second electric power time series whose Euclidean distance from the first electric power time series is less than or equal to a second preset value based on the first time window, wherein the number of data in any second electric power time series is the same as the number of data in the second electric power time series, and the prediction day is expressed in month and day.

[0143] Step 73: determine whether the number of all second power time series is greater than or equal to the third preset value. If so, proceed to step 74; if not, adjust the first time window according to the first preset rule, and then return to step 72.

[0144] Step 74: Filter out a third electric power time series from all second electric power time series based on a second preset rule.

[0145] Step 75: Calculate a fourth electric power time series within a set time period next to any set time period based on the third electric power time series;

[0146] Step 76: Calculate the second power amount for the next set time period based on the fourth power amount time series.

[0147] The values ​​of the second preset value, the third preset value and the first time window are set according to the experience of those skilled in the art or according to actual application scenarios, and are not limited in this regard in the embodiments of the present application.

[0148] Exemplarily, the collection cycle of photovoltaic power generation and electricity demand is 5 minutes, the set time cycle is 30 minutes, and the first power time series generated at the end time (11:00) of the set time period 10:30-11:00 is (a1, a2, ..., a6, a7), where a1 is the power collected at 10:30 and a7 is the power collected at 11:00.

[0149] The forecast day is represented by month and day. When selecting historical data, the historical data within the first time window of the same year and different years are selected with the forecast day as the center. For example, the first time window is 40 days and the forecast day is April 1, then the historical data from March 12 to April 20 in the current year and the previous three years are selected to obtain the second electric power time series.

[0150] When the number of second power time series is less than the third preset value, the number of second power time series may be too small to accurately capture patterns and trends in the historical data, making it impossible to perform effective statistical testing, resulting in a decrease in the accuracy of the prediction results. In this case, the first time window can be adjusted to 50 days to increase the first time window and further obtain more historical data.

[0151] Specifically, step 74 includes:

[0152] Step 741: Filter out all the second power time series corresponding to the date with the same average temperature as the forecast day, and define them as the first candidate time series, wherein the first candidate time series does not include the power time series of the forecast day.

[0153] Step 742: Set a second time window with the forecast day as the center point, and select a pending time series within the second time window from the first candidate time series based on the second time window, and define it as the second candidate time series.

[0154] Step 743: Set a third time window with the current moment as the center point, and obtain a pending time sequence within the third time window from the second candidate time sequence based on the third time window, which is defined as a third candidate time sequence.

[0155] Step 744 , determining whether the number of the third pending time series is greater than or equal to a fourth preset value; if so, defining the third pending time series as a third electric energy time series; if not, proceeding to step 745 .

[0156] Step 745: Determine whether the width of the third time window is the preset threshold. If so, adjust the second time window according to the second preset rule, and then return to step 742. If not, adjust the third time window according to the third preset rule, and then return to step 743.

[0157] The fourth preset value, the preset threshold, the value of the second time window and the value of the third time window are set according to the experience of technical personnel in this field or according to the actual application scenario, and the embodiments of the present application are not limited to this.

[0158] If the electricity time series of the same day is selected for forecasting, it may be affected by specific short-term events or instantaneous fluctuations on that day. Therefore, when screening the first candidate time series, the electricity time series of the forecast day is excluded.

[0159] The second time window is smaller than or equal to the first time window. Since photovoltaic power generation and pedestrian traffic are affected by seasonal and cyclical variations, for example, seasonal variations in sunshine duration and solar altitude affect photovoltaic power generation, while pedestrian traffic can vary with temperature or holidays, selecting data within the second time window ensures that seasonal and cyclical variations are taken into account.

[0160] As described above, by setting the third time window and selecting the data in the second time window, it is possible to ensure that the prediction model can accurately reflect the changes in power generation close to the current time point, thereby improving the accuracy of the prediction value.

[0161] For example, if the third time window is 60 minutes, when the third time window is adjusted for the first time according to the third preset rule, the third time window is adjusted to 80 minutes. If the second time window is 8 days, when the second time window is adjusted for the first time according to the second preset rule, the second time window is adjusted to 10 days.

[0162] Specifically, step 75 includes:

[0163] Obtaining a fifth electric power time series corresponding to the next set time period of each third electric power time series;

[0164] The weighted average of the i-th values ​​in all fifth power time series is used as the i-th power value in the fourth power time series, where i is a positive integer from 1 to I, and I is the total number of power data in the fourth power time series.

[0165] Preferably, the weight coefficient of the fifth electric power time series corresponding to any third electric power time series is set according to the Euclidean distance between any third electric power time series and the first electric power time series.

[0166] For example, there are two fifth power time series, namely S1: (b1, b2, ..., b6, b7) and S2: (c1, c2, ..., c6, c7), the weight coefficient of S1 is k1, the weight coefficient of S2 is k2, then the fourth power time series is ( , ,..., ), add up all the values ​​in the fourth electric energy time series to obtain the second electric energy for the next set time period.

[0167] The second amount of electricity calculated based on the electricity consumption data is the second electricity demand, and the second amount of electricity calculated based on the power generation data is the second photovoltaic power generation.

[0168] According to the technical solution of the present invention, photovoltaic power generation and electricity demand can be accurately predicted in a short period of time based on actual data and historical data, and then the energy supply and demand can be flexibly adjusted, thereby improving the performance of the energy management system and ensuring the stability of the power supply.

[0169] Figure 2 The figure shows a schematic diagram of an embodiment of an energy control system based on source-grid-load-storage power supply provided by the present invention. Figure 2 As shown, the system includes: a data acquisition module 10 , a first prediction module 20 , a first control module 30 , a second prediction module 40 and a second control module 50 .

[0170] The data acquisition module 10 is used to acquire first historical data and predicted data of the traction substation area at a set time on the current date.

[0171] The first prediction module 20 is configured to determine a first photovoltaic power generation and a first electricity demand on a prediction day based on the first historical data and the prediction data, wherein the prediction day is the day after the current day.

[0172] The first control module 30 is configured to obtain the amount of storage capacity in the energy storage device, calculate the difference between the first available power and the first power demand, and when the difference is less than or equal to a first preset value, establish a cost objective function based on the capacity of the energy storage device, the difference, the operating loss and maintenance loss of the energy storage device, and the predicted electricity price cost for each time period within the day, solve the cost objective function to obtain the charging time and charging capacity for charging the energy storage device, and charge the energy storage device based on the charging time and charging capacity, wherein the first available power is the sum of the first photovoltaic power generation and the storage capacity.

[0173] The second prediction module 40 is used to periodically collect the power consumption of all power-consuming devices and the power generation of photovoltaic power generation equipment within the prediction day, and periodically determine the second photovoltaic power generation and the second power demand within each set time period.

[0174] The second control module 50 is used to control the charging and discharging of the energy storage device according to the source-grid-load-storage coordinated power supply mechanism.

[0175] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, wherein the computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute any one of the above-mentioned energy control methods based on source-grid-load-storage power supply.

[0176] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0177] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The above-described program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0178] The above embodiments merely represent preferred implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. An energy control method based on source-grid-load-storage power supply, characterized in that: The steps include: Step 1: obtaining first historical data and forecast data of the traction substation area at a set time on the current date; Step 2: determining a first photovoltaic power generation and a first electricity demand on a forecast day based on the first historical data and the forecast data, wherein the forecast day is the day after the current date; Step 3: Obtain the amount of stored electricity in the energy storage device, and calculate the difference between a first available amount of electricity and the first electricity demand, wherein the first available amount of electricity is the sum of the first photovoltaic power generation and the stored electricity; Step 4: Determine whether the difference is less than or equal to a first preset value. If so, proceed to step 7; if not, proceed to step 5. Step 5: Establishing a cost objective function based on the capacity of the energy storage device, the difference, and the electricity price cost for each time period within the predicted day, and solving the cost objective function to obtain the charging time and charging power for charging the energy storage device; Step 6: charging the energy storage device based on the charging time and the charging amount; Step 7: During the forecast day, periodically collect the power consumption of all electrical devices and the power generation of photovoltaic power generation equipment, periodically determine the second photovoltaic power generation and the second power demand within each set time period, and control the charging and discharging of the energy storage device according to the source-grid-load-storage coordinated power supply mechanism; The first historical data includes actual photovoltaic power generation and predicted photovoltaic power generation for each day within a first preset time period before the predicted day, and the predicted data includes predicted weather data and predicted sunlight data. In step 2, determining the first photovoltaic power generation for the predicted day based on the first historical data and the predicted data includes: Step 211: determine whether the current date is a specific date. If so, proceed to step 222; if not, proceed to step 215; Step 222: Calculate the sum of the actual photovoltaic power generation on all dates within the first preset time period and define it as a first value. Then calculate the ratio of the first value to the first adjustment parameter and define it as a first ratio. Step 213: Determine whether the first ratio is greater than or equal to a preset reference value. If so, proceed to step 214; if not, proceed to step 215. Step 214: Calculate the sum of the predicted photovoltaic power generation for all dates within the first preset time period and define it as a second value. Generate a second adjustment parameter based on the first value, the second value, and the first adjustment parameter. Then define the second adjustment parameter as the first adjustment parameter. The calculation formula for the second adjustment parameter is: ， Among them, AP2 is the second adjustment parameter, E A is the first value, E P is the second value, and AP1 is the first adjustment parameter; Step 215: Input the forecast data into a preset model to obtain a second photovoltaic power generation on the forecast day, calculate the product of the second photovoltaic power generation and the first adjustment parameter, and define it as the first photovoltaic power generation.

2. The method according to claim 1, characterized in that After step 214, the following steps are further included: Calculating a ratio of the first value to the second value and defining the ratio as a second ratio; Determine whether the second ratio is within a preset interval; if not, determine whether the specific date is a first-category specific date; if not, send a reminder message to the staff.

3. The method according to claim 1, characterized in that The first historical data includes a first actual power consumption and a first actual temperature value in each preset time period of each day within a second preset time period before the predicted day, and the predicted data includes predicted weather data. In step 2, determining the first power demand on the predicted day based on the first historical data and the predicted data includes: Step 221: Determine the date type of the predicted day, the air conditioner operation mode, and the predicted temperature value for each of the preset time periods, wherein the date type is a weekday, weekend, or statutory holiday, and the air conditioner operation mode is cooling, heating, or off; Step 222: Calculate the average value of the first actual power consumption corresponding to any preset time period within the second preset time, which is defined as the first power average value, and calculate the average value of the first actual temperature corresponding to any preset time period within the second preset time, which is defined as the first temperature average value; Step 223: Based on the date type and the air conditioner operation mode, select a corresponding power forecast model for any preset time period within the forecast day, then input the date type, the predicted temperature value, the first average power value, and the first average temperature value corresponding to any preset time period into the power forecast model corresponding to any preset time period to obtain the power demand corresponding to any preset time period within the forecast day; Step 224 : Repeat step 223 , and after traversing all preset time periods, define the sum of the power demand amounts corresponding to all the preset time periods as the first power demand amount.

4. The method according to claim 3, characterized in that In step 223, the method for constructing the power prediction model is: Step 2231: Extract second historical data within a third preset time, pre-process the second historical data, and generate third historical data, wherein the second historical data includes the date type, the air conditioner operation mode, and the second actual power consumption and the second actual temperature value within each preset time period of each day within the third preset time period. Step 2232: For any day within the third preset time period, calculate the average value of the second actual power usage corresponding to any preset time period within the second preset time period before the any day, defining it as a second average power value, and calculate the average value of the second actual temperature corresponding to any preset time period within the second preset time period before the any day, defining it as a second average temperature value. Then, store the second average power value and the second average temperature value in correspondence with the data of the any day. Step 2233: After traversing all dates within the third preset time, generate fourth historical data, and then divide the fourth historical data into N data sets based on the date type, the air conditioner operation mode, and the preset time period; Step 2234: Use the actual power consumption as the dependent variable, the actual temperature value, the m-th power of the actual temperature value, the date type, the second average power consumption, and the second average temperature value as independent variables to construct a linear equation containing a constant parameter; Step 2235: extract any data set, use any of the data sets to fit the linear equation, determine the weight coefficient corresponding to each independent variable, and substitute it into the linear equation to generate an electricity prediction model corresponding to any of the data sets.

5. The method according to claim 1, wherein In step 7, the periodic determination of the second photovoltaic power generation and the second electricity demand in each set time period includes: Step 71: Determine whether the current time is the end time of any set time period. If so, extract all power values ​​within any set time period to generate a first power time series, where the power values ​​are photovoltaic power generation or power demand. Step 72: With the forecast day as the center point, set a first time window, and search the first historical data based on the first time window for a second electric energy time series whose Euclidean distance from the first electric energy time series is less than or equal to a second preset value, wherein the number of data in any second electric energy time series is the same as the number of data in the second electric energy time series, and the forecast day is represented by month and day; Step 73: Determine whether the number of all the second electric energy time series is greater than or equal to a third preset value. If so, proceed to step 74; if not, adjust the first time window according to the first preset rule, and then return to step 72. Step 74: Filter out a third electric power time series from all the second electric power time series based on a second preset rule; Step 75: Calculate a fourth electric energy time series within a set time period next to any of the set time periods based on the third electric energy time series; Step 76: Calculate the second power amount for the next set time period based on the fourth power amount time series.

6. The method according to claim 5, characterized in that The step 74 includes: Step 741: Filter out all the second power time series corresponding to the date with the same average temperature as the predicted day, and define them as first candidate time series, wherein the first candidate time series does not include the power time series of the predicted day; Step 742: Set a second time window with the forecast day as the center point, and select a candidate time series within the second time window from the first candidate time series based on the second time window, defining the second candidate time series as the second candidate time series. Step 743: Set a third time window with the current moment as the center point, and obtain a pending time sequence within the third time window from the second candidate time sequence based on the third time window, defining the third candidate time sequence as a third candidate time sequence. Step 744: Determine whether the number of the third candidate time series is greater than or equal to a fourth preset value. If so, define the third candidate time series as a third electric energy time series. If not, proceed to step 745. Step 745: Determine whether the width of the third time window is a preset threshold. If so, adjust the second time window according to the second preset rule, and then return to step 742. If not, adjust the third time window according to the third preset rule, and then return to step 743.

7. The method according to claim 5, characterized in that The step 75 includes: Obtaining a fifth electric power time series corresponding to the next set time period of each of the third electric power time series; The weighted average of the i-th values ​​in all the fifth electric energy time series is used as the i-th electric energy value in the fourth electric energy time series, where i is a positive integer from 1 to I, and I is the total number of electric energy data in the fourth electric energy time series.

8. An energy control system based on source-grid-load-storage power supply, used to implement the method according to any one of claims 1 to 7, characterized in that: include: A data acquisition module, a first prediction module, a first control module, a second prediction module, and a second control module; The data acquisition module is used to acquire first historical data and forecast data of the traction substation area at a set time on the current date; The first prediction module is configured to determine a first photovoltaic power generation and a first electricity demand on a prediction day based on the first historical data and the prediction data, wherein the prediction day is a day after the current date; The first control module is configured to obtain the amount of storage capacity in the energy storage device, calculate the difference between a first available amount of power and the first power demand, and when the difference is less than or equal to a first preset value, establish a cost objective function based on the capacity of the energy storage device, the difference, the operating loss and maintenance loss of the energy storage device, and the electricity price cost for each time period within the predicted day, solve the cost objective function to obtain a charging time and a charging amount for charging the energy storage device, and charge the energy storage device based on the charging time and the charging amount, wherein the first available amount of power is the sum of the first photovoltaic power generation and the stored amount; The second prediction module is used to periodically collect the power consumption of all power-consuming devices and the power generation of photovoltaic power generation equipment during the prediction day, and periodically determine the second photovoltaic power generation and the second power demand in each set time period; The second control module is used to control the charging and discharging of the energy storage device according to the source-grid-load-storage coordinated power supply mechanism.

9. A computer storage medium, characterized in that The computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images