Energy management method, apparatus, device, medium, and product

Abstract

The present disclosure relates to the technical field of Internet of Things, and particularly provides an energy management method, device, equipment, medium and product. In the present disclosure, load charging data of a light storage and charging system is acquired; the load charging data is predicted and analyzed based on a preset prediction model to determine predicted transaction data and a predicted operation mode. A power supply module is operated based on the predicted operation mode to obtain actual transaction data; back testing is performed based on the actual transaction data and the predicted transaction data to determine a back testing result. In a case where the back testing result indicates that the predicted operation mode is unreasonable, a target operation mode and power change data of the power supply module indicated by the target operation mode are determined based on the actual transaction data. The power supply module indicated by the target operation mode is operated based on the target operation mode and the power change data. In this way, the power supply strategy can be adjusted more timely, which is conducive to the management of energy, and thus the utilization rate of energy can be improved.

Description

Technical Field

[0001] This disclosure belongs to the field of Internet of Things (IoT) technology, specifically relating to an energy management method, device, equipment, medium, and product. Background Technology

[0002] A photovoltaic-storage-charging system is a comprehensive energy system that integrates photovoltaic power generation, energy storage devices, and charging facilities. It aims to achieve efficient utilization of clean energy, balance power supply and demand, and intelligent energy management, representing an information-based upgrade of traditional photovoltaic power generation systems. By collecting various information data, it can allocate and adjust energy, achieving intelligent energy distribution and safe management.

[0003] Generally, when a load in a photovoltaic-storage-charging system needs charging, the power supply strategy—which involves one or more power modules from the photovoltaic power generation, energy storage device, and external power grid—can be determined based on the SOC (State of Charge) value and maximum charging / discharging power of the energy storage device. After the load has been powered for a period of time, the current power supply strategy is manually checked to ensure it meets the load's power demand. If not, the power supply strategy needs to be manually adjusted. However, manual adjustments may not be timely. Summary of the Invention

[0004] This disclosure is made in view of the above-mentioned problems. This disclosure provides an energy management method, apparatus, equipment, medium, and product that can improve energy utilization efficiency.

[0005] According to one aspect of this disclosure, an energy management method is provided, comprising:

[0006] Acquire load charging data of the photovoltaic-storage-charging system;

[0007] Based on a preset prediction model, the load charging data is predicted and analyzed to determine the predicted transaction data and the predicted operating mode. The predicted operating mode is used to characterize the power supply module used to supply power to the load. The power supply module is the external power grid, a photovoltaic module in the photovoltaic-storage-charging system, and / or an energy storage module. The predicted transaction data is used to characterize the power supply status of the power supply module.

[0008] The power supply module is operated based on the predicted operating mode to obtain actual transaction data;

[0009] Backtesting is performed based on the actual transaction data and the predicted transaction data to determine the backtesting results;

[0010] If the backtest result indicates that the predicted operating mode is unreasonable, the target operating mode and the power change data of the power supply module indicated by the target operating mode are determined based on the actual transaction data.

[0011] Based on the target operating mode and the power change data, the power supply module indicated by the target operating mode is operated.

[0012] Optionally, the backtesting based on the actual transaction data and the predicted transaction data to determine the backtesting results includes:

[0013] The target vector distance is determined based on the vector generated from the actual transaction data and the vector generated from the predicted transaction data.

[0014] The target backtesting accuracy is determined based on the target vector distance and the most recently calculated historical vector distance.

[0015] If the target backtest accuracy is greater than a preset accuracy threshold, the backtest result is determined to indicate that the predicted operation mode is unreasonable.

[0016] If the target backtesting accuracy is less than the preset accuracy threshold, the standard deviation of the backtesting accuracy is determined based on the historical backtesting accuracy calculated in the most recent N times and the target backtesting accuracy. If the standard deviation is greater than the base backtesting accuracy, the backtesting result is determined to indicate that the prediction operation mode is unreasonable, and the base backtesting accuracy is the backtesting accuracy corresponding to the prediction transaction data obtained from the first prediction analysis.

[0017] Optionally, when the backtesting result indicates that the predicted operating mode is unreasonable, determining the target operating mode and the power change data of the power supply module indicated by the target operating mode based on the actual transaction data includes:

[0018] Based on the actual transaction data and the preset energy dispatch strategy, the target operating mode is determined;

[0019] Based on the actual transaction data, preset power change data constraints, and preset objective function, the power change data is determined, and the objective function is used to maximize the net profit of the photovoltaic-storage-charging system.

[0020] Optionally, determining the target operating mode based on the actual transaction data and the preset energy dispatch strategy includes:

[0021] If the total profit data, energy storage change, and grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the total profit data is greater than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is greater than zero in the preset energy dispatch strategy, then the target operating mode is determined to be the photovoltaic operating mode. The photovoltaic operating mode is a mode in which the discharge amount of the photovoltaic module is used to supply power to the load and charge the energy storage module.

[0022] If the total profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the total profit data is less than zero, the energy storage change is less than zero, and the grid-connected charging and discharging amount is less than zero in the preset energy dispatch strategy, then the target operation mode is determined to be the guaranteed operation mode. The guaranteed operation mode is a mode in which the priority of the energy storage module to supply power to the load is lower than that of the photovoltaic module and higher than that of the external power grid.

[0023] If the grid-connected profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the grid-connected profit data is greater than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is less than zero in the preset energy dispatch strategy, then the target operating mode is determined to be the economic operating mode. The economic operating mode is a mode in which the external power grid is used to supply power to the load, and the energy storage module is used for grid-connected power supply.

[0024] If the grid-connected profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions of the preset energy dispatch strategy, where the grid-connected profit data is less than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is less than zero, then the target operating mode is determined to be the off-grid operating mode. The off-grid operating mode is a mode in which the photovoltaic module charges the energy storage module and the energy storage module supplies power to the load.

[0025] Optionally, determining the electricity change data based on the actual transaction data, preset electricity change data constraints, and a preset objective function includes:

[0026] Based on the grid-connected profit data in the actual transaction data and the preset power change data constraints, the preset objective function is calculated to determine the power change data. The preset objective function is the mapping relationship between the grid-connected profit data, the power change data and the electricity cost. The preset power change data constraint is that the power change data equals the load power demand.

[0027] Optionally, the step of operating the power supply module indicated by the target operating mode based on the target operating mode and the power change data includes:

[0028] If the difference between the actual transaction data and the preset transaction data is less than or equal to the preset transaction threshold, the power supply module indicated by the target operation mode is run according to the first sub-operation mode of the target operation mode. The first sub-operation mode is to run the indicated power supply module according to the priority of the power supply module within the operation cycle.

[0029] If the difference between the actual transaction data and the preset transaction data is greater than the preset transaction threshold, the power supply module indicated by the target operation mode is run according to the second sub-operation mode of the target operation mode. The second sub-operation mode is to run all the indicated power supply modules from the beginning of the operation cycle until the end of the operation cycle.

[0030] Optionally, acquiring the load charging data of the photovoltaic energy storage and charging system includes:

[0031] Acquire charging data from the photovoltaic-storage-charging system. The charging data includes vehicle type, market electricity price data, charging time period data, charging frequency, charging mode, environmental data, current time data, and power data.

[0032] The vehicle type, the market electricity price data, the charging time period data, the charging mode, and the environmental data are encoded to obtain the first sub-load charging data.

[0033] The power data is normalized to obtain the charging data of the second sub-load;

[0034] The first sub-load charging data, the second sub-load charging data, the charging frequency, and the current time data are used as the load charging data.

[0035] According to another aspect of this disclosure, an energy management device is provided, comprising:

[0036] The acquisition module is used to acquire load charging data of the photovoltaic energy storage and charging system;

[0037] The first determining module is used to perform predictive analysis on the load charging data based on a preset prediction model, and to determine the predicted transaction data and the predicted operating mode. The predicted operating mode is used to characterize the power supply module used to supply power to the load. The power supply module is an external power grid, a photovoltaic module in a photovoltaic-storage-charging system, and / or an energy storage module. The predicted transaction data is used to characterize the power supply status of the power supply module.

[0038] The second determining module is used to run the power supply module based on the predicted operating mode to obtain actual transaction data;

[0039] The third determining module is used to perform backtesting based on the actual transaction data and the predicted transaction data, and determine the backtesting results.

[0040] The fourth determining module is used to determine the target operating mode and the power change data of the power supply module indicated by the target operating mode, based on the actual transaction data, when the backtesting result indicates that the predicted operating mode is unreasonable.

[0041] The operation module is used to run the power supply module indicated by the target operation mode based on the target operation mode and the power change data.

[0042] According to another aspect of this disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor running the computer program to implement the above-described energy management method.

[0043] According to another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, the program being executed by a processor to implement the above-described energy management method.

[0044] According to another aspect of this disclosure, a computer program product is provided, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device executes the above-described energy management method.

[0045] This disclosure involves acquiring load charging data from a photovoltaic-storage-charging system; performing predictive analysis on the load charging data based on a pre-set prediction model to determine predicted transaction data and a predicted operating mode. The predicted operating mode characterizes the power supply modules used to supply power to the load, which can be external power grid, photovoltaic modules in the photovoltaic-storage-charging system, and / or energy storage modules. The predicted transaction data characterizes the power supply status of the power supply modules. The power supply modules are operated based on the predicted operating mode to obtain actual transaction data. Backtesting is performed based on the actual transaction data and the predicted transaction data to determine the backtesting results. If the backtesting results indicate that the predicted operating mode is unreasonable, a target operating mode and the power change data of the power supply modules indicated by the target operating mode are determined based on the actual transaction data. The power supply modules indicated by the target operating mode are operated based on the target operating mode and the power change data. By comparing the actual power supply status of the power supply modules supplying power to the load in the real world with the predicted power supply status, it is determined whether the power supply strategy meets the load's power demand. If not, a more suitable power supply strategy and power change data for the upcoming next time period need to be determined. This allows for more timely adjustments to power supply strategies, which is beneficial for energy management and can improve energy utilization.

[0046] It should be understood that both the foregoing general description and the following detailed description are exemplary and intended to provide further illustration of the claimed technology. Attached Figure Description

[0047] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0048] Figure 1 A flowchart of an energy management method provided in this disclosure.

[0049] Figure 2 This is a schematic diagram of the structure of an energy management device provided in this disclosure.

[0050] Figure 3 This is a hardware block diagram of an electronic device provided in this disclosure.

[0051] Figure 4 This is a schematic diagram of a computer program product provided in this disclosure. Detailed Implementation

[0052] To enable those skilled in the art to better understand the technical solution of this application, the application scenario of this application will be described first below.

[0053] A photovoltaic-storage-charging system is a comprehensive energy system that integrates photovoltaic power generation, energy storage devices, and charging facilities. It aims to achieve efficient utilization of clean energy, balance power supply and demand, and intelligent energy management, representing an information-based upgrade of traditional photovoltaic power generation systems. By collecting various data, it can allocate and adjust energy, achieving intelligent energy distribution and safe management. The system primarily utilizes sensors, RFID tags, and IoT devices for data collection, and transmits data and manages the system via wireless communication networks (such as Wi-Fi, 4G, and 5G). Based on an integrated, two-way communication network, the photovoltaic-storage-charging system combines sensing technology, equipment technology, and fixed algorithms to achieve reliable management and safe allocation of photovoltaic power generation systems, energy storage systems, and charging stations, providing users with an intelligent and automated energy management system.

[0054] Currently, when a load in a photovoltaic-storage-charging system needs charging, the power supply strategy—which involves one or more power modules from the photovoltaic power generation, energy storage device, and external power grid—can be determined based on the SOC (State of Charge) value and maximum charging / discharging power of the energy storage device. Specifically, the strategy is as follows: when the energy storage SOC value is lower than the prohibited discharge SOC value, the system stops discharging and prioritizes replenishing the load gap from the external power grid; when the SOC is between the prohibited discharge and prohibited charging SOC values, the system performs timely charging and discharging to minimize power consumption from the external power grid; when the SOC is higher than the prohibited charging SOC value, the system stops charging and prioritizes replenishing the load gap from the external power grid. After the load has been powered for a period of time, it is necessary to manually check whether the current power supply strategy meets the load's power demand. If not, manual adjustment of the power supply strategy is required. However, manual adjustment may result in delayed responses.

[0055] To address the aforementioned technical problems, this disclosure provides an energy management method, apparatus, equipment, medium, and product. In this disclosure, load charging data from a photovoltaic-storage-charging system is acquired; the load charging data is predicted and analyzed based on a preset prediction model to determine predicted transaction data and a predicted operating mode. The predicted operating mode characterizes the power supply module used to supply power to the load, which may be an external power grid, a photovoltaic module in the photovoltaic-storage-charging system, or an energy storage module; the predicted transaction data characterizes the power supply status of the power supply module. The power supply module is operated based on the predicted operating mode to obtain actual transaction data; backtesting is performed based on the actual transaction data and the predicted transaction data to determine the backtesting results. If the backtesting results indicate that the predicted operating mode is unreasonable, a target operating mode and the power change data of the power supply module indicated by the target operating mode are determined based on the actual transaction data. The power supply module indicated by the target operating mode is operated based on the target operating mode and the power change data. By comparing the actual power supply status of the power supply module supplying power to the load in the real world with the predicted power supply status, it is determined whether the power supply strategy meets the load's power demand. If not, a power supply strategy and power change data more suitable for the upcoming next time period to meet the load's power demand need to be determined. This allows for more timely adjustments to power supply strategies, which is beneficial for energy management and can improve energy utilization.

[0056] To make the objectives, technical solutions, and advantages of this disclosure more apparent, exemplary embodiments according to this disclosure will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments of this disclosure. It should be understood that this disclosure is not limited to the exemplary embodiments described herein.

[0057] Figure 1 A flowchart illustrating an energy management method provided in this disclosure. Figure 1 As shown, the method includes:

[0058] S101: Obtain load charging data of the photovoltaic energy storage and charging system.

[0059] Specifically, in this embodiment, the load charging data in the photovoltaic-storage-charging system can be acquired and stored through the acquisition module. This load charging data includes charging frequency, current time data, power data, and data stored in a coded manner. Acquiring load charging data across multiple dimensions can improve the accuracy of training the prediction model, thereby improving the accuracy of predicting transaction data and operational patterns.

[0060] S102: Based on a preset prediction model, perform predictive analysis on load charging data to determine predicted transaction data and predicted operating mode.

[0061] Specifically, feature extraction is performed on load charging data to obtain a data feature set. Based on a pre-set prediction model, predictive analysis is conducted on the data feature set to determine the predicted transaction data and the predicted operating mode. The predicted operating mode characterizes the power supply module used to supply power to the load, which can be the external power grid, photovoltaic modules in a photovoltaic-storage-charging system, or energy storage modules. The predicted transaction data is used to characterize the power supply status of the power supply module. This data can include: total profit data P (a positive total profit indicates the photovoltaic-storage-charging system is profitable that day, a negative total profit indicates a loss); energy storage change ΔE (the change in energy storage module power reflects the charging and discharging status of the photovoltaic-storage-charging system; a greater than zero change indicates the module is charging, a less than zero change indicates discharging); grid-connected charging and discharging amount Q (reflecting the system's supply to or from the external grid; a greater than zero amount indicates the system is receiving power from the grid, a less than zero amount indicates supplying power); and grid-connected profit data R (a positive grid-connected profit indicates the system is profitable through grid connection, a negative result indicates a loss). Among them, grid connection refers to the grid situation in which the photovoltaic, energy storage and charging system and the external power grid work together.

[0062] In this embodiment, the prediction model can be an LSTM model, and the preset prediction interval period is T, that is, prediction and backtesting are performed every time T.

[0063] S103: The power supply module operates based on the predictive operation mode to obtain actual transaction data.

[0064] Specifically, the power supply module, characterized by the predicted operating mode, can supply power to the load. During actual operation, actual transaction data will be generated. The predicted transaction data obtained through the prediction model may contain certain errors, while the actual transaction data determined by the actual operating power supply module is the true value of the real world. Determining the actual transaction data can be used for subsequent backtesting verification of the predicted operating mode.

[0065] S104: Conduct backtesting based on actual transaction data and predicted transaction data, and determine the backtesting results.

[0066] Specifically, backtesting involves correcting and verifying the output of the prediction model. The backtesting accuracy, or backtesting result, can be calculated using actual trading data and predicted trading data. The backtesting result includes indicators of whether the prediction operation mode is unreasonable and indicators of whether the prediction operation mode is reasonable.

[0067] S105: If the backtest results indicate that the predicted operating mode is unreasonable, determine the target operating mode and the power change data of the power supply module indicated by the target operating mode based on the actual transaction data.

[0068] Specifically, when the predicted operating mode is unreasonable, the predicted energy dispatch strategy, i.e. the predicted operating mode, is replaced according to the actual transaction data. The operation is started according to the target operating strategy that conforms to the actual transaction data. The power change data of the power supply module indicated by the target operating mode can be calculated and determined through the actual transaction data, so as to determine the amount of power that each power supply module needs to provide or purchase under the actual transaction data.

[0069] S106: Based on the target operating mode and power change data, operate the power supply module indicated by the target operating mode.

[0070] Specifically, the power supply module operates according to the target operating mode and power change data, so that the photovoltaic-storage-charging system can operate under the optimal strategy for a long time. This can achieve safe and reasonable energy allocation between the photovoltaic-storage-charging system and the external power grid, improve the accuracy of energy allocation and safety control, and increase energy utilization.

[0071] In one possible implementation, an exemplary method for determining backtesting results based on actual transaction data and predicted transaction data includes:

[0072] The distance to the target vector is determined based on the vector generated from actual transaction data and the vector generated from predicted transaction data.

[0073] Specifically, as mentioned above, actual transaction data and predicted transaction data include total profit data, energy storage change, grid-connected charging and discharging volume, and grid-connected profit data, respectively. Vector distance can represent the degree of similarity between the two.

[0074] The target vector distance can be calculated using the following formula:

[0075]

[0076] in, The distance to the target vector. A vector of total profit data from actual transactions. This is a vector representing the changes in energy storage based on actual transaction data. This is a vector of grid-connected charging and discharging quantities based on actual transaction data. A vector of actual transaction data and grid-connected profit data. This is a vector of total profit data for predicting trading data. This is a vector representing the change in energy storage in the transaction data. To predict the vector of grid-connected charging and discharging quantities in transaction data, A vector for predicting the grid connection profit data from transaction data.

[0077] The target backtesting accuracy is determined based on the target vector distance and the most recently calculated historical vector distance.

[0078] Specifically, the target backtesting accuracy rate can verify the accuracy of the predicted trading data, and can be calculated using the following formula:

[0079]

[0080] Among them, P n To achieve the target backtest accuracy, The distance to the target vector. This is the historical vector distance obtained in the most recent calculation.

[0081] If the target backtest accuracy is greater than the preset accuracy threshold, the backtest result is determined to indicate that the prediction operation mode is unreasonable.

[0082] Specifically, in this embodiment, the preset accuracy threshold can be 100%. When the target backtest accuracy is greater than 100%, it indicates that the actual transaction data obtained by running the power supply module according to the prediction operation mode is seriously deviating from the predicted transaction data. At this time, the prediction operation mode is unreasonable and the power supply module needs to be adjusted.

[0083] If the target backtest accuracy is less than the preset accuracy threshold, the standard deviation of the backtest accuracy is determined based on the historical backtest accuracy calculated in the most recent N times and the target backtest accuracy. If the standard deviation is greater than the baseline backtest accuracy, the backtest result is determined to indicate that the prediction operation mode is unreasonable.

[0084] Specifically, when the target backtest accuracy is less than 100%, the prediction operation mode may or may not be reasonable. The average backtest accuracy of the most recent 10 and 5 tests can be calculated separately, and the standard deviation of the average backtest accuracy can be determined using the following formula:

[0085]

[0086] Among them, P n Standard deviation This is the average accuracy of the last 5 backtests. This is the average accuracy of the most recent 10 backtests.

[0087] When the standard deviation exceeds the baseline backtest accuracy, it indicates that the actual transaction data obtained from operating the power supply module according to the predictive operation mode deviates too much from the predicted transaction data. In this case, the predictive operation mode is unreasonable, and the power supply module needs to be adjusted. The baseline backtest accuracy is the backtest accuracy corresponding to the predicted transaction data obtained from the first predictive analysis.

[0088] In one possible implementation, when the backtesting results indicate that the predicted operating mode is unreasonable, an exemplary method for determining the target operating mode and the power supply module's power change data indicated by the target operating mode based on actual transaction data includes:

[0089] Based on actual transaction data and preset energy dispatch strategies, the target operating mode is determined.

[0090] Specifically, the preset energy dispatch strategy is a method for determining the operating mode based on the positive or negative status or charging / discharging status of transaction data. Therefore, the target operating mode that meets the actual operation can be determined based on the correspondence between the actual transaction data obtained from the actual operation of the photovoltaic-storage-charging system and the dispatch strategy, that is, the power supply module used to supply power to the load can be determined.

[0091] The electricity change data is determined based on actual transaction data, preset electricity change data constraints, and preset objective function.

[0092] Example location:

[0093] Based on the grid connection profit data in the actual transaction data and the preset constraints of power change data, the preset objective function is calculated to determine the power change data.

[0094] Specifically, the preset objective function is the mapping relationship between grid-connected profit data, target business electricity consumption data, and electricity costs. This objective function aims to maximize the net profit of the photovoltaic-storage-charging system. In other words, the objective function can be used to calculate how much electricity change data is needed to maximize the operating profit of the photovoltaic-storage-charging system. The electricity change data can be calculated using the following formula:

[0095] max(RC grid ×X grid -C pv ×X pv -C storage ×X storage )

[0096] Where R represents grid-connected profit data, and C... grid X is the cost of purchasing electricity from the external grid. grid C represents the amount of electricity purchased from external power grids. pv X is the cost of generating electricity from photovoltaic modules. pv C represents the amount of electricity generated by the photovoltaic module. storage X storage This refers to the charging and discharging capacity of the energy storage module.

[0097] It is important to note that the calculation process must meet preset constraints on power change data, which stipulate that the power change data must equal the load's power demand. Furthermore, in this embodiment, the power change data includes the power purchased from the external grid, the power generated by the photovoltaic module, and the charging and discharging power of the energy storage module. The maximum power generation capacity of the photovoltaic module, the maximum charging and discharging capacity of the energy storage module, and the maximum power purchased from the external grid are preset. The final determined power generation of the photovoltaic module must be greater than or equal to zero and less than or equal to the maximum power generation capacity of the photovoltaic module; the power purchased from the external grid must be greater than or equal to zero and less than or equal to the maximum power purchased from the external grid; and the charging and discharging power of the energy storage module must be greater than or equal to the negative maximum charging and discharging capacity of the energy storage module and less than or equal to the maximum charging and discharging capacity of the energy storage module.

[0098] In one possible implementation, an exemplary method for determining the target operating mode based on actual transaction data and a preset energy dispatch strategy includes:

[0099] If the total profit data, energy storage change, and grid-connected charging and discharging volume in the actual transaction data meet the conditions that the total profit data, energy storage change, and grid-connected charging and discharging volume are all greater than zero in the preset energy dispatch strategy, then the target operation mode is determined to be the photovoltaic operation mode.

[0100] Specifically, when the total profit data P>0 in the actual transaction data, the change in energy storage ΔE>0, and the grid-connected charging and discharging amount Q>0, it indicates that the photovoltaic-storage-charging system is profitable on that day, the energy storage module is charging on that day, and the photovoltaic-storage-charging system obtains electricity from the external grid on that day. The target operating mode is determined to be the photovoltaic operating mode. In this mode, the photovoltaic module is prioritized for powering the load; that is, the photovoltaic operating mode uses the discharge of the photovoltaic module to power the load and charge the energy storage module. Furthermore, if the load's electricity consumption is detected to be greater than the photovoltaic module's power generation in this mode, it indicates that the prediction analysis for this operating cycle has a large error, and a new round of prediction needs to be initiated immediately to adjust the operating mode based on the prediction results.

[0101] If the total profit data, energy storage change, and grid-connected charging and discharging volume in the actual transaction data meet the conditions that the total profit data, energy storage change, and grid-connected charging and discharging volume are all less than zero in the preset energy dispatch strategy, then the target operation mode is determined as the guaranteed operation mode.

[0102] Specifically, if the total profit data P in the actual transaction data is less than 0, the change in energy storage ΔE is less than 0, and the grid-connected charging and discharging amount Q is less than 0, it indicates that the photovoltaic-storage-charging system incurs a loss on that day, the energy storage module discharges on that day, and the photovoltaic-storage-charging system supplies power to the external grid on that day. In this case, the target operating mode is determined to be the guaranteed operating mode. The guaranteed operating mode prioritizes energy storage modules supplying power to the load over photovoltaic modules, but prioritizes the external grid. In other words, under this mode, photovoltaic modules are used first to generate electricity. If the photovoltaic modules' power generation is insufficient, the energy storage modules' power is activated. If the energy storage modules' power generation is insufficient, the system connects to the external grid for power.

[0103] If the grid-connected profit data, energy storage change, and grid-connected charging and discharging volume in the actual transaction data meet the conditions of the preset energy dispatch strategy, where the grid-connected profit data is greater than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging volume is less than zero, then the target operating mode is determined to be the economic operating mode.

[0104] Specifically, if the grid-connected profit data R > 0 in the actual transaction data, the energy storage change ΔE > 0, and the grid-connected charging and discharging amount Q < 0, it indicates that the photovoltaic-storage-charging system has obtained profit through grid connection on that day, the energy storage module is charged on that day, and the photovoltaic-storage-charging system supplies power to the external grid on that day. Therefore, the target operating mode is determined to be the economic operating mode. The economic operating mode is a mode in which the external grid is used to supply power to the load, and the energy storage module is used for grid-connected power supply. In other words, under this mode, the external grid can be directly used for charging, and the energy stored module's power can be used to supply power to the grid.

[0105] If the grid-connected profit data, energy storage change, and grid-connected charging and discharging volume in the actual transaction data meet the conditions of the preset energy dispatch strategy, where the grid-connected profit data is less than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging volume is less than zero, then the target operating mode is determined to be the off-grid operating mode.

[0106] Specifically, if the grid-connected profit data R < 0 in the actual transaction data, the energy storage change ΔE > 0, and the grid-connected charging and discharging amount Q < 0, it indicates that the photovoltaic-storage-charging system incurred a loss through grid connection on that day, the energy storage module was charged on that day, and the photovoltaic-storage-charging system supplied power to the external grid on that day. Therefore, the target operating mode is determined to be the off-grid operating mode. The off-grid operating mode is a mode where the photovoltaic module charges the energy storage module, and the energy storage module supplies power to the load. In other words, under this mode, the grid can operate independently without relying on the external grid, providing power entirely through photovoltaic module power generation and energy storage module power supply to the load.

[0107] In one possible implementation, an exemplary method for operating a power supply module indicated by a target operating mode based on a target operating mode and power change data includes:

[0108] If the difference between the actual transaction data and the preset transaction data is less than or equal to the preset transaction threshold, the power supply module indicated by the target operation mode is run according to the first sub-operation mode of the target operation mode.

[0109] Specifically, in the first sub-operation mode, the photovoltaic-storage-charging system adopts a relatively balanced strategy, comprehensively utilizing various energy sources. The first sub-operation mode operates according to the priority of the power supply modules within the operating cycle. For example, when the target operating mode is the guaranteed operation mode, the first sub-operation mode represents a strategy that prioritizes the use of photovoltaic module power generation. If the photovoltaic module power generation is insufficient, the energy storage module's power is activated. If the energy storage module's power is insufficient, the system connects to the external power grid, operating the power supply modules indicated by the guaranteed operation mode.

[0110] If the difference between the actual transaction data and the preset transaction data is greater than the preset transaction threshold, the power supply module indicated by the target operation mode will be run according to the second sub-operation mode of the target operation mode.

[0111] Specifically, in the second sub-operation mode, the photovoltaic-storage-charging system will adopt a strategy that primarily relies on or reduces the use of certain energy sources. The second sub-operation mode operates all indicated power supply modules from the start of the operating cycle until its end. For example, when the target operating mode is the guaranteed operating mode, the second sub-operation mode represents a strategy that directly uses photovoltaic modules, energy storage modules, and the external power grid to jointly power the load, operating the power supply modules indicated by the guaranteed operating mode.

[0112] In one possible implementation, an exemplary method for acquiring load charging data of a photovoltaic energy storage and charging system includes:

[0113] Acquire charging data from the photovoltaic-storage-charging system.

[0114] Specifically, the data acquisition module can collect charging data from the photovoltaic-storage-charging system. This data includes vehicle type, market electricity price data, charging time period data, charging frequency, charging mode, environmental data, current time data, and power data. Vehicle types include private cars, commercial vehicles, and special vehicles. Charging time period data includes: morning (from sunrise to noon, 6:00 AM to 10:00 AM); noon (11:00 AM to 1:00 PM); afternoon (1:00 PM to 6:00 PM); evening (around sunset, 6:00 PM to 8:00 PM); night (8:00 PM to midnight); and late night (midnight to early morning, midnight to 6:00 AM). The charging time period refers to the time from start to finish charging and can be counted in seconds. Market electricity price data includes market electricity price models, i.e., market price gradients, market price segments, average market price, and prices at different stages. The data includes: electricity price for charging at the same stage and service fees for charging at different stages; charging frequency (number of charges per day); charging modes (fast charging and slow charging); environmental data (weather conditions such as sunny days, ambient temperature, ambient humidity, and light intensity); current time data (date, time, and rest days); and power data (PV power generation, PV power output, PV radiation, PV radiation intensity, energy storage charging, energy storage discharging, energy storage charging power, energy storage discharging power, SOC (state of charge), the ratio of stored energy to maximum capacity, SOH (state of health), grid-connected charging, grid-connected discharging, grid-connected charging power, and grid-connected discharging power).

[0115] In addition, in this embodiment, the acquisition module can be built into the optical storage and charging system, or it can be set outside the optical storage and charging system for connection and acquisition.

[0116] The vehicle type, market electricity price data, charging time period data, charging mode and environmental data are encoded to obtain the first sub-load charging data; the power data is normalized to obtain the second sub-load charging data; the first sub-load charging data, the second sub-load charging data, the charging frequency and the current time data are used as the load charging data.

[0117] Specifically, for enumerated data such as vehicle type, market electricity price data, charging time period data, charging mode, and environmental data, different types can be digitally encoded. For example, private cars can be encoded as 1, commercial vehicles as 2, and special vehicles as 3, etc., to obtain the first sub-load charging data. The electricity data can be normalized to make the data range between [0, 1] to obtain the second sub-load charging data. Finally, the first sub-load charging data, the second sub-load charging data, the charging frequency, and the current time data can be used as load charging data for subsequent predictive analysis.

[0118] Figure 2 This is a schematic diagram of the structure of an energy management device provided in this disclosure. Figure 2 As shown, the device 200 includes: an acquisition module 210, a first determination module 220, a second determination module 230, a third determination module 240, a fourth determination module 250, and an operation module 260.

[0119] The acquisition module 210 is used to acquire load charging data of the photovoltaic energy storage and charging system;

[0120] The first determining module 220 is used to perform predictive analysis on the load charging data based on a preset prediction model, and to determine the predicted transaction data and the predicted operating mode. The predicted operating mode is used to characterize the power supply module used to supply power to the load. The power supply module is an external power grid, a photovoltaic module in a photovoltaic-storage-charging system, and / or an energy storage module. The predicted transaction data is used to characterize the power supply status of the power supply module.

[0121] The second determining module 230 is used to run the power supply module based on the predicted operating mode to obtain actual transaction data;

[0122] The third determining module 240 is used to perform backtesting based on the actual transaction data and the predicted transaction data, and determine the backtesting result.

[0123] The fourth determining module 250 is used to determine the target operating mode and the power change data of the power supply module indicated by the target operating mode, based on the actual transaction data, when the backtest result indicates that the predicted operating mode is unreasonable.

[0124] The operation module 260 is used to run the power supply module indicated by the target operation mode based on the target operation mode and the power change data.

[0125] Optionally, the third determining module is used to:

[0126] The target vector distance is determined based on the vector generated from the actual transaction data and the vector generated from the predicted transaction data.

[0127] The target backtesting accuracy is determined based on the target vector distance and the most recently calculated historical vector distance.

[0128] If the target backtest accuracy is greater than a preset accuracy threshold, the backtest result is determined to indicate that the predicted operation mode is unreasonable.

[0129] If the target backtesting accuracy is less than the preset accuracy threshold, the standard deviation of the backtesting accuracy is determined based on the historical backtesting accuracy calculated in the most recent N times and the target backtesting accuracy. If the standard deviation is greater than the base backtesting accuracy, the backtesting result is determined to indicate that the prediction operation mode is unreasonable, and the base backtesting accuracy is the backtesting accuracy corresponding to the prediction transaction data obtained from the first prediction analysis.

[0130] Optionally, the fourth determining module is used to:

[0131] Based on the actual transaction data and the preset energy dispatch strategy, the target operating mode is determined;

[0132] Based on the actual transaction data, preset power change data constraints, and preset objective function, the power change data is determined, and the objective function is used to maximize the net profit of the photovoltaic-storage-charging system.

[0133] Optionally, the fourth determining module is used to:

[0134] If the total profit data, energy storage change, and grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the total profit data is greater than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is greater than zero in the preset energy dispatch strategy, then the target operating mode is determined to be the photovoltaic operating mode. The photovoltaic operating mode is a mode in which the discharge amount of the photovoltaic module is used to supply power to the load and charge the energy storage module.

[0135] If the total profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the total profit data is less than zero, the energy storage change is less than zero, and the grid-connected charging and discharging amount is less than zero in the preset energy dispatch strategy, then the target operation mode is determined to be the guaranteed operation mode. The guaranteed operation mode is a mode in which the priority of the energy storage module to supply power to the load is lower than that of the photovoltaic module and higher than that of the external power grid.

[0136] If the grid-connected profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the grid-connected profit data is greater than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is less than zero in the preset energy dispatch strategy, then the target operating mode is determined to be the economic operating mode. The economic operating mode is a mode in which the external power grid is used to supply power to the load, and the energy storage module is used for grid-connected power supply.

[0137] If the grid-connected profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions of the preset energy dispatch strategy, where the grid-connected profit data is less than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is less than zero, then the target operating mode is determined to be the off-grid operating mode. The off-grid operating mode is a mode in which the photovoltaic module charges the energy storage module and the energy storage module supplies power to the load.

[0138] Optionally, the fourth determining module is used to:

[0139] Based on the grid-connected profit data in the actual transaction data and the preset power change data constraints, the preset objective function is calculated to determine the power change data. The preset objective function is the mapping relationship between the grid-connected profit data, the power change data and the electricity cost. The preset power change data constraint is that the power change data equals the load power demand.

[0140] Optionally, the running module is used to:

[0141] If the difference between the actual transaction data and the preset transaction data is less than or equal to the preset transaction threshold, the power supply module indicated by the target operation mode is run according to the first sub-operation mode of the target operation mode. The first sub-operation mode is to run the indicated power supply module according to the priority of the power supply module within the operation cycle.

[0142] If the difference between the actual transaction data and the preset transaction data is greater than the preset transaction threshold, the power supply module indicated by the target operation mode is run according to the second sub-operation mode of the target operation mode. The second sub-operation mode is to run all the indicated power supply modules from the beginning of the operation cycle until the end of the operation cycle.

[0143] Optionally, the acquisition module is used for:

[0144] Acquire charging data from the photovoltaic-storage-charging system. The charging data includes vehicle type, market electricity price data, charging time period data, charging frequency, charging mode, environmental data, current time data, and power data.

[0145] The vehicle type, the market electricity price data, the charging time period data, the charging mode, and the environmental data are encoded to obtain the first sub-load charging data.

[0146] The power data is normalized to obtain the charging data of the second sub-load;

[0147] The first sub-load charging data, the second sub-load charging data, the charging frequency, and the current time data are used as the load charging data.

[0148] This application also provides an electronic device for performing the above-described energy management method. Please refer to... Figure 3 It illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 3 As shown, the electronic device 3 includes: a processor 300, a memory 301, a bus 302, and a communication interface 303. The processor 300, the communication interface 303, and the memory 301 are connected via the bus 302. The memory 301 stores a computer program that can run on the processor 300. When the processor 300 runs the computer program, it executes the energy management method provided in any of the foregoing embodiments of this application.

[0149] The memory 301 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this device network element and at least one other network element is achieved through at least one communication interface 303 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0150] Bus 302 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store programs. After receiving an execution instruction, the processor 300 executes the program. The energy management method disclosed in any of the foregoing embodiments of this application can be applied to the processor 300, or implemented by the processor 300.

[0151] The processor 300 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 300 or by instructions in software form. The processor 300 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 301. The processor 300 reads the information in memory 301 and, in conjunction with its hardware, completes the steps of the above method.

[0152] The electronic devices and energy management methods provided in this application are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0153] This application also provides a computer-readable storage medium corresponding to the energy management method provided in the foregoing embodiments. The computer-readable storage medium shown may be an optical disc, on which a computer program is stored. When the computer program is run by a processor, it executes the energy management method provided in any of the foregoing embodiments.

[0154] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0155] The computer-readable storage medium provided in the above embodiments of this application and the energy management method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0156] This application also provides a computer program product 400, such as... Figure 4 As shown. This computer program product carries a computer program 401. The instructions included in the program code can be used to execute the steps of the energy management method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0157] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0158] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0159] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0160] Additionally, as used herein, the “or” used in a list of items beginning with “at least one” indicates a separate list, such that a list of, for example, “at least one of A, B, or C” means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word “exemplary” does not imply that the described example is preferred or better than other examples.

[0161] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0162] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0163] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0164] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. An energy management method, characterized in that, include: Acquire load charging data of the photovoltaic-storage-charging system; Based on a preset prediction model, the load charging data is predicted and analyzed to determine the predicted transaction data and the predicted operating mode. The predicted operating mode is used to characterize the power supply module used to supply power to the load. The power supply module is the external power grid, a photovoltaic module in the photovoltaic-storage-charging system, and / or an energy storage module. The predicted transaction data is used to characterize the power supply status of the power supply module. The power supply module is operated based on the predicted operating mode to obtain actual transaction data; Backtesting is performed based on the actual transaction data and the predicted transaction data to determine the backtesting results; If the backtest result indicates that the predicted operating mode is unreasonable, the target operating mode and the power change data of the power supply module indicated by the target operating mode are determined based on the actual transaction data. Based on the target operating mode and the power change data, the power supply module indicated by the target operating mode is operated.

2. The method according to claim 1, characterized in that, The backtesting based on the actual transaction data and the predicted transaction data, and the determination of the backtesting results, includes: The target vector distance is determined based on the vector generated from the actual transaction data and the vector generated from the predicted transaction data. The target backtesting accuracy is determined based on the target vector distance and the most recently calculated historical vector distance. If the target backtest accuracy is greater than a preset accuracy threshold, the backtest result is determined to indicate that the predicted operation mode is unreasonable. If the target backtesting accuracy is less than the preset accuracy threshold, the standard deviation of the backtesting accuracy is determined based on the historical backtesting accuracy calculated in the most recent N times and the target backtesting accuracy. If the standard deviation is greater than the base backtesting accuracy, the backtesting result is determined to indicate that the prediction operation mode is unreasonable, and the base backtesting accuracy is the backtesting accuracy corresponding to the prediction transaction data obtained from the first prediction analysis.

3. The method according to claim 1, characterized in that, When the backtesting results indicate that the predicted operating mode is unreasonable, the process of determining the target operating mode and the power supply module's power change data indicated by the target operating mode, based on the actual transaction data, includes: Based on the actual transaction data and the preset energy dispatch strategy, the target operating mode is determined; Based on the actual transaction data, preset power change data constraints, and preset objective function, the power change data is determined, and the objective function is used to maximize the net profit of the photovoltaic-storage-charging system.

4. The method according to claim 3, characterized in that, The determination of the target operating mode based on the actual transaction data and the preset energy dispatch strategy includes: If the total profit data, energy storage change, and grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the total profit data is greater than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is greater than zero in the preset energy dispatch strategy, then the target operating mode is determined to be the photovoltaic operating mode. The photovoltaic operating mode is a mode in which the discharge amount of the photovoltaic module is used to supply power to the load and charge the energy storage module. If the total profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the total profit data is less than zero, the energy storage change is less than zero, and the grid-connected charging and discharging amount is less than zero in the preset energy dispatch strategy, then the target operation mode is determined to be the guaranteed operation mode. The guaranteed operation mode is a mode in which the priority of the energy storage module to supply power to the load is lower than that of the photovoltaic module and higher than that of the external power grid. If the grid-connected profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions that the grid-connected profit data is greater than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is less than zero in the preset energy dispatch strategy, then the target operating mode is determined to be the economic operating mode. The economic operating mode is a mode in which the external power grid is used to supply power to the load, and the energy storage module is used for grid-connected power supply. If the grid-connected profit data, the energy storage change, and the grid-connected charging and discharging amount in the actual transaction data respectively satisfy the conditions of the preset energy dispatch strategy, where the grid-connected profit data is less than zero, the energy storage change is greater than zero, and the grid-connected charging and discharging amount is less than zero, then the target operating mode is determined to be the off-grid operating mode. The off-grid operating mode is a mode in which the photovoltaic module charges the energy storage module and the energy storage module supplies power to the load.

5. The method according to claim 3, characterized in that, The step of determining the electricity change data based on the actual transaction data, preset electricity change data constraints, and a preset objective function includes: Based on the grid-connected profit data in the actual transaction data and the preset power change data constraints, the preset objective function is calculated to determine the power change data. The preset objective function is the mapping relationship between the grid-connected profit data, the power change data and the electricity cost. The preset power change data constraint is that the power change data equals the load power demand.

6. The method according to claim 1, characterized in that, The step of operating the power supply module indicated by the target operating mode based on the target operating mode and the power change data includes: If the difference between the actual transaction data and the preset transaction data is less than or equal to the preset transaction threshold, the power supply module indicated by the target operation mode is run according to the first sub-operation mode of the target operation mode. The first sub-operation mode is to run the indicated power supply module according to the priority of the power supply module within the operation cycle. If the difference between the actual transaction data and the preset transaction data is greater than the preset transaction threshold, the power supply module indicated by the target operation mode is run according to the second sub-operation mode of the target operation mode. The second sub-operation mode is to run all the indicated power supply modules from the beginning of the operation cycle until the end of the operation cycle.

7. The method according to claim 1, characterized in that, The acquisition of load charging data for the photovoltaic energy storage and charging system includes: Acquire charging data from the photovoltaic-storage-charging system. The charging data includes vehicle type, market electricity price data, charging time period data, charging frequency, charging mode, environmental data, current time data, and power data. The vehicle type, the market electricity price data, the charging time period data, the charging mode, and the environmental data are encoded to obtain the first sub-load charging data. The power data is normalized to obtain the charging data of the second sub-load; The first sub-load charging data, the second sub-load charging data, the charging frequency, and the current time data are used as the load charging data.

8. An energy management device, characterized in that, include: The acquisition module is used to acquire load charging data of the photovoltaic energy storage and charging system; The first determining module is used to perform predictive analysis on the load charging data based on a preset prediction model, and to determine the predicted transaction data and the predicted operating mode. The predicted operating mode is used to characterize the power supply module used to supply power to the load. The power supply module is an external power grid, a photovoltaic module in a photovoltaic-storage-charging system, and / or an energy storage module. The predicted transaction data is used to characterize the power supply status of the power supply module. The second determining module is used to operate the power supply module based on the predicted operating mode to obtain actual transaction data; The third determining module is used to perform backtesting based on the actual transaction data and the predicted transaction data, and determine the backtesting results. The fourth determining module is used to determine the target operating mode and the power change data of the power supply module indicated by the target operating mode, based on the actual transaction data, when the backtesting result indicates that the predicted operating mode is unreasonable. The operation module is used to run the power supply module indicated by the target operation mode based on the target operation mode and the power change data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, Includes computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device performs the method as described in any one of claims 1-7.

Images