Energy storage equipment control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an energy storage equipment control method. The method comprises the following steps: acquiring first current monitoring data and historical monitoring data of target energy storage equipment; performing prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage equipment; based on the load prediction result, determining a charging and discharging strategy of the target energy storage equipment; and carrying out charging and discharging control on the target energy storage equipment based on the charging and discharging strategy. Prediction processing is carried out through the historical monitoring data, a relatively accurate load prediction result at the current moment can be obtained through prediction, so that a charging and discharging strategy of the target energy storage equipment can be formulated according to the load prediction result and the first current monitoring data, and the charging and discharging of the target energy storage equipment can be controlled according to the charging and discharging strategy. The renewable energy scheduling efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method and device for controlling an energy storage device, an electronic device and a storage medium. Background Art

[0002] With the rapid development of renewable energy, especially the widespread application of wind and solar energy, the power system is facing the challenges of increasing load volatility and instability. According to a report by the International Energy Agency (IEA), the proportion of global renewable energy power generation is expected to exceed 40% in the next decade, which requires the power grid to have higher flexibility and intelligence in scheduling and energy storage. At present, energy storage systems mainly use technologies such as lithium-ion batteries and pumped storage. However, their scheduling and control often rely on experience and simple algorithms, and cannot effectively respond to rapidly changing electricity demand, that is, the efficiency of renewable energy scheduling is low. For example, after the proportion of its renewable energy exceeded 40%, Germany still faced the problem of insufficient power supply during peak hours, resulting in drastic fluctuations in electricity prices. Therefore, how to provide a control method for energy storage equipment that can improve the efficiency of renewable energy scheduling has become an urgent problem to be solved. Summary of the invention

[0003] The embodiment of the present invention provides a method for controlling an energy storage device, aiming to solve the problem of low efficiency in existing renewable energy scheduling. By obtaining the first current monitoring data and historical monitoring data of the target energy storage device whose scheduling efficiency of renewable energy needs to be improved, and performing prediction processing based on the historical monitoring data, a relatively accurate load prediction result at the current moment can be predicted, so that a charging and discharging strategy for the target energy storage device can be formulated according to the load prediction result and the first current monitoring data, and then when the target energy storage device is charged and discharged according to the charging and discharging strategy, the scheduling efficiency of renewable energy can be improved.

[0004] In a first aspect, an embodiment of the present invention provides a method for controlling an energy storage device, the method comprising the following steps: Acquire first current monitoring data and historical monitoring data of a target energy storage device; Performing prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; Determining a charging and discharging strategy for the target energy storage device based on the load forecast result; Based on the charging and discharging strategy, the charging and discharging of the target energy storage device is controlled.

[0005] Optionally, performing prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device includes: Inputting the historical monitoring data and the first current monitoring data into a preset load model for short-term load forecasting to obtain a first forecasting result; Inputting the historical monitoring data and the first current monitoring data into the preset load model for long-term load forecasting to obtain a second forecasting result; The load forecasting result is determined based on the first forecasting result and the second forecasting result.

[0006] Optionally, before analyzing and processing the historical monitoring data to obtain a load forecast result of the target energy storage device, the method further includes: Obtaining historical energy usage data of the area corresponding to the target energy storage reserve and a load forecasting model to be trained; Based on the historical energy usage data, a sample training set is constructed; The load forecasting model to be trained is trained based on the sample training set to obtain the preset load model.

[0007] Optionally, constructing a sample training set based on the historical energy usage data includes: Performing data analysis and processing based on the historical energy usage data to obtain a power demand pattern and energy generation characteristics for each of the historical energy usage data; Taking each of the historical energy usage data as sample data, and taking the corresponding power demand pattern and the energy generation characteristics as label data of each of the sample data; A mapping relationship is established for each of the sample data and the corresponding label data, and the data are added to a preset empty set. When all the sample data and the corresponding label data are added, the sample training set is obtained.

[0008] Optionally, after controlling the charge and discharge of the target energy storage device based on the charge and discharge strategy, the method further includes: After controlling the charge and discharge of the target energy storage device based on the charge and discharge strategy, acquiring second current monitoring data of the target energy storage device; Based on the second current monitoring data, the preset load forecasting model is updated and trained.

[0009] Optionally, determining a charging and discharging strategy of the target energy storage device based on the load forecast result and the first current monitoring data includes: Obtain current energy trading data; Determining a pre-charge and discharge strategy for the target energy storage device based on the load forecast result and the first current monitoring data; The pre-charge and discharge strategy is adjusted based on the current energy transaction data to obtain the charge and discharge strategy of the target energy storage device.

[0010] In a second aspect, an embodiment of the present invention further provides an energy storage device control device, the energy storage device control device comprising: A first acquisition module, used to acquire first current monitoring data and historical monitoring data of a target energy storage device; A first prediction module, configured to perform prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; A first determination module, configured to determine a charge and discharge strategy for the target energy storage device based on the load prediction result; The first control module is used to control the charging and discharging of the target energy storage device based on the charging and discharging strategy.

[0011] Optionally, the first prediction module includes: A first prediction submodule, used for inputting the historical monitoring data and the first current monitoring data into a preset load model to perform short-term load forecasting processing to obtain a first prediction result; A second prediction submodule, used for inputting the historical monitoring data and the first current monitoring data into the preset load model to perform long-term load forecasting processing to obtain a second prediction result; The first determination submodule is used to determine the load prediction result based on the first prediction result and the second prediction result.

[0012] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the energy storage device control method provided in the embodiment of the present invention when executing the computer program.

[0013] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the energy storage device control method provided in the embodiment of the invention are implemented.

[0014] In an embodiment of the present invention, the first current monitoring data and historical monitoring data of the target energy storage device are obtained; prediction processing is performed based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; based on the load prediction result, the charge and discharge strategy of the target energy storage device is determined; based on the charge and discharge strategy, the charge and discharge of the target energy storage device is controlled. By obtaining the first current monitoring data and historical monitoring data of the target energy storage device for which the efficiency of renewable energy scheduling needs to be improved, and performing prediction processing based on the historical monitoring data, a relatively accurate load prediction result at the current moment can be predicted, so that the charge and discharge strategy of the target energy storage device can be formulated based on the load prediction result and the first current monitoring data, and then when the charge and discharge of the target energy storage device is controlled according to the charge and discharge strategy, the efficiency of renewable energy scheduling can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 is a flow chart of a method for controlling an energy storage device provided by an embodiment of the present invention; Figure 2 is a structural schematic diagram of an energy storage device control device provided in an embodiment of the present invention; Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, Figure 1 is a flow chart of a method for controlling an energy storage device provided by an embodiment of the present invention, comprising: 101. Obtain first current monitoring data and historical monitoring data of a target energy storage device.

[0019] In an embodiment of the present invention, the above-mentioned energy storage device control method can be applied to the above-mentioned target energy storage device, and the above-mentioned target energy storage device can have functions such as data analysis, data processing, data storage, and data transmission, or in order to reduce the use of computing resources of the target energy storage reserve, the above-mentioned energy storage device control method can also be applied to an energy storage device management platform, and the above-mentioned energy storage device management platform can be constructed by a server or a server cluster, and the above-mentioned server or server cluster can be any electronic device with functions such as data analysis, data processing, data storage, and data transmission. The above-mentioned energy storage device management platform can send instructions and receive information to the above-mentioned target energy storage device through the above-mentioned data transmission function to implement the above-mentioned energy storage device control method. The above-mentioned preset load forecasting model can also be deployed in the above-mentioned energy storage device management platform, and related forecasting processing can be implemented based on the above-mentioned preset load forecasting model.

[0020] The target energy storage device may be any container capable of storing energy, or may be an energy storage system composed of a combination of multiple containers or a specific structure. The target energy storage device may be a device with low efficiency in dispatching renewable energy. That is, the storage capacity of the target energy storage device was originally intended to meet the energy demand of the corresponding area, but in actual application, it does not meet the energy demand of the corresponding area. In this case, the corresponding energy storage device may be determined as the target energy storage device.

[0021] The above-mentioned energy storage equipment management platform can provide the energy monitoring data of the corresponding area to relevant managers through a visual user interaction interface, and the relevant managers will monitor it to determine the target energy storage equipment that needs to re-formulate the charging and discharging strategy to improve the efficiency of renewable energy scheduling.

[0022] The above-mentioned first current monitoring data may include the battery power of the energy storage device (i.e., the electrical energy of the above-mentioned target energy storage device, usually expressed in kilowatt-hours (kWh)), the charging and discharging status (i.e., the current charging or discharging status of the energy storage device, for example, charging, discharging or standby, etc.), power consumption and supply (i.e., the amount of power consumed by the energy storage device or supplied to the power grid at the current moment), the health status of the device (i.e., the health indicators of the energy storage device, such as battery temperature, life, charging and discharging efficiency, etc.), and environmental factors (such as current power demand, temperature, humidity, and other external conditions that may affect the operation of the energy storage device).

[0023] The above-mentioned historical monitoring data may include past load data (i.e., the load demand of the energy storage device in the past period of time, such as fluctuations in the power demand of the power grid), historical charging and discharging records (i.e., records of the charging and discharging process of the energy storage device in the past, including information such as the charging amount, discharging amount, and charging and discharging time), historical power generation data (such as power generation data of renewable energy such as solar energy and wind energy, which is used to understand the fluctuation characteristics of renewable energy), and historical data of environmental factors (such as temperature changes, electricity market prices, seasonal factors, etc. in the past period of time that may affect power demand or the efficiency of energy storage equipment).

[0024] It is understandable that the first current monitoring data can be simply understood as the real-time status data of the energy storage device at the current moment, which is used to adjust the device operation immediately. The historical monitoring data can be simply understood as the operation record over a period of time in the past, which is used to analyze trends and predict future load demand, and assist in making decisions on the charging and discharging strategies of energy storage devices. Combining the above two can provide comprehensive information for the intelligent scheduling of energy storage devices and optimize the energy efficiency and economy of the system.

[0025] 102. Perform forecasting processing based on the historical monitoring data and the first current monitoring data to obtain a load forecasting result of the target energy storage device.

[0026] In an embodiment of the present invention, the above prediction processing can be implemented according to a preset load prediction model. Specifically, the load prediction model to be trained can be constructed by any algorithm capable of realizing load prediction, and the load prediction model to be trained can be trained to obtain the above preset load prediction model. The above historical monitoring data and the above first current monitoring data are input into the above preset load prediction model, so that the above load prediction model outputs the above load prediction result.

[0027] The above algorithm may be a support vector machine (SVM) algorithm or a deep learning algorithm. Specifically, the above algorithm may be an artificial neural network (ANN), a long short-term memory network (LSTM), a convolutional neural network (CNN), a recurrent neural network (RNN), a gated recurrent unit (GRU), an autoencoder, a Transformer model, etc.

[0028] It is understandable that in the energy storage equipment load forecasting, the use of deep learning algorithms can process complex time series data and take into account multiple factors to accurately predict the load. By capturing the time series characteristics of historical load data, it can help optimize the charging and discharging strategies of energy storage equipment in subsequent steps.

[0029] 103. Based on the load forecast results, determine the charging and discharging strategy of the target energy storage device.

[0030] In an embodiment of the present invention, the charging and discharging strategy of the energy storage device can be adjusted by optimizing scheduling based on load forecast results and real-time data using an optimization algorithm to meet power demand and minimize energy waste.

[0031] Specifically, the load forecast results can be used to determine the high-load and low-load periods of the energy storage device. The period can be composed of a start time point, an end time point, and a duration. During high-load periods, discharge can be prioritized to support grid demand; while during low-load periods, charging can be performed to store excess electrical energy. This strategy can effectively meet electricity demand and minimize energy waste, thereby improving the overall efficiency and economy of the energy storage system.

[0032] 104. Based on the charging and discharging strategy, the charging and discharging of the target energy storage device is controlled.

[0033] In an embodiment of the present invention, after determining the charge and discharge strategy, the charge and discharge strategy can be applied to the target energy storage device so that the target energy storage device automatically discharges first when the load is high and charges first when the load is low. Alternatively, the energy storage device management platform sends a charge and discharge instruction to the target energy storage device to implement the charge and discharge strategy, thereby realizing the charge and discharge control of the target energy storage device.

[0034] In an embodiment of the present invention, the first current monitoring data and historical monitoring data of the target energy storage device are obtained; prediction processing is performed based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; based on the load prediction result, the charge and discharge strategy of the target energy storage device is determined; based on the charge and discharge strategy, the charge and discharge of the target energy storage device is controlled. By obtaining the first current monitoring data and historical monitoring data of the target energy storage device for which the efficiency of renewable energy scheduling needs to be improved, and performing prediction processing based on the historical monitoring data, a relatively accurate load prediction result at the current moment can be predicted, so that the charge and discharge strategy of the target energy storage device can be formulated based on the load prediction result and the first current monitoring data, and then when the charge and discharge of the target energy storage device is controlled according to the charge and discharge strategy, the efficiency of renewable energy scheduling can be improved.

[0035] It can be understood that in the specific implementation of this application, it involves current monitoring data, historical monitoring data, historical energy usage data, sample data and other related data. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data and the use of load forecasting models need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0036] It should be noted that the energy storage device control method provided in the embodiment of the present invention can be applied to computers, servers and other devices that can control energy storage devices.

[0037] Optionally, in the step of performing forecasting processing based on the historical monitoring data and the first current monitoring data to obtain the load forecast result of the target energy storage device, the historical monitoring data and the first current monitoring data can also be input into a preset load model for short-term load forecasting processing to obtain a first forecast result; the historical monitoring data and the first current monitoring data can be input into a preset load model for long-term load forecasting processing to obtain a second forecast result; and the load forecast result is determined based on the first forecast result and the second forecast result.

[0038] In an embodiment of the present invention, the historical monitoring data and the first current monitoring data of the target energy storage device can be simultaneously input into a preset load forecasting model to perform short-term load forecasting and obtain a first forecasting result. This forecasting result mainly reflects the change in the power load in the next few hours, which is convenient for timely adjusting the charging and discharging strategy of the energy storage device.

[0039] At the same time, the same historical monitoring data and current data are input into the preset load model for long-term load forecasting to obtain the second forecast result, covering the load demand fluctuations in the next few days or a week. Based on the first forecast result and the second forecast result, the load forecast result of the target energy storage device is finally determined by comprehensively considering short-term load fluctuations and long-term trends. This result can well guide the charging and discharging strategy of the energy storage device, ensure the balance of power supply and demand in different time periods, and optimize the operating efficiency of the equipment.

[0040] More specifically, usually, the accuracy of the prediction result is related to the amount of sample data used when training the preset load model, and is also related to the duration of the prediction, that is, the more data, the shorter the prediction duration (for example, short-term load prediction is shorter than long-term load prediction), and the higher its accuracy. Therefore, the first prediction result can be used to verify the second prediction result. When the second prediction result is consistent with the first prediction result, the second prediction result can be combined with the first prediction result to obtain the above-mentioned load prediction result. When the second prediction result does not match the first prediction result, only the first prediction result can be used as the above-mentioned load prediction result. At the same time, the relevant information about the insufficient prediction accuracy of the above-mentioned preset load prediction model is fed back to the relevant personnel, so that the relevant personnel can increase the amount of sample data again, and train the above-mentioned preset load prediction model again to improve the prediction accuracy.

[0041] Optionally, in the step before analyzing and processing based on historical monitoring data to obtain the load forecast result of the target energy storage device, the historical energy usage data of the area corresponding to the target energy storage reserve and the load forecast model to be trained can also be obtained; based on the historical energy usage data, a sample training set is constructed; based on the sample training set, the load forecast model to be trained is trained to obtain a preset load model.

[0042] In an embodiment of the present invention, the above-mentioned historical energy usage data may include daily electricity consumption records, renewable energy power generation, load fluctuations and other information in the above-mentioned area. Usually, the above-mentioned historical energy usage data can be obtained from the monitoring system of the power company or the smart meter.

[0043] After obtaining the above historical energy usage data, corresponding label data can be constructed for each historical energy usage data to obtain the above sample training set, and the above load prediction model to be trained is trained based on the above sample training set to obtain the above predicted load model.

[0044] It should be noted that the load forecasting model to be trained can be constructed by any algorithm such as the artificial neural network (ANN), long short-term memory network (LSTM), convolutional neural network (CNN), recurrent neural network (RNN), etc.

[0045] More specifically, in the above training process, it is assumed that the sample training set includes sample data of the Tth period, sample data of the T+1th period, sample data of the T+2th period, sample data of the T+3th period, and sample data of the T+4th period. Then the sample data of the Tth period and the corresponding label data can be used as input, so that the load forecasting model to be trained predicts the load forecasting results of the T+1th period to the T+4th period based on the sample data and label data of the Tth period. And calculate the loss value between the above load forecasting results and the above sample data, with minimizing the above loss value as the optimization goal, and perform prediction training on the above load forecasting model to be trained until the above loss value converges to the minimum, or when the number of training times reaches the preset value, stop training to obtain the above preset load forecasting model.

[0046] Optionally, in the step of constructing a sample training set based on historical energy usage data, data analysis and processing can also be performed based on the historical energy usage data to obtain the power demand pattern and energy generation characteristics of each historical energy usage data; each historical energy usage data is used as sample data, and the corresponding power demand pattern and energy generation characteristics are used as label data for each sample data; a mapping relationship is established for each sample data and the corresponding label data, and added to a preset empty set. When all sample data and the corresponding label data are added, a sample training set is obtained.

[0047] In an embodiment of the present invention, by performing data analysis and processing on historical energy usage data, the power demand pattern and energy generation characteristics of each data point are extracted, such as the peak and trough periods of power demand, seasonal changes, the impact of weather conditions on demand, and the power generation characteristics of renewable energy (such as solar energy and wind energy).

[0048] Then, for each historical energy usage data, its corresponding power demand pattern and energy generation characteristics are determined, and the historical data is used as sample data, while the power demand pattern and energy generation characteristics are used as label data. A mapping relationship is established between each sample data and the corresponding label data, and it is added to the preset empty set. Through this process, all sample data and their corresponding label data are added one by one, and finally a sample training set is obtained.

[0049] By deeply analyzing historical energy usage data, extracting electricity demand patterns and energy generation characteristics, we can better understand the complex relationship between electricity consumption and renewable energy generation. A mapping relationship is established for each sample data, and combined with label data for training, so that the load forecasting model can learn the laws of regional load fluctuations and improve forecasting accuracy. It not only helps to predict short-term and long-term changes in electricity demand, but also effectively optimizes the scheduling of energy storage equipment, reduces electricity waste, and improves the stability and economy of the energy storage system.

[0050] Optionally, in the step after charging and discharging the target energy storage device is controlled based on the charging and discharging strategy, second current monitoring data of the target energy storage device can be obtained after charging and discharging the target energy storage device is controlled based on the charging and discharging strategy; based on the second current monitoring data, the preset load forecasting model is updated and trained.

[0051] In the embodiment of the present invention, the data kernel of the second current monitoring data is the same, that is, both can include data such as battery power, charging and discharging status, power consumption and supply, equipment health status, environmental factors, etc. After implementing the above energy storage device control method, the second current monitoring data is obtained again, and the preset load forecasting model is updated and trained according to the second current monitoring data, which can greatly improve the forecast accuracy.

[0052] In the subsequent process, the second current monitoring data can be extracted every preset time period, and the above-mentioned update training can be performed using the above-mentioned second current monitoring data, so that the load forecasting model can adapt well to the power load fluctuations in the corresponding area, the changes in the operating status of the energy storage equipment, and the dynamic changes of external environmental factors, so that the model can reflect the regional power demand and the operating trend of the energy storage equipment in real time. Through regular update training, the load forecasting model can be continuously optimized and gradually improve the accuracy of the prediction of future power loads, ensuring that the charging and discharging control strategy of the energy storage equipment is always consistent with the actual demand, further improving the system's dispatching efficiency, reducing energy waste and improving the stability of the power grid.

[0053] Optionally, in the step of determining the charging and discharging strategy of the target energy storage device based on the load forecast result and the first current monitoring data, the current energy trading data can also be obtained; based on the load forecast result and the first current monitoring data, the pre-charging and discharging strategy of the target energy storage device is determined; based on the current energy trading data, the pre-charging and discharging strategy is adjusted to obtain the charging and discharging strategy of the target energy storage device.

[0054] In an embodiment of the present invention, the above-mentioned energy trading data may include information such as real-time prices in the electricity market, supply and demand relationships, and trends in the electricity market in the future. The above-mentioned pre-charge and discharge strategy is mainly preliminarily set based on the changes in electricity demand in the load forecast results and the current state of the energy storage device to ensure discharge during peak electricity demand periods and charging during valley periods. Based on the current energy trading data obtained, the pre-charge and discharge strategy is adjusted to take into account price fluctuations in the electricity market and changes in electricity supply and demand. For example, when the electricity market price is low, the energy storage device can choose to increase charging; while in the period when the electricity market price is high, it can choose to increase discharge and sell the stored electricity at a higher price. In this way, the economic benefits can be maximized and the energy storage device can play a more flexible role in the electricity market. Finally, the adjusted charge and discharge strategy will be optimized in real time according to changes in the energy market to achieve more efficient energy management and cost control.

[0055] like Figure 2 As shown, an embodiment of the present invention further provides an energy storage device control device, comprising: A first acquisition module 201, used to acquire first current monitoring data and historical monitoring data of a target energy storage device; A first prediction module 202, configured to perform prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; A first determination module 203, configured to determine a charge and discharge strategy for the target energy storage device based on the load prediction result; The first control module 204 is used to control the charging and discharging of the target energy storage device based on the charging and discharging strategy.

[0056] Optionally, the first prediction module 202 includes: A first prediction submodule, used for inputting the historical monitoring data and the first current monitoring data into a preset load model to perform short-term load forecasting processing to obtain a first prediction result; A second prediction submodule, used for inputting the historical monitoring data and the first current monitoring data into the preset load model to perform long-term load forecasting processing to obtain a second prediction result; The first determination submodule is used to determine the load prediction result based on the first prediction result and the second prediction result.

[0057] Optionally, the energy storage device control device further includes: A second acquisition module is used to acquire historical energy usage data of the area corresponding to the target energy storage reserve and a load forecasting model to be trained; A first construction module is used to construct a sample training set based on the historical energy usage data; The first training module is used to train the load prediction model to be trained based on the sample training set to obtain the preset load model.

[0058] Optionally, the first building block includes: A first analysis submodule is used to perform data analysis based on the historical energy usage data to obtain a power demand pattern and energy generation characteristics of each of the historical energy usage data; A first processing submodule is used to use each of the historical energy usage data as sample data, and use the corresponding power demand pattern and the energy generation characteristics as label data of each of the sample data; The first adding submodule is used to establish a mapping relationship between each of the sample data and the corresponding label data, and add them to a preset empty set. When all the sample data and the corresponding label data are added, the sample training set is obtained.

[0059] Optionally, the energy storage device control device further includes: A third acquisition module, configured to acquire second current monitoring data of the target energy storage device after controlling the charge and discharge of the target energy storage device based on the charge and discharge strategy; An update training module is used to update and train the preset load forecasting model based on the second current monitoring data.

[0060] Optionally, the first determining module 203 includes: Obtain current energy trading data; Determining a pre-charge and discharge strategy for the target energy storage device based on the load forecast result and the first current monitoring data; The pre-charge and discharge strategy is adjusted based on the current energy transaction data to obtain the charge and discharge strategy of the target energy storage device.

[0061] like Figure 3 As shown, an embodiment of the present invention further provides an electronic device, characterized in that it includes a processor, and the processor can execute any one of the above energy storage device control methods.

[0062] Specifically, it includes a processor 301 and a memory 302, and a computer program for executing the energy storage device control method stored in the memory 302 and capable of running on the processor 301, wherein: The processor 301 runs the computer program of the energy storage device control method stored in the memory 302 and performs the following steps: Acquire first current monitoring data and historical monitoring data of a target energy storage device; Performing prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; Determining a charging and discharging strategy for the target energy storage device based on the load forecast result; Based on the charging and discharging strategy, the charging and discharging of the target energy storage device is controlled.

[0063] Optionally, the processor 301 performs prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device, including: Inputting the historical monitoring data and the first current monitoring data into a preset load model for short-term load forecasting to obtain a first forecasting result; Inputting the historical monitoring data and the first current monitoring data into the preset load model for long-term load forecasting to obtain a second forecasting result; The load forecasting result is determined based on the first forecasting result and the second forecasting result.

[0064] Optionally, before analyzing and processing the historical monitoring data to obtain the load forecast result of the target energy storage device, the method executed by the processor 301 further includes: Obtaining historical energy usage data of the area corresponding to the target energy storage reserve and a load forecasting model to be trained; Based on the historical energy usage data, a sample training set is constructed; The load forecasting model to be trained is trained based on the sample training set to obtain the preset load model.

[0065] Optionally, the processor 301 executes the step of constructing a sample training set based on the historical energy usage data, including: Performing data analysis and processing based on the historical energy usage data to obtain a power demand pattern and energy generation characteristics for each of the historical energy usage data; Taking each of the historical energy usage data as sample data, and taking the corresponding power demand pattern and the energy generation characteristics as label data of each of the sample data; A mapping relationship is established for each of the sample data and the corresponding label data, and the data are added to a preset empty set. When all the sample data and the corresponding label data are added, the sample training set is obtained.

[0066] Optionally, after controlling the charge and discharge of the target energy storage device based on the charge and discharge strategy, the method executed by the processor 301 further includes: After controlling the charge and discharge of the target energy storage device based on the charge and discharge strategy, acquiring second current monitoring data of the target energy storage device; Based on the second current monitoring data, the preset load forecasting model is updated and trained.

[0067] Optionally, the determining, by the processor 301, of a charging and discharging strategy of the target energy storage device based on the load forecast result and the first current monitoring data includes: Obtain current energy trading data; Determining a pre-charge and discharge strategy for the target energy storage device based on the load forecast result and the first current monitoring data; The pre-charge and discharge strategy is adjusted based on the current energy transaction data to obtain the charge and discharge strategy of the target energy storage device.

[0068] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the energy storage device control method or the application-side energy storage device control method provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0069] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the above-mentioned computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0070] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for controlling an energy storage device, characterized in that: The method comprises the following steps: Acquire first current monitoring data and historical monitoring data of a target energy storage device; Performing prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; Determining a charging and discharging strategy for the target energy storage device based on the load forecast result; Based on the charging and discharging strategy, the charging and discharging of the target energy storage device is controlled.

2. The energy storage device control method according to claim 1, characterized in that: The performing prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device includes: Inputting the historical monitoring data and the first current monitoring data into a preset load model for short-term load forecasting to obtain a first forecasting result; Inputting the historical monitoring data and the first current monitoring data into the preset load model for long-term load forecasting to obtain a second forecasting result; The load forecasting result is determined based on the first forecasting result and the second forecasting result.

3. The energy storage device control method according to claim 2, characterized in that: Before analyzing and processing the historical monitoring data to obtain the load forecast result of the target energy storage device, the method further includes: Obtaining historical energy usage data of the area corresponding to the target energy storage reserve and a load forecasting model to be trained; Based on the historical energy usage data, a sample training set is constructed; The load forecasting model to be trained is trained based on the sample training set to obtain the preset load model.

4. The energy storage device control method according to claim 3, characterized in that: The sample training set is constructed based on the historical energy usage data, including: Performing data analysis and processing based on the historical energy usage data to obtain a power demand pattern and energy generation characteristics for each of the historical energy usage data; Taking each of the historical energy usage data as sample data, and taking the corresponding power demand pattern and the energy generation characteristics as label data of each of the sample data; A mapping relationship is established for each of the sample data and the corresponding label data, and the data are added to a preset empty set. When all the sample data and the corresponding label data are added, the sample training set is obtained.

5. The energy storage device control method according to any one of claims 2 to 4, characterized in that: After controlling the charge and discharge of the target energy storage device based on the charge and discharge strategy, the method further includes: After controlling the charge and discharge of the target energy storage device based on the charge and discharge strategy, acquiring second current monitoring data of the target energy storage device; Based on the second current monitoring data, the preset load forecasting model is updated and trained.

6. The energy storage device control method according to claim 1, characterized in that: The determining, based on the load forecast result and the first current monitoring data, a charging and discharging strategy of the target energy storage device includes: Obtain current energy trading data; Determining a pre-charge and discharge strategy for the target energy storage device based on the load forecast result and the first current monitoring data; The pre-charge and discharge strategy is adjusted based on the current energy transaction data to obtain the charge and discharge strategy of the target energy storage device.

7. An energy storage device control device, characterized in that: The energy storage device control device comprises: A first acquisition module, used to acquire first current monitoring data and historical monitoring data of a target energy storage device; A first prediction module, configured to perform prediction processing based on the historical monitoring data and the first current monitoring data to obtain a load prediction result of the target energy storage device; A first determination module, configured to determine a charge and discharge strategy for the target energy storage device based on the load prediction result; The first control module is used to control the charging and discharging of the target energy storage device based on the charging and discharging strategy.

8. The energy storage device control device according to claim 7, characterized in that: The first prediction module comprises: A first prediction submodule, used for inputting the historical monitoring data and the first current monitoring data into a preset load model to perform short-term load forecasting processing to obtain a first prediction result; A second prediction submodule, used for inputting the historical monitoring data and the first current monitoring data into the preset load model to perform long-term load forecasting processing to obtain a second prediction result; The first determination submodule is used to determine the load prediction result based on the first prediction result and the second prediction result.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the energy storage device control method as claimed in any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the energy storage device control method according to any one of claims 1 to 6 are implemented.

Images