Energy storage system energy management method and system, device, storage medium

Abstract

The application provides an energy storage system energy management method and system, equipment and a storage medium, and belongs to the technical field of energy storage system management. The method comprises the following steps: acquiring real-time operation data of each type of energy storage system; selecting an initial energy distribution strategy from a plurality of energy distribution strategies based on the current working mode of the energy storage system and the operation data of each type of energy storage system; obtaining a prediction result of energy distribution of the energy storage system to external loads and internal devices respectively based on historical operation data of the energy storage system; selecting a key control parameter from the initial energy distribution strategy based on the prediction result of energy distribution of the energy storage system to external loads and internal devices respectively, and managing the current energy distribution of the energy storage system based on the key control parameter. The application can provide a reasonable energy distribution strategy in a complex and changeable environment.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of energy storage system management, and more particularly relates to an energy storage system energy management method and system, equipment and a storage medium. BACKGROUND

[0002] In the field of energy today, energy storage systems, as a key technology for balancing energy supply and demand, improving energy utilization efficiency and enhancing the stability of power systems, are being used more and more widely. From distributed power generation scenarios such as supporting energy storage for solar and wind power generation, to peak shaving, backup power and other applications in commercial and industrial fields, energy storage systems play an indispensable role. For energy storage systems, effective energy management is crucial. It is not only directly related to the performance, life and safety of the energy storage system itself, but also has a profound impact on the operating efficiency of the entire energy system.

[0003] However, the existing energy storage systems currently use fixed rules or simple threshold controls in energy distribution strategies, which cannot be adjusted flexibly according to the real-time operating state of the energy storage system (such as power supply data, equipment state and load power changes), resulting in unreasonable energy distribution. SUMMARY

[0004] The purpose of the present application is to provide an energy storage system energy management method and system, equipment and a storage medium to improve the rationality of energy distribution of the energy storage system in complex environments.

[0005] The first aspect of the embodiment of the present application provides an energy storage system energy management method, comprising:

[0006] Real-time acquisition of various types of operating data of the energy storage system, including charging data of the energy storage system, power supply data of the energy storage system to external loads, power supply data of the energy storage system to internal devices, and state data of the internal devices of the energy storage system;

[0007] Selecting an initial energy distribution strategy from a plurality of energy distribution strategies based on the current working mode of the energy storage system and the various types of operating data of the energy storage system; each energy distribution strategy includes a control mode of at least one type of operating data of the energy storage system, and the control mode includes a control parameter; the working mode is any one of a charging mode, a discharging mode, a charging and discharging mode, and a standby mode;

[0008] Obtaining a prediction result of energy distribution of the energy storage system to external loads and internal devices respectively based on historical operating data of the energy storage system;

[0009] The key control parameter is selected from the initial energy distribution strategy based on the prediction result of the energy distribution of the energy storage system to the external load and the internal devices respectively, and the current energy distribution of the energy storage system is managed based on the key control parameter.

[0010] In a second aspect, the present application provides an energy management system of an energy storage system, comprising:

[0011] The data acquisition module is configured to acquire various types of operation data of the energy storage system in real time, wherein the various types of operation data of the energy storage system comprise charging data of the energy storage system, power supply data of the energy storage system to the external load, power supply data of the energy storage system to the internal devices, and state data of the internal devices of the energy storage system.

[0012] The first selection module is configured to select an initial energy distribution strategy from a plurality of energy distribution strategies based on the working mode in which the energy storage system is currently located and the various types of operation data of the energy storage system, wherein each energy distribution strategy comprises a control mode of at least one type of operation data of the energy storage system, and the control mode comprises a control parameter; and the working mode is any one of a charging mode, a discharging mode, a charging and discharging mode, and a standby mode.

[0013] The second selection module is configured to obtain a prediction result of the energy distribution of the energy storage system to the external load and the internal devices respectively based on historical operation data of the energy storage system.

[0014] The energy management module is configured to select a key control parameter from the initial energy distribution strategy based on the prediction result of the energy distribution of the energy storage system to the external load and the internal devices respectively, and manage the current energy distribution of the energy storage system based on the key control parameter.

[0015] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the energy management method of the energy storage system when executing the computer program.

[0016] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the energy management method of the energy storage system.

[0017] The energy management method and system of the energy storage system, the device, and the storage medium provided by the embodiments of the present application have the following beneficial effects:

[0018] The embodiments of the present application can comprehensively master the current running state of the system by acquiring the charging data of the energy storage system, the power supply data of the external load, the power supply data of the internal device and the state data of the internal device. On this basis, the current working mode of the energy storage system is judged, so as to dynamically select the initial energy distribution strategy adapting to the current working mode from the preset multiple energy distribution strategies, ensuring the matching of the strategy selection and the current running condition and avoiding the rigid problem of the traditional fixed threshold control. Further, in order to improve the rationality of energy distribution, the embodiments of the present application also use the historical running data of the energy storage system to predict the energy distribution demand of the external load and the internal device of the system; the key control parameters are selected from the initial energy distribution strategy in combination with the prediction result, so as to dynamically adjust the current energy distribution, realizing the adaptive optimization of the energy distribution strategy. Compared with the prior art which only relies on a single indicator such as the state of charge for fixed threshold control, the embodiments of the present application comprehensively consider the multi-dimensional running data, working mode and existing demand prediction, significantly improving the rationality and flexibility of energy distribution, effectively avoiding energy waste or insufficient supply, prolonging the service life of the energy storage system and improving the running efficiency and safety of the entire energy system. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 The flowchart of the energy management method of the energy storage system provided by an embodiment of the present application is shown.

[0021] Figure 2 The structural block diagram of the energy management system of the energy storage system provided by an embodiment of the present application is shown.

[0022] Figure 3 The schematic block diagram of the electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures, techniques, etc. are presented in order to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0024] For the purpose, technical solutions and advantages of the present application to be clearer, specific embodiments will be described below with reference to the drawings.

[0025] Please refer to Figure 1 , Figure 1 The flowchart of the energy management method of the energy storage system provided by an embodiment of the present application can include the following steps.

[0026] S101: Real-time acquisition of various types of operation data of the energy storage system.

[0027] The various types of operation data of the energy storage system include charging data of the energy storage system, power supply data of the energy storage system to external loads, power supply data of the energy storage system to internal devices, and state data of the internal devices of the energy storage system.

[0028] In the present embodiment, the energy storage system is a system that can receive electric energy transmitted by the power grid, photovoltaic power generation system or other electric energy generation systems, and store the electric energy through internal energy storage medium (such as battery pack). The energy storage system can be an integrated cabinet type energy storage system, a container type energy storage system or a household energy storage system.

[0029] The operation data of the energy storage system includes charging data of the energy storage system, power supply data of the energy storage system to external loads, power supply data of the energy storage system to internal devices, and state data of the internal devices of the energy storage system. The charging data of the energy storage system is the key parameter data generated in the process of the energy storage system obtaining electric energy from external power source (such as power grid, photovoltaic power station, wind farm) and storing it into the energy storage medium, which is mainly used to monitor the safety, efficiency and progress of the charging process. The charging data of the energy storage system includes charging voltage, charging current, charging power, charging electric quantity, charging time length, charging efficiency and charging state, etc.

[0030] The power supply data of the energy storage system to external loads includes output voltage, output current, output power, power supply time length and power supply efficiency of the energy storage system, which can reflect the power supply capacity and power supply quality of the energy storage system. The power supply data of the energy storage system to internal devices refers to the key parameter data generated when the energy storage system provides electric energy to internal devices to maintain normal operation, and the purpose is to monitor the stability of internal power supply of the energy storage system. The power supply data of the energy storage system to internal devices includes internal power supply voltage, internal power supply current, internal power supply electric quantity and internal power supply stability parameters, etc. The internal power supply stability parameters include voltage fluctuation range and current ripple coefficient, etc. The state data of the internal devices of the energy storage system includes the operating parameters and health status data of the battery pack, the converter and the liquid cooling device, such as the state of charge of the battery pack, the temperature of the battery pack, the life of the battery pack, the working mode of the converter, the valve opening degree of the liquid cooling device, etc.

[0031] S102: Select an initial energy distribution strategy from a plurality of energy distribution strategies based on a current working mode of the energy storage system and each type of running data of the energy storage system.

[0032] Each energy distribution strategy includes a control mode of at least one type of running data of the energy storage system, and the control mode includes a control parameter; and the working mode is any one of a charging mode, a discharging mode, a charging and discharging mode, and a standby mode.

[0033] In the embodiment, the working mode of the energy storage system includes any one of the charging mode, the discharging mode, the charging and discharging mode, and the standby mode, and the energy distribution strategy is different in different working modes. The energy distribution strategy is a rule set corresponding to energy distribution and optimization of the energy storage system, and includes different control logic and parameter configuration schemes to achieve an energy management target in a specific working mode.

[0034] For example, when the energy storage system is in the charging mode, the energy storage system only receives external power charging, and the energy distribution strategy at this time focuses on shortening the charging time, reducing the charging cost, prolonging the equipment life, etc. When the energy storage system is in the discharging mode, the energy storage system supplies power to the load and each internal device as the only power supply, and the energy distribution strategy at this time focuses on guaranteeing the continuity of power supply, avoiding power failure caused by excessive discharge of the energy storage, and also focuses on preferentially maintaining the stability of power supply to the external load and then meeting the stability of power supply to each internal device of the energy storage system. When the energy storage system is in the charging and discharging mode, part of the battery units of the battery pack can be used to receive charging power (such as photovoltaic power generation input, wind power generation input, etc.), and another part of the battery units can be used to supply power to the external load, so as to guarantee the stability of power supply to the external load, and the energy distribution strategy at this time focuses on balancing the charging and power supply efficiency. When the energy storage system is in the standby mode, the energy storage system neither obtains power from the outside nor outputs power to the external load, and only maintains a low-power running state of each internal device of the energy storage system.

[0035] In the embodiment, there are a plurality of energy distribution strategies in the strategy library. The initial energy distribution strategy is an energy management scheme preliminarily screened from the preset strategy library according to the current working mode of the energy storage system and the real-time running data of the energy storage system, and needs to be further optimized to form a final execution strategy. Each energy distribution strategy includes a control mode of at least one type of running data of the energy storage system. For example, the energy distribution strategy 1 only includes a control mode related to charging data of the energy storage system, the energy distribution strategy 2 includes power supply data of the energy storage system to the external load, power supply data of the energy storage system to each internal device, and state data of each internal device of the energy storage system, and the control mode corresponding to each type of data.

[0036] The control mode of each type of operation data includes control parameters. For example, the control parameters corresponding to the charging data of the energy storage system include a charging voltage threshold, a charging current threshold, a charging power threshold, a charging capacity threshold, a charging time range, and a charging efficiency, etc., for controlling the stability and quality of charging. The control parameters corresponding to the power supply data of the energy storage system to the external load include an output voltage threshold, an output current threshold, an output power threshold, a power supply time range, and a power supply efficiency, etc. The control parameters corresponding to the power supply data of the energy storage system to the internal devices refer to the control parameters corresponding to the power supply data of the energy storage system to the external load. The control parameters corresponding to the state data of the internal devices of the energy storage system include a cutoff voltage and a temperature protection threshold for battery charging or discharging, a switching frequency of the converter, an opening degree of the valve or a flow speed of the liquid cooling device, etc., for ensuring the safety and service life of the devices.

[0037] In the embodiment, a "working mode-strategy mapping relationship library" can be established, each energy allocation strategy includes a control mode of at least one type of operation data of the energy storage system, each control mode includes a plurality of control parameters, and an initial energy allocation strategy can be preliminarily determined according to the working mode of the energy storage system and the operation data of the energy storage system, so as to facilitate subsequent fine selection and adjustment of the control parameters in the initial energy allocation strategy according to the historical operation data of the energy storage system.

[0038] In the embodiment, the prediction results of the energy storage system for energy allocation to the external load and the internal devices respectively at present are obtained based on the historical operation data of the energy storage system, and the prediction results include:

[0039] In the embodiment, the prediction results of the energy storage system for energy allocation to the external load and the internal devices respectively at present are obtained based on the historical operation data of the energy storage system, and the prediction results include:

[0040] The historical operation data of the energy storage system is classified to obtain first type data and second type data, the first type data is data with time sequence characteristics, and the second type data is data without time sequence characteristics;

[0041] The first type data is input into an autoregressive integrated moving average model to obtain a first prediction result, the second type data is input into a random forest model to obtain a second prediction result, the first prediction result and the second prediction result are weighted and fused and classified to obtain the prediction results of the energy storage system for energy allocation to the external load and the internal devices respectively at present.

[0042] In the embodiment, different types of data have differentiated characteristics and prediction rules, and classifying the historical operation data of the energy storage system can significantly improve the prediction accuracy and strategy effectiveness. The first type of data is data with time series characteristics, such as load power, renewable energy power generation, etc. The second type of data is data without time series characteristics, such as battery charge, temperature of each device in the energy storage system, health status of each device, etc.

[0043] The continuity and dynamic correlation of the data value of the first data change with time, which needs to be captured by the autoregressive integrated moving average model. In the embodiment, if the first type of data and the non-time series data are modeled together, the model cannot effectively separate the correlation in the time dimension, resulting in magnified prediction error. Therefore, the first type of data needs to be analyzed separately. The direct correlation of the data value of the second data with time is weak, which needs to rely on physical laws, device characteristics or multivariate coupling relationships, such as the nonlinear relationship between charge and charge depth. Therefore, the second type of data needs to be input into the random forest model for analysis.

[0044] In the embodiment, the first prediction result and the second prediction result are weighted and fused to obtain the prediction result of the energy allocation of the energy storage system to the external load and each device in the energy storage system, including: determining the weights corresponding to the first prediction result and the second prediction result based on the charge of the battery in the energy storage system, and weighting and fusing the first prediction result and the second prediction result based on the weights corresponding to the first prediction result and the second prediction result to obtain the prediction result of the energy allocation of the energy storage system to the external load and each device in the energy storage system.

[0045] In the embodiment, because the battery charge has a key influence on the energy allocation decision of the energy storage system, when the battery charge is greater than the preset charge, the weight corresponding to the first prediction result is increased by the first step, which can make the energy allocation strategy more actively respond to the change of the external load energy demand. When the battery charge is less than or equal to the preset charge, to avoid over-discharge damage to the battery life and to ensure power supply reliability, the weight corresponding to the second prediction result is increased by the second step, so that the energy allocation pays more attention to protecting the battery. After determining the weights corresponding to the prediction results, the first prediction result and the second prediction result are multiplied by the corresponding weights and summed, and the prediction result of the energy allocation is obtained through the calculation method of weighted fusion. According to the prediction result of the allocation object, the prediction result of the energy allocation of the energy storage system to the external load and each device in the energy storage system is obtained, which can assist in selecting key control parameters from the initial energy allocation strategy to obtain a more accurate target energy allocation strategy.

[0046] S104: selecting a key control parameter from the initial energy distribution strategy based on a prediction result of the current energy distribution of the energy storage system to the external load and the internal devices respectively, and managing the current energy distribution of the energy storage system based on the key control parameter.

[0047] In the embodiment, after determining the target energy distribution strategy, i.e., the key control parameter, the processor can analyze the control parameter in the strategy, generate executable hardware control instructions, and control the corresponding hardware devices according to the control instructions to manage the energy of the energy storage system.

[0048] As can be seen from the above, the embodiments of the present application can comprehensively grasp the current running state of the system by acquiring the charging data of the energy storage system, the power supply data of the external load, the power supply data of the internal devices, and the state data of the internal devices in real time. On this basis, the working mode of the energy storage system is determined, so as to dynamically select the initial energy distribution strategy that adapts to the current working mode from the plurality of preset energy distribution strategies, thereby ensuring the matching of the strategy selection and the current running condition and avoiding the rigid problem of the traditional fixed threshold control. Further, in order to improve the rationality of energy distribution, the embodiments of the present application also use the historical running data of the energy storage system to predict the energy distribution demand of the system on the external load and the internal devices; and the key control parameter is selected from the initial energy distribution strategy in combination with the prediction result, so as to dynamically adjust the current energy distribution, thereby realizing the adaptive optimization of the energy distribution strategy. Compared with the prior art which only relies on a single indicator such as the state of charge for fixed threshold control, the embodiments of the present application comprehensively consider multi-dimensional running data, working modes, and existing demand prediction, thereby significantly improving the rationality and flexibility of energy distribution, effectively avoiding energy waste or insufficient supply, prolonging the service life of the energy storage system, and improving the running efficiency and safety of the entire energy system.

[0049] In an embodiment of the present application, the initial energy distribution strategy is selected from the plurality of energy distribution strategies based on the working mode of the energy storage system and the running data of each type of the energy storage system, including:

[0050] determining the correlation degree between the working mode of the energy storage system and the running data of each type of the energy storage system, and determining the weight coefficient corresponding to the running data of each type based on each correlation degree;

[0051] normalizing each type of running data to obtain a normalized value, and performing weighted summation on the normalized value of each type of running data and the weight coefficient corresponding to the running data of the type to obtain the running coordination degree of the energy storage system;

[0052] An initial energy allocation strategy is selected from the plurality of energy allocation strategies based on a comparison result of the operation coordination degree of the energy storage system and a preset coordination degree threshold.

[0053] In the embodiment, first, data cleaning and feature construction are needed for each type of operation data of the energy storage system. The data cleaning includes processing missing values by using linear interpolation method, processing abnormal values by using interquartile range method, and moving average filtering processing for high-frequency fluctuation data, and the window size is determined according to the data acquisition frequency of the high-frequency fluctuation data. After the data cleaning of each type of operation data of the energy storage system, feature extraction is needed for the cleaned data in order to calculate the correlation degree in the subsequent.

[0054] In the embodiment, the correlation degree matrix of working mode-operation data can be constructed based on expert knowledge modeling. There are multiple different correlation degrees between each working mode and each type of operation data. The greater the correlation degree, the greater the weight coefficient of the type of operation data corresponding to the working mode. In the embodiment, because different types of operation data cannot be directly compared and calculated, each type of operation data can be normalized to obtain a normalized value, and then the normalized value of each type of operation data is weighted and summed with the weight coefficient corresponding to the type of operation data to obtain the operation coordination degree of the energy storage system.

[0055] Under a specific working mode, the weight coefficient corresponding to each type of operation data of the energy storage system can be fixed or variable. When the weight coefficient changes, the operation coordination degree of the energy storage system can be calculated based on the following formula.

[0056] wherein S is the operation coordination degree of the energy storage system, n is the type of operation data, is the normalized risk factor of the jth type of operation data, such as the normalized risk factor of the discharge depth of the energy storage system or the temperature of the battery pack, etc. is the weight coefficient of the jth type of operation data.

[0057] The normalized risk factor needs to map the physical threshold value of each type of operation data of the energy storage system, such as converting the risk factor by using an S-shaped risk function, and the S-shaped risk function is .

[0058] The normalized risk factor is: wherein is the normalized risk factor, k is the steepness parameter of the curve, which determines the sensitivity of the risk change; x j is the risk driving variable, which represents the value corresponding to the jth type of operation data; a is the center point of the curve, which corresponds to the threshold inflection point of the risk driving variable.

[0059] In the embodiment, the initial energy distribution strategy is selected from the plurality of energy distribution strategies based on a comparison result of the operation coordination degree of the energy storage system and the preset coordination degree threshold.

[0060] For example, if the working mode is the discharging mode, the plurality of energy distribution strategies include the energy distribution strategy 1 including only the control mode related to the power supply data of the energy storage system to the external load, and the energy distribution strategy 2 including the power supply data of the energy storage system to the external load, the power supply data of the energy storage system to each device inside the energy storage system, and the state data of each device inside the energy storage system, and the control mode corresponding to each type of data. When the operation coordination degree of the energy storage system is greater than the preset coordination degree threshold, the energy distribution strategy 2 can be selected to better distribute the energy of the energy storage system. When the operation coordination degree of the energy storage system is less than or equal to the preset coordination degree threshold, the energy distribution strategy 1 can be selected to ensure the power supply stability of the external load in the discharging mode without considering the state of each device inside the energy storage system.

[0061] From the above, it can be concluded that the embodiment of the present application first determines the weight coefficients corresponding to each type of operation data by determining the correlation degree between the current working mode of the energy storage system and each type of operation data, which can measure the importance of different types of operation data in the current working mode. Then, the embodiment of the present application normalizes each type of operation data and weights and sums the weight coefficients corresponding to each type of operation data to obtain the operation coordination degree. The normalization process eliminates the influence of different data dimensions, and the weighted sum comprehensively considers each type of data and its weight, so that the operation coordination degree can comprehensively and accurately reflect the current operation state of the energy storage system. Finally, the initial energy distribution strategy is selected based on the comparison result of the operation coordination degree and the preset coordination degree threshold, such as flexibly selecting different energy distribution strategies according to the size of the operation coordination degree in the discharging mode, which can not only ensure the power supply stability of the external load, but also optimize the overall energy distribution of the system, thereby enhancing the system performance and operation efficiency.

[0062] In an embodiment of the present application, the energy management method of the energy storage system further comprises:

[0063] calculating the change amount of each type of operation data of the energy storage system within a first time length after the current time;

[0064] normalizing the change amount of each type of operation data of the energy storage system within the first time length to obtain a plurality of normalization results corresponding to each type of operation data, respectively;

[0065] determine an importance level of the type of operation data based on the normalized result corresponding to the type of operation data, and update the weight coefficient corresponding to the type of operation data based on the importance level of the type of operation data, until the weight coefficients corresponding to all types of operation data are updated, to obtain the updated weight coefficients corresponding to the types of operation data;

[0066] weight the normalized values of each type of operation data by the weight coefficients corresponding to the type of operation data to obtain the operation coordination degree of the energy storage system, including:

[0067] weight the normalized values of each type of operation data by the updated weight coefficients corresponding to the type of operation data to obtain the updated operation coordination degree of the energy storage system.

[0068] In the embodiment, the current working mode of the energy storage system includes any one of the charging mode, the discharging mode, the charging and discharging mode, or the standby mode. Even if the variation amount of each type of operation data of the energy storage system in the first time period is the same in different working modes, the adjustment of the weight coefficient of the energy storage system in different working modes is different. For example, when the energy storage system is in the charging mode or the standby mode, even if the variation amount of the temperature of the battery pack in the first time period is the same, the adjustment amount of the weight coefficient corresponding to the temperature of the battery pack when the energy storage system is in the charging mode is greater than the adjustment amount of the weight coefficient corresponding to the temperature of the battery pack when the energy storage system is in the standby mode.

[0069] The embodiment obtains a plurality of normalized results corresponding to a plurality of types of operation data based on the normalized values of the variation amounts of the types of operation data in the first time period, eliminates the influence of different data variation amounts due to the differences in dimensions and orders of magnitude, and makes the data comparable. Then the embodiment determines the importance level of each type of operation data based on the normalized results, and updates the weight coefficient accordingly, fully considers the influence of data variation on system operation, so that the updated weight coefficient can better meet the actual operation requirements of the system. Finally, the normalized values of each type of operation data are weighted and summed by the updated weight coefficients corresponding to the type of operation data to obtain the updated operation coordination degree of the energy storage system, which significantly improves the accuracy and strategy adaptability of the state evaluation of the energy storage system.

[0070] In an embodiment of the present application, the energy management method of the energy storage system further includes:

[0071] In response to detecting a fault signal inside the energy storage system, determining a fault location based on the fault signal, and determining the type of operation data of the energy storage system that is abnormal based on the fault location;

[0072] update the weight coefficients corresponding to each type of operation data of the energy storage system based on the type of operation data of the energy storage system that has an abnormality and the type of operation data of the energy storage system that has no abnormality, to obtain the updated weight coefficients corresponding to each type of operation data of the energy storage system;

[0073] weight the normalized values of each type of operation data by the weight coefficients corresponding to the type of operation data to obtain the operation coordination degree of the energy storage system, including:

[0074] weight the normalized values of each type of operation data by the updated weight coefficients corresponding to the type of operation data to obtain the updated operation coordination degree of the energy storage system.

[0075] In this embodiment, when a fault signal is detected inside the energy storage system, the energy management system of the energy storage system can determine the specific location of the fault based on the fault signal, for example, by a rule-based judgment or a fault diagnosis algorithm of a machine learning model to determine the specific location of the fault. After determining the fault location, further determine the type of operation data of the energy storage system related to the fault, for example, if the fault occurs in the battery pack, the operation data related to the battery pack, such as battery voltage, battery internal resistance, battery remaining capacity, etc. may be determined as abnormal data. The weight coefficients corresponding to the state data of each device inside the energy storage system will be reduced.

[0076] In this embodiment, the weight coefficients corresponding to each type of operation data are updated according to the type of operation data of the energy storage system that has an abnormality and the type of operation data of the energy storage system that has no abnormality. This means that when the system fails, the importance of different types of operation data to the overall operation state of the energy storage system needs to be re-evaluated, the weight coefficient of the abnormal data type is reduced, and the weight coefficient of the non-abnormal data type is increased to more accurately reflect the current actual operation condition of the energy storage system.

[0077] After determining the updated weight coefficients corresponding to each type of operation data, the normalized values of each type of operation data are weighted and summed by the updated weight coefficients to obtain the updated operation coordination degree of the energy storage system.

[0078] This embodiment updates the weight coefficients to make the operation coordination degree more reflect the true state of the energy storage system under fault conditions, and the updated operation coordination degree can be used to more accurately select the initial energy allocation strategy, thereby improving the reliability and safety of the energy storage system.

[0079] In an embodiment of the present application, the prediction result of energy allocation includes a plurality of prediction features, and the plurality of prediction features include at least two of the following: a peak amplitude of a current external load, an energy consumption peak of each internal device, or a time coupling relationship between each two devices inside the energy storage system;

[0080] selecting a key control parameter from the initial energy distribution strategy based on a prediction result of current energy distribution of the energy storage system to the external load and each device in the energy storage system respectively, including:

[0081] determining a target prediction feature in the prediction result of the energy distribution, the target prediction feature having an influence level on the operation of the energy storage system greater than a preset influence level;

[0082] based on the target prediction feature, screening a control parameter having an association degree greater than a preset association degree threshold from control parameters contained in the initial energy distribution strategy, as the key control parameter.

[0083] In the embodiment, the peak amplitude of the current external load refers to a maximum power value that can be reached by the external load at the current time, which directly reflects the "highest upper limit" of the energy demand of the external load. The energy consumption peak of each device in the energy storage system refers to the maximum energy consumption power reached by each device required for the operation of the energy storage system itself, which directly affects the internal energy loss of the energy storage system, such as cooling systems, lighting devices, and converters. The time coupling relationship between each two devices in the energy storage system refers to the association characteristics of any two devices in the energy storage system in the running time, that is, the start-stop and load change of one device will cause the running state change of another device within a certain time range, for example, the cooling system needs to be started synchronously within 5 minutes after the converter is started to maintain its temperature stability. This relationship determines the time sequence and coordination logic that the energy distribution needs to follow.

[0084] In the embodiment, the prediction result of the energy distribution includes a plurality of prediction features, and the target prediction feature is determined according to a comparison result of the influence level of each prediction feature on the operation of the energy storage system and a preset influence level.

[0085] The influence level of the prediction result of the energy distribution on the operation of the energy storage system is determined, including:

[0086] For each prediction feature contained in the prediction result of the energy distribution, two types of evaluation dimensions corresponding to the prediction feature are determined, the two types of evaluation dimensions including any two of a safety dimension, an energy efficiency dimension, and a stability dimension; a three-level threshold interval is preset for each type of evaluation dimension, corresponding to a first influence level, a second influence level, and a third influence level, respectively, the first influence level being greater than the second influence level, and the second influence level being greater than the third influence level; the actual value of each evaluation dimension corresponding to each prediction feature is calculated, the actual value is matched to the corresponding threshold interval to obtain the influence level of each evaluation dimension, and each influence level is assigned a value; the influence levels of each evaluation dimension under the same prediction feature are multiplied by the weight coefficients corresponding to each evaluation dimension and then summed to obtain a comprehensive influence score of the prediction feature; the influence level of the prediction feature on the operation of the energy storage system is determined based on a comparison result of the comprehensive influence score and a preset influence threshold.

[0087] In the embodiment, the safety dimension evaluation index corresponding to the peak amplitude of the current external load is the system output power redundancy rate, which can be expressed as the difference between the maximum output power of the energy storage system and the peak amplitude of the current external load divided by the maximum output power of the energy storage system, and then multiplied by 100%. The stability dimension corresponding to the peak amplitude of the current external load is the voltage fluctuation deviation rate, which can be expressed as the absolute value of the difference between the actual voltage when the peak amplitude of the current external load occurs and the rated voltage divided by the rated voltage, and then multiplied by 100%. The safety dimension corresponding to the energy consumption peak of each internal device is the device overload risk coefficient, which can be expressed as the ratio of the energy consumption peak of the internal device to the rated power of the device. The energy efficiency dimension corresponding to the energy consumption peak of each internal device is the device energy consumption over-standard rate, which can be expressed as the difference between the energy consumption peak of the internal device and the regular energy consumption threshold of the device divided by the regular energy consumption threshold of the device, and then multiplied by 100%. The safety dimension corresponding to the time coupling relationship between each two devices in the energy storage system is the cooperative operation risk index, which can be expressed as the ratio of the high-load overlapping operation time length of the two devices to the safety threshold. The energy efficiency dimension corresponding to the time coupling relationship between each two devices in the energy storage system is the coupling energy consumption increment rate, which can be expressed as the percentage of the additional energy consumption of the two devices due to time coupling to the total energy consumption of the two devices running independently.

[0088] The influence level of the predicted feature on the operation of the energy storage system is determined based on a comparison result of the comprehensive influence score and a preset influence threshold.

[0089] For example, the preset influence threshold includes a first preset influence threshold 3A and a second preset influence threshold 2A. If the comprehensive influence score is greater than the first preset influence threshold, the influence level is high; if the comprehensive influence score is greater than the second preset influence threshold and less than or equal to the first preset influence threshold, the influence level is medium; and if the comprehensive influence score is less than or equal to the first preset influence threshold, the influence level is low.

[0090] In this embodiment, it is assumed that the preset influence level is a medium influence level, and only the predicted features with an influence level on the operation of the energy storage system greater than the medium influence level in the prediction result of the energy allocation can be used as target predicted features. After determining the target predicted features, the control parameters associated with the target predicted features with an association degree greater than a preset association degree threshold can be selected from the control parameters included in the initial energy allocation strategy as key control parameters. The selection method can include obtaining the key control parameters based on the target predicted features and the control parameters by using a selection model. The selection model can be a data classification model in the prior art, such as a convolutional neural network model, a clustering model, or the like. The selection method can also include first layering the control parameters, and the control parameters in different layers have different importance levels. After selecting a plurality of candidate key parameters in each layer, the plurality of candidate key control parameters are subjected to redundancy screening to obtain the key control parameters. As can be seen from the above, the embodiments of the present application first determine that the prediction result of the energy allocation covers a plurality of important predicted features, and these predicted features can reflect the conditions related to the energy allocation of the energy storage system. Then, by determining the target predicted features with an influence level greater than the preset influence level on the operation of the energy storage system, the predicted features with the most significant influence on the system operation can be selected, and the interference of irrelevant or less influential predicted features is avoided. Finally, the embodiments of the present application select the key control parameters with an association degree greater than a preset association degree threshold from the control parameters included in the initial energy allocation strategy based on the target predicted features, so that the selected key control parameters are closely related to the key influencing factors of the system operation. In this way, the energy allocation based on these key control parameters can more targetedly address the key problems in the operation of the energy storage system, and effectively improve the rationality and accuracy of the energy allocation.

[0091] In an embodiment of the present application, selecting, based on the target predicted features, the control parameters associated with the target predicted features with an association degree greater than a preset association degree threshold from the control parameters included in the initial energy allocation strategy as key control parameters includes:

[0092] dividing the control parameters included in the initial energy allocation strategy into a plurality of control parameter layers;

[0093] For each control parameter layer, a plurality of association degrees between each control parameter in the layer and each target predicted feature are calculated. If the plurality of association degrees are all greater than a preset association degree threshold, the control parameter is marked as a candidate key control parameter;

[0094] After all the control parameters in the plurality of control parameter layers are processed, a plurality of candidate key control parameters are obtained, and the key control parameters are obtained by performing redundancy screening on the plurality of candidate key control parameters.

[0095] In the embodiment, the control parameters included in the initial energy distribution strategy are divided into three levels according to the core attributes of the control functions: a basic control parameter level, such as a power supply reference voltage of an external load, a rated operating current of an internal device, and the like, which maintains the basic operation of the system; an adjustment control parameter level, such as a charge-discharge power adjustment coefficient, a load priority weight, and the like, which is used for dynamically optimizing energy distribution; and a protection control parameter level, such as a battery over-discharge protection threshold, a device over-temperature shutdown threshold, and the like, which ensures the safety of the system. The hierarchical division of the control parameters structures the parameter system, avoiding misjudgment of the correlation degree due to mixed functions of the parameters during screening.

[0096] For each control parameter level, the correlation degree of each control parameter in the level with all target predicted features is calculated one by one, which can be represented by a Pearson correlation coefficient or the like. Only when the correlation degree of a control parameter with all target predicted features is greater than a preset correlation degree threshold, the control parameter is marked as a candidate key control parameter, ensuring that the candidate key control parameter can comprehensively respond to the influence of all key predicted features.

[0097] For all candidate key control parameters generated in the three control parameter levels, redundant parameters are removed by calculating the functional overlap degree between the parameters. For example, the key control parameters are obtained by redundancy screening of the multiple candidate key control parameters, including:

[0098] If the correlation degrees of two candidate key control parameters with the same predicted feature are both greater than a first value, the parameter with the highest adjustment sensitivity is retained from the two candidate key control parameters, and the key control parameter is obtained.

[0099] In the embodiment, after obtaining the multiple candidate key control parameters, first, for each group of candidate key control parameters, it is determined whether there are two parameters with a correlation degree with the same target predicted feature both greater than a preset first value. If such a situation exists, it indicates that the two parameters have redundancy in the function of regulating the target predicted feature. At this time, the adjustment sensitivity of the two parameters is quantitatively compared by a preset sensitivity test method, and finally the parameter with higher adjustment sensitivity is retained, and the redundant parameter with lower sensitivity is removed, so as to obtain the key control parameter with no functional redundancy and higher regulation efficiency.

[0100] As can be seen from the above, the embodiment first divides the control parameter levels of the initial energy distribution strategy, which can orderly sort the parameters; then calculates the correlation degree of each layer control parameter with the target predicted feature and marks the candidate key control parameter, which can preliminarily screen the important control parameters; finally, the redundancy screening is performed, the parameter with the highest adjustment sensitivity is retained, and the redundancy is removed, thereby improving the effectiveness of the energy management strategy of the energy storage system.

[0101] Corresponding to the energy management method of the energy storage system of the above embodiment, Figure 2A structural block diagram of an energy management system of an energy storage system is provided in an embodiment of the present application. For ease of illustration, only parts related to the embodiments of the present application are shown. Referring to Figure 2 The energy management system 20 of the energy storage system includes a data acquisition module 21, a first selection module 22, a second selection module 23, and an energy management module 24.

[0102] The data acquisition module 21 is configured to acquire, in real time, operation data of the energy storage system, the operation data including power supply data, state data of each device in the energy storage system, and load power data.

[0103] The first selection module 22 is configured to select an initial energy distribution strategy from a plurality of energy distribution strategies based on an application scenario of the energy storage system and the operation data of the energy storage system, the initial energy distribution strategy including at least one type of control parameter corresponding to adjustment of the power supply data, the state data of each device in the energy storage system, and the load power data.

[0104] The second selection module 23 is configured to obtain a prediction result of energy distribution based on historical operation data of the energy storage system, select a key control parameter from the initial energy distribution strategy based on the prediction result of energy distribution, and obtain a target energy distribution strategy based on the key control parameter.

[0105] The energy management module 24 is configured to manage energy of the energy storage system based on the target energy distribution strategy.

[0106] In an embodiment of the present application, the first selection module 22 is specifically configured to:

[0107] determine a degree of correlation between a current working mode of the energy storage system and each type of operation data of the energy storage system, and determine a weight coefficient corresponding to each type of operation data based on each degree of correlation;

[0108] normalize each type of operation data to obtain a normalized value, and perform weighted summation on the normalized value of each type of operation data and the weight coefficient corresponding to the type of operation data to obtain an operation coordination degree of the energy storage system;

[0109] select the initial energy distribution strategy from the plurality of energy distribution strategies based on a comparison result of the operation coordination degree of the energy storage system and a preset coordination degree threshold.

[0110] In an embodiment of the present application, the energy management system of the energy storage system further includes a weight updating module, which is configured to:

[0111] calculate a variation of each type of operation data of the energy storage system within a first time length after the current time;

[0112] The change amount of each type of operation data of the energy storage system in the first time length is normalized respectively to obtain a plurality of normalized results corresponding to the plurality of types of operation data respectively;

[0113] The importance level of each type of operation data is determined based on the normalized result corresponding to the type of operation data, and the weight coefficient corresponding to the type of operation data is updated based on the importance level of the type of operation data until the weight coefficients corresponding to all types of operation data are updated to obtain the updated weight coefficients corresponding to each type of operation data;

[0114] The first selection module 22 is specifically configured to:

[0115] The normalized value of each type of operation data is weighted and summed with the updated weight coefficient corresponding to the type of operation data to obtain the updated operation coordination degree of the energy storage system.

[0116] In an embodiment of the present application, the weight updating module is further configured to:

[0117] In response to detecting a fault signal inside the energy storage system, determining a fault location based on the fault signal, and determining the type of operation data of the energy storage system that has an abnormality based on the fault location;

[0118] The weight coefficients corresponding to each type of operation data of the energy storage system are updated based on the type of operation data of the energy storage system that has an abnormality and the type of operation data of the energy storage system that does not have an abnormality to obtain the updated weight coefficients corresponding to each type of operation data;

[0119] The first selection module 22 is specifically configured to:

[0120] The normalized value of each type of operation data is weighted and summed with the updated weight coefficient corresponding to the type of operation data to obtain the updated operation coordination degree of the energy storage system.

[0121] In an embodiment of the present application, the prediction result of energy allocation includes a plurality of prediction features, and the plurality of prediction features include at least two of the following: a peak amplitude of a current external load, an energy consumption peak of each internal device, or a time coupling relationship between each two devices inside the energy storage system;

[0122] The energy management module 24 is specifically configured to:

[0123] Determine a target prediction feature in the prediction result of energy allocation, which has an influence level on the operation of the energy storage system greater than a preset influence level;

[0124] Based on the target prediction feature, filter out control parameters with an association degree greater than a preset association degree threshold from control parameters contained in the initial energy allocation strategy, as key control parameters.

[0125] In one embodiment of this application, the energy management module 24 is specifically used for:

[0126] The control parameters included in the initial energy allocation strategy are hierarchically divided to obtain multiple control parameter layers;

[0127] For each control parameter layer, calculate multiple correlation degrees between each control parameter in that layer and each target prediction feature. If multiple correlation degrees are all greater than a preset correlation degree threshold, then mark the control parameter as a candidate key control parameter.

[0128] After processing all control parameters in multiple control parameter layers, multiple candidate key control parameters are obtained. Redundancy screening is performed on these candidate key control parameters to obtain the key control parameters.

[0129] In one embodiment of this application, the energy management module 24 is specifically used for:

[0130] If two candidate key control parameters have a correlation degree with the same predicted feature that is greater than the first value, then the parameter with the highest adjustment sensitivity among the two candidate key control parameters is retained to obtain the key control parameter.

[0131] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the data acquisition module 21, the first selection module 22, the second selection module 23, and the energy management module 24 are shown.

[0132] It should be appreciated that in the embodiments of the present application, the processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0133] The input device 302 can include a touchpad, a fingerprint collection sensor (for collecting fingerprint information and direction information of a fingerprint of a user), a microphone, etc., and the output device 303 can include a display (LCD, etc.), a speaker, etc.

[0134] The memory 304 can include a read-only memory and a random access memory, and provide instructions and data for the processor 301. A part of the memory 304 can also include a non-volatile random access memory. For example, the memory 304 can also store operating data of the energy storage system, key control parameters, etc.

[0135] In specific implementations, the processor 301, the input device 302 and the output device 303 described in the embodiments of the present application can execute the implementation manners described in the energy storage system energy management method provided by the embodiments of the present application, and can also execute the implementation manners of the electronic device described in the embodiments of the present application, which will not be described herein again.

[0136] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the implementation. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0137] The computer readable storage medium can be an internal storage unit of the electronic device of any of the preceding embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0138] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0140] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the embodiments of the apparatus described above are merely illustrative, and the unit division is merely logical function division, and there can be another division manner in actual implementation. For example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, or can be in electrical, mechanical or other forms.

[0141] The unit described as a separate component can or can not be physically separate, and the component shown as a unit can or can not be a physical unit, that is, can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0142] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0143] The above is merely specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An energy management method for an energy storage system, characterized in that, include: Real-time acquisition of various types of operational data from the energy storage system, including charging data, power supply data from the energy storage system to external loads, power supply data from the energy storage system to internal devices, and status data of internal devices. Based on the current operating mode of the energy storage system and the various types of operating data of the energy storage system, an initial energy allocation strategy is selected from multiple energy allocation strategies. Each energy distribution strategy includes a control method for at least one type of operating data of the energy storage system, and the control method includes control parameters; the operating mode is any one of charging mode, discharging mode, charge-discharge mode, and standby mode; Based on the historical operating data of the energy storage system, the predicted results of the current energy distribution of the energy storage system to the external load and the internal devices are obtained; Based on the predicted results of the energy allocation of the energy storage system to the external load and the internal devices, key control parameters are selected from the initial energy allocation strategy, and the current energy allocation of the energy storage system is managed based on the key control parameters. The energy distribution prediction results include multiple prediction features, which include at least two of the following: the peak amplitude of the current external load, the peak energy consumption of each internal device, or the time coupling relationship between every two devices within the energy storage system. The key control parameters selected from the initial energy allocation strategy based on the predicted energy allocation results of the energy storage system for the external load and various internal devices include: Identify target prediction features in the energy allocation prediction results whose impact on the operation of the energy storage system is greater than a preset impact level; Based on the target prediction features, control parameters with a correlation degree greater than a preset correlation degree threshold are selected from the control parameters included in the initial energy allocation strategy and used as key control parameters.

2. The energy management method for an energy storage system as described in claim 1, characterized in that, The process of selecting an initial energy allocation strategy from multiple energy allocation strategies based on the current operating mode of the energy storage system and various types of operational data of the energy storage system includes: Determine the correlation between the current operating mode of the energy storage system and various types of operating data of the energy storage system, and determine the weight coefficient corresponding to each type of operating data based on the correlation degree; Normalize the operational data of each type to obtain normalized values, and then sum the normalized values ​​of each type of operational data with the corresponding weight coefficients to obtain the operational coordination degree of the energy storage system. Based on the comparison results between the operational coordination degree of the energy storage system and the preset coordination degree threshold, an initial energy allocation strategy is selected from multiple energy allocation strategies.

3. The energy management method for an energy storage system as described in claim 2, characterized in that, Also includes: Calculate the changes in various types of operational data of the energy storage system within the first time interval following the current moment; The changes in the various types of operational data of the energy storage system within the first time period are normalized to obtain multiple normalization results corresponding to the various types of operational data. Based on the normalization result corresponding to each type of running data, the importance level of that type of running data is determined. Based on the importance level of that type of running data, the weight coefficients corresponding to that type of running data are updated until the weight coefficients corresponding to all types of running data are updated, and the updated weight coefficients corresponding to each type of running data are obtained. The step of obtaining the operational coordination degree of the energy storage system by weighting and summing the normalized values ​​of each type of operational data with the corresponding weight coefficients includes: The updated operational coordination degree of the energy storage system is obtained by weighting and summing the normalized values ​​of each type of operational data with the corresponding weight coefficients of the updated operational data of that type.

4. The energy management method for an energy storage system as described in claim 2, characterized in that, Also includes: In response to the detection of a fault signal inside the energy storage system, the fault location is determined based on the fault signal, and the type of abnormal operating data of the energy storage system is determined based on the fault location; The weight coefficients of each type of operational data in the energy storage system are updated based on the types of operational data that have experienced anomalies and the types of operational data that have not experienced anomalies, resulting in updated weight coefficients for each type of operational data. The step of obtaining the operational coordination degree of the energy storage system by weighting and summing the normalized values ​​of each type of operational data with the corresponding weight coefficients includes: The updated operational coordination degree of the energy storage system is obtained by weighting and summing the normalized values ​​of each type of operational data with the corresponding weight coefficients of the updated operational data of that type.

5. The energy management method for an energy storage system as described in claim 1, characterized in that, The step of selecting control parameters from the control parameters included in the initial energy allocation strategy based on the target prediction features, whose correlation with the target prediction features is greater than a preset correlation threshold, as key control parameters includes: The control parameters included in the initial energy allocation strategy are hierarchically divided to obtain multiple control parameter layers; For each control parameter layer, calculate multiple correlation degrees between each control parameter in that layer and each target prediction feature. If all of the multiple correlation degrees are greater than a preset correlation degree threshold, then mark the control parameter as a candidate key control parameter. After processing all the control parameters in the multiple control parameter layers, multiple candidate key control parameters are obtained. Redundancy screening is performed on the multiple candidate key control parameters to obtain the key control parameters.

6. The energy management method for an energy storage system as described in claim 5, characterized in that, The process of obtaining key control parameters by redundancy screening of the multiple candidate key control parameters includes: If two candidate key control parameters have a correlation degree with the same predicted feature that is greater than the first value, then the parameter with the highest adjustment sensitivity among the two candidate key control parameters is retained to obtain the key control parameter.

7. An energy management system for an energy storage system, characterized in that, include: The data acquisition module is used to acquire various types of operational data of the energy storage system in real time. These operational data include the charging data of the energy storage system, the power supply data of the energy storage system to external loads, the power supply data of the energy storage system to internal devices, and the status data of the internal devices of the energy storage system. The first selection module is used to select an initial energy allocation strategy from multiple energy allocation strategies based on the current working mode of the energy storage system and various types of operating data of the energy storage system. Each energy distribution strategy includes a control method for at least one type of operating data of the energy storage system, and the control method includes control parameters; the operating mode is any one of charging mode, discharging mode, charge-discharge mode, and standby mode; The second selection module is used to obtain the predicted results of the energy allocation of the energy storage system to the external load and the internal devices based on the historical operating data of the energy storage system. The predicted results of the energy allocation include multiple prediction features, which include at least two of the following: the peak amplitude of the current external load, the peak energy consumption of each internal device, or the time coupling relationship between every two devices in the energy storage system. The energy management module is used to select key control parameters from the initial energy allocation strategy based on the predicted results of the current energy allocation of the energy storage system to external loads and internal devices, and to manage the current energy allocation of the energy storage system based on the key control parameters. The energy management module is specifically used to: determine the target prediction features in the energy allocation prediction results whose impact level on the operation of the energy storage system is greater than a preset impact level; Based on the target prediction features, control parameters with a correlation degree greater than a preset correlation degree threshold are selected from the control parameters included in the initial energy allocation strategy and used as key control parameters.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images