Microgrid electrochemical energy storage management method and system, terminal and storage medium

Abstract

The invention belongs to the technical field of power grid energy storage management, and particularly relates to an electrochemical energy storage management method and system for a micro-grid, a terminal and a storage medium, and the method comprises the steps: obtaining the real-time multi-dimensional data of the micro-grid through a plurality of sensors disposed in the micro-grid, and transmitting the obtained multi-dimensional data to a data processing center through a communication module; the obtained multi-dimensional data provides a comprehensive and accurate information basis for load prediction, and the load prediction model constructed by using the machine learning algorithm can accurately predict the energy demand in the future preset time period based on the real-time data, thereby guiding the charging and discharging strategy of the electrochemical energy storage system, and improving the performance of the electrochemical energy storage system. And the accuracy and the real-time performance of energy storage and scheduling are obviously improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid energy storage management, and specifically relates to an electrochemical energy storage management method, system, terminal and storage medium for a microgrid. Background Art

[0002] In the operation and management of microgrids, effective storage and dispatch of energy are key links to ensure power supply stability and economy. Traditional electrochemical energy storage management methods often rely on manual experience for charge and discharge control, lack of comprehensive perception and accurate prediction of the real-time operating status of microgrids, resulting in low energy utilization efficiency, and difficulty in making timely and effective responses in special circumstances such as load fluctuations, weather changes and holidays.

[0003] Specifically, traditional energy storage management usually relies only on limited load data and grid electricity price information, ignoring the impact of weather forecasts, holidays and other multi-dimensional factors on energy demand. This single-dimensional data processing method limits the accuracy of load forecasting, causing the charging and discharging strategies of energy storage systems to often lag behind changes in actual demand, and failing to maximize the capacity and efficiency of energy storage equipment.

[0004] In addition, traditional energy storage management methods do not make full use of the time attributes of data and fail to fully tap the value of timestamp information in load forecasting, such as the date's position in the year and the day of the week, which all have a significant impact on load changes.

[0005] In the formulation of charging and discharging strategies, traditional methods are often too simple and rigid, lacking dynamic consideration of the current battery power state and health status, and sensitive response to the real-time electricity price of the power grid. This may not only lead to premature aging of the battery, but also increase the operating cost of the power grid and reduce the overall economic benefits. Summary of the invention

[0006] In view of the defect in the prior art that traditional energy storage management ignores the impact of multi-dimensional factors such as weather forecasts and holidays on energy demand, thus limiting the accuracy of load forecasting, the present invention provides an electrochemical energy storage management method, system, terminal and storage medium for a microgrid to solve the above technical problems.

[0007] In a first aspect, the present invention provides a method for managing electrochemical energy storage in a microgrid, comprising: The real-time multi-dimensional data of the microgrid is obtained through several sensors deployed in the microgrid, and the obtained multi-dimensional data is transmitted to the data processing center through the communication module; the multi-dimensional data includes load conditions, weather forecast information and holiday information; The data processing center performs data preprocessing on the received data, including data cleaning, denoising, data normalization and data integration, and builds the preprocessed multi-dimensional data into a data set; A load forecasting model is built based on the established data set combined with a machine learning algorithm, which inputs multi-dimensional data collected in real time and pre-processed to predict energy demand within a preset time period in the future; Based on the predicted energy demand, a charging and discharging strategy is formulated in combination with the current operating information of the electrochemical energy storage. The current operating information of the electrochemical energy storage includes the current battery charge status, the current battery health status and the real-time electricity price of the power grid.

[0008] A further improvement of the present invention also includes: timestamping the multi-dimensional data of the microgrid acquired by the sensor and sorting them in chronological order to complete data integration.

[0009] A further improvement of the present invention further includes: comparing the date recorded on the timestamp with a preset holiday date table to determine whether the date recorded on the timestamp is a holiday.

[0010] A further improvement of the present invention further comprises: Use the pre-existing datetime.fromisoformat function to convert the timestamp string on the obtained multi-dimensional data into a datetime object; Use the pre-stored timetuple method to get the time tuple in the datetime object, and use the tm_yday attribute to get the day of the year on the multidimensional data timestamp; Use the pre-stored weekday method to obtain the day of the week corresponding to the date on the multi-dimensional data timestamp. The day of the week is represented by an integer. Maps integers representing the day of the week to the corresponding weekday names according to a predefined list of weekday names.

[0011] A further improvement of the present invention is that the calculation formula for predicting the load according to the preprocessed multi-dimensional data in the load prediction model is: ; in, To forecast load, i.e. energy demand over a preset period of time in the future; The real-time load is obtained; is the load factor, ; The date on the multidimensional data timestamp is the day of the year; The calculation coefficient for the day of the year; The day of the week corresponding to the date on the multi-dimensional data timestamp; The calculation coefficient for the day of the week; is the temperature value in the weather condition; is the temperature coefficient; Whether it is a holiday is represented by binary, 1 means it is a holiday, and 0 means it is not a holiday; is the holiday coefficient; is the error term, which represents the load variation that cannot be explained by the load forecasting model.

[0012] A further improvement of the present invention is that a charging and discharging strategy is formulated based on the predicted energy demand and combined with the current operation information of the electrochemical energy storage, and the method steps include: Obtain the current real-time power price of the power grid, battery SOC, and the current operating voltage, operating current, and operating temperature of the battery; The current state of charge of the battery is determined according to the acquired SOC, and the current health state of the battery is determined according to the current operating voltage, operating current and operating temperature of the battery; the battery state of charge includes a low level and a high level, the battery state of charge is at a low level when the SOC is lower than a first preset threshold, and the battery state of charge is at a high level when the SOC is higher than a second preset threshold, and the first preset threshold is lower than the second preset threshold; Calculate the cost corresponding to the current real-time electricity price of the power grid; When the predicted energy demand is lower than the cost corresponding to the current real-time electricity price of the power grid, and the battery power state is at a low level, the pre-stored charging strategy is activated to charge the battery; When the predicted energy demand is higher than the cost corresponding to the current real-time electricity price of the power grid, and the battery power state is at a high level, the pre-stored discharge strategy is activated to discharge the battery.

[0013] A further improvement of the present invention further comprises: When the SOC is lower than 20%, the charging strategy is activated, and when the SOC is between 20% and 80%, the battery is quickly charged with a preset high current; When the SOC reaches 80%, the charging current is automatically reduced, and when the SOC reaches 90%, the discharge strategy is started.

[0014] In a second aspect, the present invention provides an electrochemical energy storage management system for a microgrid, comprising: The multi-dimensional data acquisition module is used to acquire real-time multi-dimensional data of the microgrid through a number of sensors deployed in the microgrid, and transmit the acquired multi-dimensional data to the data processing center through the communication module; the multi-dimensional data includes load conditions, weather forecast information, and holiday information; the data processing center includes a data pre-processing module, an energy demand prediction module, and a charging and discharging strategy formulation module; The data preprocessing module is used to perform data preprocessing on the received data, including data cleaning, denoising, data normalization and data integration, and to establish the preprocessed multi-dimensional data into a data set; The energy demand forecasting module is used to build a load forecasting model based on the established data set combined with the machine learning algorithm, input the multi-dimensional data collected in real time and pre-processed, and predict the energy demand in the future preset time period; The charging and discharging strategy formulation module is used to formulate a charging and discharging strategy based on the predicted energy demand and the current operating information of the electrochemical energy storage. The current operating information of the electrochemical energy storage includes the current battery power status, the current battery health status and the real-time electricity price of the power grid.

[0015] In a third aspect, the present invention provides a terminal, comprising: processor, memory, wherein: The memory is used to store computer programs. The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.

[0016] In a fourth aspect, the present invention provides a computer storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the methods described in the above aspects.

[0017] The beneficial effects of the present invention are: Improve the accuracy and real-time performance of energy storage and dispatch: Sensors deployed in microgrids can obtain multi-dimensional data in real time, including load conditions, weather forecast information, and holiday information, which provide a comprehensive and accurate information basis for load forecasting. The load forecasting model built using machine learning algorithms can accurately predict energy demand within a preset time period in the future based on real-time data, thereby guiding the charging and discharging strategy of the electrochemical energy storage system and significantly improving the accuracy and real-time performance of energy storage and dispatch.

[0018] Optimize the charging and discharging strategy of the energy storage system: The present invention considers the current state of charge and health of the battery, as well as the real-time electricity price of the power grid, and formulates a dynamic charging and discharging strategy. This strategy can avoid premature aging of the battery, while reducing the operating cost of the power grid and improving the overall economic benefits. In particular, in terms of SOC management, by setting the charging current at different stages (such as starting fast charging when the SOC is lower than 20%, and reducing the charging current when the SOC reaches 80%), and starting the discharge strategy when the SOC reaches 90%, the battery power is finely managed and the battery life is extended.

[0019] Enhanced responsiveness to special situations: By integrating weather forecasts and holiday information, the present invention can more accurately predict changes in energy demand, especially in special situations such as load fluctuations, weather changes, and holidays, and can respond promptly and effectively to ensure power supply stability and economy. Improved data utilization and load forecast accuracy: Timestamps are added to the multi-dimensional data acquired by sensors and sorted in chronological order, making full use of the time attributes of the data and improving data utilization. By converting the timestamp into a datetime object and extracting key information such as the date's position in the year and the day of the week, the accuracy of load forecasting is further improved.

[0020] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0023] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.

[0024] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in this specific embodiment. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of them. Based on the embodiments in this patent, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this patent.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0027] The electrochemical energy storage management method for a microgrid provided in an embodiment of the present invention is executed by a computer device, and accordingly, the electrochemical energy storage management system for the microgrid runs in the computer device.

[0028] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be an electrochemical energy storage management system for a microgrid. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0029] like Figure 1 As shown, the method includes: Step 110, obtaining real-time multi-dimensional data of the microgrid through a number of sensors deployed in the microgrid, and transmitting the obtained multi-dimensional data to a data processing center through a communication module; the multi-dimensional data includes load conditions, weather forecast information, and holiday information; Step 120, the data processing center performs data preprocessing on the received data, including data cleaning, denoising, data normalization and data integration, and establishes the preprocessed multi-dimensional data into a data set; Step 130, constructing a load forecasting model based on the established data set combined with a machine learning algorithm, inputting multi-dimensional data collected in real time and pre-processed, and forecasting energy demand within a preset time period in the future; Step 140, formulate a charging and discharging strategy based on the predicted energy demand and combined with the current operation information of the electrochemical energy storage, the current operation information of the electrochemical energy storage including the current battery power state, the current battery health state and the real-time power price of the power grid.

[0030] To facilitate understanding of the present invention, the electrochemical energy storage management method for a microgrid provided by the present invention is further described below based on the principle of the electrochemical energy storage management method for a microgrid of the present invention and the process of managing the electrochemical energy storage of a microgrid in an embodiment.

[0031] In order to improve the accuracy of the prediction, the method also includes time stamping the multi-dimensional data of the microgrid acquired by the sensor and sorting them in chronological order to complete the data integration. Whenever the sensor collects real-time data of the microgrid, such as load conditions, weather forecast information, and holiday information, the system will immediately time stamp the data. The generation of timestamps is based on the internal clock of the microgrid management system, ensuring that each data point has a unique and accurate time tag. Subsequently, the system will sort the collected multi-dimensional data according to the timestamp. This step is crucial because it ensures the temporal order of the data in subsequent processing and analysis, allowing the load forecasting model to predict future energy demand based on the evolution trend of historical data. After the sorting is completed, the system will perform data integration. This step involves associating different dimensional data (such as load, weather, and holiday information) at the same time point to form a complete data set. In addition, the system will check the integrity and consistency of the data to ensure that there are no missing or erroneous data points.

[0032] In addition, the method also includes comparing the date recorded on the timestamp with a preset holiday date table to determine whether the date recorded on the timestamp is a holiday. Specifically, the multi-dimensional data with timestamps uploaded by the sensor are first collected. These data contain key elements such as load conditions, weather forecast information, and holiday information. Among them, the timestamp, as a time mark of the data, not only records the exact time of data collection, but also implies date information. Next, the date part of the timestamp is extracted and compared with the preset holiday date table. The holiday date table is a pre-defined data set that contains all statutory holidays, compensatory holidays, and possible special holidays (such as school holidays, religious holidays, etc.) throughout the year. This date table will be regularly updated according to the actual holiday arrangements of the country or region to ensure its accuracy and timeliness. During the comparison process, check one by one whether the date on the timestamp matches any date in the holiday date table. If a match is found, the date is determined to be a holiday; if no match is found, it is determined to be a non-holiday. The determination result will then be used as an important input variable of the load forecasting model. Energy demand is usually lower and more volatile during holidays, so the load forecasting model needs to adjust its forecasting algorithm based on this information (adjust the holiday coefficient ) to improve the accuracy of the prediction. In addition, the judgment results will also affect the formulation of charging and discharging strategies. For example, during holidays, due to the lower energy demand, it may be more inclined to discharge to utilize excess energy storage; while during non-holidays, it may be more inclined to charge to reserve energy.

[0033] Furthermore, the method further comprises: S121. Use the pre-stored datetime.fromisoformat function to convert the timestamp string on the acquired multi-dimensional data into a datetime object; S122. Use the pre-stored timetuple method to obtain the time tuple in the datetime object, and obtain the day of the year of the date on the multi-dimensional data timestamp through the tm_yday attribute; S123. Use the pre-stored weekday method to obtain the day of the week corresponding to the date on the multi-dimensional data timestamp, where the day of the week is represented by an integer; S124. Mapping the integer representing the day of the week to the corresponding day of the week name according to a predefined day of the week name list.

[0034] Specifically, timestamps in multidimensional data usually exist in the form of strings in ISO 8601 format, such as "2023-10-05T14:30:00". For the convenience of subsequent processing, the system uses the fromisoformat function in the datetime module to convert these timestamp strings into datetime objects. This step ensures the standardization and easy handling of timestamp data. After conversion to a datetime object, the system needs to extract the day of the year for that date. This is achieved by calling the timetuple method of the datetime object to obtain a time tuple, and then accessing the tm_yday attribute of the tuple. The tm_yday attribute represents the day of the year (ranging from 1 to 365 or 366, depending on whether it is a leap year). In addition, when determining the day of the week, the weekday method returns an integer, where 0 represents Monday, 1 represents Tuesday, and so on, until 6 represents Sunday. In order to convert the integer representation of the day of the week into a more intuitive week name, the system maintains a predefined list of week names. This list maps integers 0 to 6 to "Monday" to "Sunday" respectively.

[0035] Specifically, the calculation formula for predicting load based on preprocessed multi-dimensional data in the load forecasting model is: ; in, To forecast load, i.e. energy demand over a preset period of time in the future; The real-time load is obtained; is the load factor, ; The date on the multidimensional data timestamp is the day of the year; The calculation coefficient for the day of the year; The day of the week corresponding to the date on the multi-dimensional data timestamp; The calculation coefficient for the day of the week; is the temperature value in the weather condition; is the temperature coefficient; Whether it is a holiday is represented by binary, 1 means it is a holiday, and 0 means it is not a holiday; is the holiday coefficient; is an error term, which indicates the load changes that the load forecasting model cannot explain. By introducing multi-dimensional data, the load forecasting model of the present invention can more comprehensively reflect the complexity and diversity of load changes, thereby improving the accuracy of the forecast; and the various calculation coefficients in the load forecasting model can be adjusted and optimized according to historical data, so that the load forecasting model can adapt to the load change characteristics of different regions and seasons. Accurate load forecasting can provide strong support for the charging and discharging strategies of energy storage equipment, realize the optimal utilization of energy and the stable operation of microgrids.

[0036] In addition, according to the predicted energy demand, a charging and discharging strategy is formulated in combination with the current operation information of the electrochemical energy storage, and the method steps include: S141, obtaining the current real-time power price of the power grid, the battery SOC, and the current operating voltage, operating current, and operating temperature of the battery; S142, judging the current state of charge of the battery according to the acquired SOC, and judging the current health state of the battery according to the current operating voltage, operating current and operating temperature of the battery; the battery state of charge includes a low level and a high level, the battery state of charge is at a low level when the SOC is lower than a first preset threshold, and the battery state of charge is at a high level when the SOC is higher than a second preset threshold, and the first preset threshold is less than the second preset threshold; S143, calculating the cost corresponding to the current real-time electricity price of the power grid; S144. When the predicted energy demand is lower than the cost corresponding to the current real-time electricity price of the power grid, and the battery power state is at a low level, the pre-stored charging strategy is activated to charge the battery; when the predicted energy demand is higher than the cost corresponding to the current real-time electricity price of the power grid, and the battery power state is at a high level, the pre-stored discharging strategy is activated to discharge the battery.

[0037] The present invention provides an accurate data basis for the subsequent charging and discharging strategy formulation by acquiring key information such as the current real-time power price of the power grid, the battery SOC (State of Charge, i.e., the percentage of remaining battery power), and the operating voltage, operating current, and operating temperature of the battery. The acquisition of real-time data ensures that the system can quickly respond to changes in the power grid and battery status, adjust the charging and discharging strategy in time, and improve the flexibility and response speed of the system. Judging the power state according to the SOC of the battery, and evaluating the battery health state in combination with the operating voltage, current, and temperature, it helps to avoid overcharging, over-discharging, or working in an unhealthy state of the battery, and prolong the battery life. By calculating the cost corresponding to the current real-time power price of the power grid, the system can evaluate the economic feasibility of purchasing electricity from the power grid or selling electricity to the power grid, and provide an economic basis for formulating charging and discharging strategies. According to the predicted energy demand and the real-time power price cost of the power grid, combined with the battery power state, the system can flexibly formulate charging and discharging strategies to ensure that the economic benefits are maximized while meeting the energy demand. Discharging when the energy demand is low and the power price is high, or charging when the energy demand is high and the power price is low, helps to balance the load of the power grid and improve the stability and reliability of the power grid operation.

[0038] To improve energy efficiency and extend battery life, the method further includes: When the SOC is lower than 20%, the charging strategy is activated, and when the SOC is between 20% and 80%, the battery is quickly charged with a preset high current; When the SOC reaches 80%, the charging current is automatically reduced, and when the SOC reaches 90%, the discharge strategy is started.

[0039] In some embodiments, the electrochemical energy storage management system of the microgrid may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments in the electrochemical energy storage management system of the microgrid may be stored in the memory of a computer device and executed by at least one processor to execute (see Figure 1 Description) Electrochemical energy storage management function of microgrid.

[0040] In this embodiment, the electrochemical energy storage management system of the microgrid can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules may include: a multi-dimensional data acquisition module and a data processing center, and the data processing center includes a data preprocessing module, an energy demand prediction module and a charge and discharge strategy formulation module. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0041] Specifically, the multi-dimensional data acquisition module is used to obtain real-time multi-dimensional data of the microgrid through a number of sensors deployed in the microgrid, and transmit the obtained multi-dimensional data to the data processing center through the communication module; the multi-dimensional data includes load conditions, weather forecast information and holiday information; the data preprocessing module is used to perform data preprocessing on the received data, including data cleaning, denoising, data normalization and data integration, and establish the preprocessed multi-dimensional data into a data set; the energy demand prediction module is used to build a load prediction model based on the established data set combined with the machine learning algorithm, input the multi-dimensional data collected in real time and preprocessed, and predict the energy demand within a preset time period in the future; the charging and discharging strategy formulation module is used to formulate a charging and discharging strategy based on the predicted energy demand and combined with the current operating information of the electrochemical energy storage. The current operating information of the electrochemical energy storage includes the current battery power status, the current battery health status and the real-time electricity price of the power grid.

[0042] Figure 3 This is a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the electrochemical energy storage management method of the microgrid provided in an embodiment of the present invention.

[0043] The terminal 300 may include: a processor 310, a memory 320 and a communication module 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0044] The memory 320 can be used to store the execution instructions of the processor 310, and the memory 320 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 can perform some or all of the steps in the following method embodiments.

[0045] The processor 310 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0046] The communication module 330 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0047] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0048] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0049] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0050] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0051] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0052] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0053] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A method for managing electrochemical energy storage in a microgrid, characterized in that: include: The real-time multi-dimensional data of the microgrid is obtained through several sensors deployed in the microgrid, and the obtained multi-dimensional data is transmitted to the data processing center through the communication module; the multi-dimensional data includes load conditions, weather forecast information and holiday information; The data processing center performs data preprocessing on the received data, including data cleaning, denoising, data normalization and data integration, and builds the preprocessed multi-dimensional data into a data set; A load forecasting model is built based on the established data set combined with a machine learning algorithm, which inputs multi-dimensional data collected in real time and pre-processed to predict energy demand within a preset time period in the future; Based on the predicted energy demand, a charging and discharging strategy is formulated in combination with the current operating information of the electrochemical energy storage. The current operating information of the electrochemical energy storage includes the current battery charge status, the current battery health status and the real-time electricity price of the power grid.

2. The electrochemical energy storage management method of the microgrid according to claim 1, characterized in that: Also includes: The multi-dimensional data of the microgrid acquired by the sensor is timestamped and sorted in chronological order to complete the data integration.

3. The electrochemical energy storage management method of the microgrid according to claim 2 is characterized in that: Also includes: The date recorded on the timestamp is compared with the preset holiday date table to determine whether the date recorded on the timestamp is a holiday.

4. The electrochemical energy storage management method of the microgrid according to claim 3 is characterized in that: Also includes: Use the pre-existing datetime.fromisoformat function to convert the timestamp string on the obtained multi-dimensional data into a datetime object; Use the pre-stored timetuple method to get the time tuple in the datetime object, and use the tm_yday attribute to get the day of the year on the multidimensional data timestamp; Use the pre-stored weekday method to obtain the day of the week corresponding to the date on the multi-dimensional data timestamp. The day of the week is represented by an integer. Maps integers representing the day of the week to the corresponding weekday names according to a predefined list of weekday names.

5. The electrochemical energy storage management method of the microgrid according to claim 4, characterized in that: The calculation formula for predicting load based on preprocessed multi-dimensional data in the load forecasting model is: ； in, To forecast load, i.e. energy demand over a preset period of time in the future; The real-time load is obtained; is the load factor, ; The date on the multidimensional data timestamp is the day of the year; The calculation coefficient for the day of the year; The day of the week corresponding to the date on the multi-dimensional data timestamp; The calculation coefficient for the day of the week; is the temperature value in the weather condition; is the temperature coefficient; Whether it is a holiday is represented by binary, 1 means it is a holiday, and 0 means it is not a holiday; is the holiday coefficient; is the error term, which represents the load variation that cannot be explained by the load forecasting model.

6. The electrochemical energy storage management method of a microgrid according to claim 1, characterized in that: According to the predicted energy demand, combined with the current operation information of electrochemical energy storage, a charging and discharging strategy is formulated, and the method steps include: Obtain the current real-time power price of the power grid, battery SOC, and the current operating voltage, operating current, and operating temperature of the battery; The current state of charge of the battery is determined according to the acquired SOC, and the current health state of the battery is determined according to the current operating voltage, operating current and operating temperature of the battery; the battery state of charge includes a low level and a high level, the battery state of charge is at a low level when the SOC is lower than a first preset threshold, and the battery state of charge is at a high level when the SOC is higher than a second preset threshold, and the first preset threshold is lower than the second preset threshold; Calculate the cost corresponding to the current real-time electricity price of the power grid; When the predicted energy demand is lower than the cost corresponding to the current real-time electricity price of the power grid, and the battery power state is at a low level, the pre-stored charging strategy is activated to charge the battery; When the predicted energy demand is higher than the cost corresponding to the current real-time electricity price of the power grid, and the battery power state is at a high level, the pre-stored discharge strategy is activated to discharge the battery.

7. The electrochemical energy storage management method of the microgrid according to claim 6, characterized in that: Also includes: When the SOC is lower than 20%, the charging strategy is activated, and when the SOC is between 20% and 80%, the battery is quickly charged with a preset high current; When the SOC reaches 80%, the charging current is automatically reduced, and when the SOC reaches 90%, the discharge strategy is started.

8. An electrochemical energy storage management system for a microgrid, characterized in that: include: The multi-dimensional data acquisition module is used to acquire real-time multi-dimensional data of the microgrid through a number of sensors deployed in the microgrid, and transmit the acquired multi-dimensional data to the data processing center through the communication module; the multi-dimensional data includes load conditions, weather forecast information, and holiday information; the data processing center includes a data pre-processing module, an energy demand prediction module, and a charging and discharging strategy formulation module; The data preprocessing module is used to perform data preprocessing on the received data, including data cleaning, denoising, data normalization and data integration, and to establish the preprocessed multi-dimensional data into a data set; The energy demand forecasting module is used to build a load forecasting model based on the established data set combined with the machine learning algorithm, input the multi-dimensional data collected in real time and pre-processed, and predict the energy demand in the future preset time period; The charging and discharging strategy formulation module is used to formulate a charging and discharging strategy based on the predicted energy demand and the current operating information of the electrochemical energy storage. The current operating information of the electrochemical energy storage includes the current battery power status, the current battery health status and the real-time electricity price of the power grid.

9. A terminal, characterized in that: include: processor; A memory for storing execution instructions of the processor; The processor is configured to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images