Distributed energy storage operation scheduling system, method, equipment, medium and product

Abstract

The invention discloses a distributed energy storage operation scheduling system, method, equipment, medium and product, and relates to the field of distributed energy storage device operation scheduling, and the system comprises a power grid side, an energy storage module, a load and a calculation unit. The calculation unit is used for acquiring historical carbon emission factors of a power grid side in a historical set time period, historical power utilization demands of all loads, current energy storage amounts, current operation states and energy storage characteristics of all energy storage modules and prediction data obtained by last operation scheduling; preprocessing the historical data, and predicting prediction data per hour in the future by using a future data prediction model according to the processed historical carbon emission factors and the processed historical electricity demands; and determining an operation scheduling scheme of each energy storage module in the future by using an ant colony algorithm according to the prediction data per hour in the future, the prediction data obtained by the previous operation scheduling and the energy storage module data. According to the invention, the efficiency and accuracy of distributed energy storage operation scheduling are improved.

Description

Technical Field

[0001] The present application relates to the field of distributed energy storage device operation scheduling, and in particular to a distributed energy storage operation scheduling system, method, equipment, medium and product. Background Art

[0002] At present, carbon emission is measured by real-time updating of carbon emission factors on the user side to determine the carbon emission responsibility and then share the carbon emission costs. Therefore, the grid management level limits the carbon emission level on the user side through carbon emission factors, carbon emission trading markets, excess payment or carbon purchase methods. However, the existing distributed energy storage-related power consumption areas or users, power operation and scheduling methods are mainly proposed for harmonic interference, reactive power, instability of new energy generation, power conservation and other issues. There is a lack of methods on how power consumption areas or power users can actively use carbon emission factor prediction data to reasonably arrange distributed energy storage low-carbon operation plans.

[0003] In addition, since many power devices in production have the characteristics of not being able to respond quickly, or there is a need that does not allow for rapid switching, it is a more feasible solution to control carbon emissions through distributed energy storage. And with the popularization of new energy vehicle charging stations and the existing application of traditional methods such as water storage, distributed energy storage is more common in life and industrial production, and has research value. Summary of the invention

[0004] The purpose of this application is to provide a distributed energy storage operation scheduling system, method, device, medium and product to improve the efficiency and accuracy of distributed energy storage operation scheduling.

[0005] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a distributed energy storage operation and scheduling system, including: a power grid side, a computing unit, a energy storage module and b loads; The grid side is respectively connected to a of the energy storage modules, b of the loads and the computing unit; a of the energy storage modules and b of the loads are both connected to the computing unit; The computing unit is used for: Obtain the historical carbon emission factor of the grid side within the historical setting period, the historical electricity demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the last calculation and scheduling obtained n f -1 hour of forecast data; the operating state is shutdown, charging or discharging; the energy storage characteristics include the maximum energy storage value; the forecast data includes the carbon emission factor forecast value and the electricity demand forecast value; n f For forecast hours; Preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand; the preprocessing includes linear interpolation and abnormal data correction; Based on the processed historical carbon emission factors and processed historical electricity demand, the future data prediction model is used to predict the future n f The forecast data for each hour of the hour; wherein the future data prediction model is obtained by training the long short-term memory neural network using the training data set; the training data set includes the historical carbon emission factors of the training grid side in the historical set period, the historical electricity demand of each training load, and the corresponding carbon emission factor forecast value and electricity demand forecast value in the future set period; According to the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling scheme of each energy storage module of the present invention is as follows: the operation scheduling scheme is shutdown, charging and the corresponding charging rate or discharging and the corresponding discharging rate.

[0006] Optionally, the computing unit includes: The data acquisition module is used to obtain the historical carbon emission factor of the grid side within the historical set period, the historical power demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the data obtained from the last operation and scheduling. n f -1 hour of forecast data; A data processing module, used for preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand; The prediction module is used to predict the future based on the processed historical carbon emission factors and the processed historical electricity demand using the future data prediction model. n f Forecast data for each hour of the hour; Scheduling scheme determination module is used to determine the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f-1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling plan of each energy storage module is as follows:

[0007] In a second aspect, the present application provides a distributed energy storage operation scheduling method, which is applied to the above-mentioned distributed energy storage operation scheduling system, and the distributed energy storage operation scheduling method includes: Obtain the historical carbon emission factor of the grid side within the historical setting period, the historical electricity demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the last calculation and scheduling obtained n f -1 hour of forecast data; the energy storage characteristics include the maximum energy storage value; the forecast data include the carbon emission factor forecast value and the electricity demand forecast value; n f For forecast hours; Preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand; the preprocessing includes linear interpolation and abnormal data correction; Based on the processed historical carbon emission factors and processed historical electricity demand, the future data prediction model is used to predict the future n f The forecast data for each hour of the hour; wherein the future data prediction model is obtained by training the long short-term memory neural network using the training data set; the training data set includes the historical carbon emission factors of the training grid side in the historical set period, the historical electricity demand of each training load, and the corresponding carbon emission factor forecast value and electricity demand forecast value in the future set period; According to the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling scheme of each energy storage module of the present invention is as follows: the operation scheduling scheme is shutdown, charging and the corresponding charging rate or discharging and the corresponding discharging rate.

[0008] Optionally, the long short-term memory neural network is trained using the training data set, specifically including: Build a training dataset; Preprocessing the historical carbon emission factor of the training grid side and the historical electricity demand of each training load to obtain the processed historical carbon emission factor of the training grid side and the processed historical electricity demand of each training load; The long short-term memory neural network is trained with the processed historical carbon emission factor of the training grid side and the processed historical electricity demand of each training load as input, and the corresponding predicted carbon emission factor value and predicted electricity demand value in the future set time period as output to obtain a future data prediction model.

[0009] Optionally, the operating state is shutdown, charging or discharging.

[0010] Optionally, preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand specifically includes: The historical carbon emission factor of the grid side and the historical electricity demand of each load in the historical set period are processed by linear interpolation method to obtain the filled historical carbon emission factor and the filled historical electricity demand; Abnormal data in the filled historical carbon emission factor and the filled historical electricity demand are eliminated or corrected to obtain a processed historical carbon emission factor and a processed historical electricity demand.

[0011] Optionally, preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand, and then further comprising: Determine whether the processed data volume of the historical carbon emission factor is less than the data volume setting value and whether the processed data volume of the historical electricity demand is less than the data volume setting value; the data volume setting value is the total number of hours in the historical setting period; If so, the processed historical carbon emission factor or the processed historical electricity demand is expanded to obtain an expanded historical carbon emission factor or an expanded historical electricity demand; Convert the format of the expanded historical carbon emission factor or the expanded historical electricity demand to obtain a converted historical carbon emission factor or a converted historical electricity demand; If not, no expansion and format conversion processing is performed.

[0012] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described distributed energy storage operation scheduling methods.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described distributed energy storage operation scheduling methods.

[0014] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned distributed energy storage operation scheduling methods.

[0015] According to the specific embodiments provided in this application, this application has the following technical effects: The present application provides a distributed energy storage operation scheduling system, method, device, medium and product, the system comprising: a power grid side, a computing unit, a energy storage module and b loads; the power grid side is connected to the energy storage module, the load and the computing unit respectively, and the energy storage module and the load are connected to the computing unit; the computing unit is used to: obtain the historical carbon emission factor of the power grid side within a historical set period, the historical electricity demand of each load, the current storage capacity of each energy storage module, the current operating state and energy storage characteristics, and the last operation scheduling obtained n f -1 hour of forecast data; pre-process the historical carbon emission factors on the grid side and the historical electricity demand of each load to obtain the processed historical carbon emission factors and the processed historical electricity demand; use the future data forecast model to predict the future based on the processed historical carbon emission factors and the processed historical electricity demand n f The forecast data for each hour in the hour; the future data prediction model is obtained by training the long short-term memory neural network using the training data set; according to the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f - One hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module are used to determine the future n f The operation scheduling scheme of each energy storage module is as follows: shutdown, charging and corresponding charging rate or discharging and corresponding discharging rate. The present application improves the efficiency and accuracy of distributed energy storage operation scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A structural diagram of a distributed energy storage operation and scheduling system provided in one embodiment of the present application; Figure 2 A schematic diagram of a flow chart of a distributed energy storage operation scheduling method provided in one embodiment of the present application; Figure 3 An operation flow chart of a distributed energy storage operation scheduling method provided in one embodiment of the present application; Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0020] In an exemplary embodiment, a distributed energy storage operation and scheduling system is provided, including: a grid side, a computing unit, a energy storage modules and b loads.

[0021] The grid side is respectively connected to a of the energy storage modules, b of the loads and the calculation unit; a of the energy storage modules and b of the loads are both connected to the calculation unit.

[0022] The computing unit is used for: Obtain the historical carbon emission factor of the grid side within the historical setting period, the historical electricity demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the last calculation and scheduling obtained n f -1 hour of forecast data; the energy storage characteristics include the maximum energy storage value; the forecast data include the carbon emission factor forecast value and the electricity demand forecast value; n f is the number of forecast hours.

[0023] The historical carbon emission factor of the grid side and the historical electricity demand of each load are preprocessed to obtain a processed historical carbon emission factor and a processed historical electricity demand; the preprocessing includes linear interpolation and abnormal data correction.

[0024] Based on the processed historical carbon emission factors and processed historical electricity demand, the future data prediction model is used to predict the future n f Forecast data for each hour within an hour; wherein, the future data prediction model is obtained by training a long short-term memory neural network using a training data set; the training data set includes the historical carbon emission factors of the training power grid side within a historical set period, the historical electricity demand of each training load, and the corresponding carbon emission factor prediction value and electricity demand prediction value within a future set period.

[0025] According to the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling scheme of each energy storage module of the present invention is as follows: the operation scheduling scheme is shutdown, charging and the corresponding charging rate or discharging and the corresponding discharging rate.

[0026] As an optional implementation manner, the calculation unit includes: The data acquisition module is used to obtain the historical carbon emission factor of the grid side within the historical set period, the historical power demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the data obtained from the last operation and scheduling. n f -1 hour of forecast data.

[0027] The data processing module is used to pre-process the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain the processed historical carbon emission factor and the processed historical electricity demand.

[0028] The prediction module is used to predict the future based on the processed historical carbon emission factors and the processed historical electricity demand using the future data prediction model. n f Forecast data for each hour of the hour.

[0029] Scheduling scheme determination module is used to determine the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n fThe operation scheduling plan of each energy storage module is as follows:

[0030] Figure 1 The topological structure of an embodiment of the present application is shown. The embodiment is a certain power consumption area intercepted in the power grid. The power grid is mounted with load 1 and load 2. In addition, it also includes distributed energy storage, which are respectively set as energy storage module 1 and energy storage module 2. The computing unit is a hardware computing module that will be carried during the specific implementation of the distributed energy storage operation scheduling method.

[0031] In this embodiment, the calculation unit is set to calculate the operation scheduling plan once every hour. In order to calculate the optimal operation scheduling plan for distributed energy storage, the calculation unit first collects the past Hours ( is the total number of hours in the historical set time period), the historical carbon emission factor provided by the grid side, the historical electricity demand provided by load 1 and load 2, the current storage capacity of energy storage module 1 and energy storage module 2, the current operating status (shutdown, charging or discharging) and energy storage characteristics (parameters such as maximum energy storage value), and predicted data (provided by humans or calculated by the calculation unit in the previous hour), and then pre-processing such as linear interpolation to supplement the missing data and correction of abnormal data is performed.

[0032] At this time, the computing unit reuses the processed historical data (processed historical carbon emission factors and processed historical electricity demand) and expected data, and uses the LSTM (Long Short-Term Memory) prediction method to predict the future The carbon emission factor for each hour within the hour and the electricity demand of load 1 and load 2 are then provided to the ant colony algorithm for optimizing the operation scheduling plan.

[0033] Finally, the calculation unit uses the LSTM prediction method to obtain the expected reference data on carbon emission factors and electricity demand (future The carbon emission factor per hour and the electricity demand of load 1 and load 2 in the previous hour), the future Hours of forecast data, as well as the data of energy storage module 1 and energy storage module 2, use the ant colony algorithm to predict the future The operation scheduling plan of the hour is optimized and the energy storage module 1 and energy storage module 2 are given in the future. The charge and discharge status and rate of each hour. Among the optimal results calculated, only the operation scheduling plan corresponding to the last hour in the future is allocated to energy storage module 1 and energy storage module 2. The forecast data for the next hour and the corresponding operation scheduling plan can be provided to the computing unit as expected values ​​and used as reference values ​​for the operation scheduling plan for the next hour.

[0034] In an exemplary embodiment, Figure 2 and Figure 3 As shown, the present application provides a distributed energy storage operation scheduling method, which is applied to the above-mentioned distributed energy storage operation scheduling system, and the distributed energy storage operation scheduling method includes: S1: Obtain the historical carbon emission factor of the grid side within the historical setting period, the historical power demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the last calculation and scheduling n f -1 hour of forecast data; the energy storage characteristics include the maximum energy storage value; the forecast data include the carbon emission factor forecast value and the electricity demand forecast value; n f The operating states are shutdown, charging rate and discharging rate.

[0035] In practical applications, when a calculation is started, historical data such as carbon emission factors on the grid side and load power demand are collected first, that is, historical data on the grid side carbon emission factors and load power demand are collected. In each hour, the historical carbon emission factor provided by the grid, the historical electricity demand provided by the load, the current energy storage module related information, and the possible expected data (obtained from the last operation and scheduling) n f -1 hour of forecast data), including the following sub-steps: Step 1.1: Obtain historical carbon emission factor data with a certain period of time (historical set period) with a regular change pattern.

[0036] Step 1.2: Obtain the historical power demand of a certain period of time or the expected power demand within a certain period of time in the future (a future set period) at the power user side of the microgrid. Preferably, the data time range is based on the operation or change cycle, and includes at least one cycle.

[0037] Step 1.3: Obtain the current storage capacity, operating status and storage characteristics of the energy storage device (energy storage module).

[0038] S2: Preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand; the preprocessing includes linear interpolation and abnormal data correction.

[0039] As an optional implementation, S2 specifically includes: The historical carbon emission factor of the grid side and the historical electricity demand of each load within the historical set time period are processed by linear interpolation method to obtain the filled historical carbon emission factor and the filled historical electricity demand.

[0040] In practical applications, after data collection is completed, missing and abnormal data preprocessing is performed, that is, the historical data that is missing for some reason is reasonably filled. For example, the missing data can be filled based on methods such as linear interpolation.

[0041] Abnormal data in the filled historical carbon emission factor and the filled historical electricity demand are eliminated or corrected to obtain a processed historical carbon emission factor and a processed historical electricity demand.

[0042] In practical applications, abnormal data with no reference value are judged through a pre-provided experience library, or abnormal data information provided by humans is marked, and these abnormal data are eliminated or modified into reasonable data.

[0043] Determine whether the amount of data of the processed historical carbon emission factor is less than the set value of the data amount and whether the amount of data of the processed historical electricity demand is less than the set value of the data amount. The set value of the data amount is the total number of hours in the historical set period. The prediction of carbon emission factor and electricity demand requires the collection of the past n p Hours of historical data (historical carbon emission factors and historical electricity demand). Since abnormal data may be eliminated during the preprocessing process, the amount of historical data is reduced. Only when the data volume reaches n p To make predictions normally.

[0044] If so, the processed historical carbon emission factor or the processed historical electricity demand is expanded to obtain an expanded historical carbon emission factor or an expanded historical electricity demand.

[0045] In practical applications, if the amount of historical data obtained is too small, the historical data can be expanded in a certain way through methods such as combination.

[0046] The expanded historical carbon emission factor or the expanded historical electricity demand is formatted to obtain a converted historical carbon emission factor or a converted historical electricity demand.

[0047] In practical applications, the data format is converted to ensure that the data format of all historical data can be directly used by the algorithm.

[0048] If not, no expansion and format conversion processing is performed.

[0049] S3: Based on the processed historical carbon emission factors and processed historical electricity demand, use the future data prediction model to predict the future n fForecast data for each hour within an hour; wherein, the future data prediction model is obtained by training a long short-term memory neural network using a training data set; the training data set includes the historical carbon emission factors of the training power grid side within a historical set period, the historical electricity demand of each training load, and the corresponding carbon emission factor prediction value and electricity demand prediction value within a future set period.

[0050] As an optional implementation, the long short-term memory neural network is trained using a training data set, specifically including: Build a training dataset.

[0051] The historical carbon emission factor of the training grid side and the historical electricity demand of each training load are preprocessed to obtain the processed historical carbon emission factor of the training grid side and the processed historical electricity demand of each training load.

[0052] The long short-term memory neural network is trained with the processed historical carbon emission factor of the training grid side and the processed historical electricity demand of each training load as input, and the corresponding predicted carbon emission factor value and predicted electricity demand value in the future set time period as output to obtain a future data prediction model.

[0053] S4: According to the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling plan of each energy storage module is as follows:

[0054] In practical applications, after preprocessing, the LSTM method is used to predict future carbon emission factors and electricity demand forecasts, and then the ant colony algorithm is used to calculate the optimal scheduling plan for the future forecast period. That is, based on the processed historical carbon emission factors and the processed historical electricity demand, the long-short term memory (LSTM) neural network prediction method is used to predict the future The carbon emission factor and the electricity demand of the load are calculated every hour, and then the ant colony algorithm is used to determine the optimal operation and scheduling plan for the distributed energy storage link, which specifically includes the following steps: Step 4.1: If the acquired data only contains processed historical electricity demand, fit and determine the hourly electricity demand forecast value of power users within a certain period of time in the future.

[0055] Step 4.2: Based on the processed historical carbon emission factors, fit and determine the predicted value of the hourly carbon emission factor within a certain period of time in the future.

[0056] Step 4.3: Through the long short-term memory neural network LSTM, combined with the existing storage capacity and operating status of the energy storage device, the ant colony algorithm is used to determine the operation scheduling plan of the distributed energy storage device every hour within a certain period of time in the future.

[0057] In practical applications, the ant colony algorithm is used to predict the future energy storage system by using the expected reference data on carbon emission factors and electricity demand, the predicted data obtained from the last operation scheduling operation, and the current energy storage module data. The optimal result is used to optimize the operation scheduling plan for the next hour. Each distributed energy storage device executes the scheduling plan corresponding to the next hour in the optimal plan. The remaining data ( The forecast data for the next hour and the corresponding operation scheduling plan are provided to the computing unit as the forecast data for the next operation (next hour), thus terminating the operation.

[0058] This application makes full use of historical data information, uses the long short-term memory neural network LSTM method to give carbon emission factors and electricity demand change calculation forecasts, and on this basis uses the ant colony algorithm to determine the optimal distributed energy storage operation and scheduling plan, which is forward-looking and guiding to give a better plan for distributed energy storage operation and scheduling, while meeting the electricity demand of power users and reducing carbon emission costs. The computational complexity of the data preprocessing and prediction, and the operation and scheduling plan are all low, with high computational efficiency and less storage space required. It has the advantages of strong feasibility and the accuracy of the operation and scheduling plan can reach up to the hourly level.

[0059] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned distributed energy storage operation scheduling method when executing the computer program.

[0060] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above-mentioned distributed energy storage operation scheduling method when executed by a processor.

[0061] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned distributed energy storage operation scheduling method when executed by a processor.

[0062] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a distributed energy storage operation scheduling method is implemented.

[0063] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0064] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0065] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0066] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0067] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0068] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A distributed energy storage operation and dispatching system, characterized in that: include: Grid side, computing unit, a energy storage modules and b loads; the computing unit is used to: Obtain the historical carbon emission factor of the grid side within the historical setting period, the historical electricity demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the last calculation and scheduling obtained n f -1 hour of forecast data; the operating state is shutdown, charging or discharging; the energy storage characteristics include the maximum energy storage value; n f For forecast hours; According to the historical carbon emission factor of the grid side and the historical electricity demand of each load, the future data prediction model is used to predict the future n f Forecast data for each hour of the hour; According to the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling plan of each energy storage module is as follows:

2. The distributed energy storage operation and dispatching system according to claim 1, characterized in that: The computing unit comprises: The data acquisition module is used to obtain the historical carbon emission factor of the grid side within the historical set period, the historical power demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the data obtained from the last operation and scheduling. n f -1 hour of forecast data; A data processing module, used for preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand; The prediction module is used to predict the future based on the processed historical carbon emission factors and the processed historical electricity demand using the future data prediction model. n f Forecast data for each hour of the hour; The scheduling scheme determination module is used to determine the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling plan of each energy storage module is as follows:

3. A distributed energy storage operation scheduling method, characterized in that: The distributed energy storage operation scheduling method is applied to the distributed energy storage operation scheduling system according to any one of claims 1 to 2, and the distributed energy storage operation scheduling method includes: Obtain the historical carbon emission factor of the grid side within the historical setting period, the historical electricity demand of each load, the current storage capacity of each energy storage module, the current operating status and energy storage characteristics, and the last calculation and scheduling obtained n f -1 hour of forecast data; the energy storage characteristics include the maximum energy storage value; the forecast data include the carbon emission factor forecast value and the electricity demand forecast value; n f For forecast hours; Preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand; the preprocessing includes linear interpolation and abnormal data correction; Based on the processed historical carbon emission factors and processed historical electricity demand, the future data prediction model is used to predict the future n f The forecast data for each hour of the hour; wherein the future data prediction model is obtained by training the long short-term memory neural network using the training data set; the training data set includes the historical carbon emission factors of the training grid side in the historical set period, the historical electricity demand of each training load, and the corresponding carbon emission factor forecast value and electricity demand forecast value in the future set period; According to the future n f The forecast data for each hour of the hour and the data obtained from the last operation and scheduling n f -1 hour of forecast data and the current storage capacity, current operating status and storage characteristics of each energy storage module, using the ant colony algorithm to determine the future n f The operation scheduling scheme of each energy storage module of the present invention is as follows: the operation scheduling scheme is shutdown, charging and the corresponding charging rate or discharging and the corresponding discharging rate.

4. The distributed energy storage operation scheduling method according to claim 3 is characterized in that: The training dataset is used to train the LSTM neural network, including: Build a training dataset; Preprocessing the historical carbon emission factor of the training grid side and the historical electricity demand of each training load to obtain the processed historical carbon emission factor of the training grid side and the processed historical electricity demand of each training load; The long short-term memory neural network is trained with the processed historical carbon emission factor of the training grid side and the processed historical electricity demand of each training load as input, and the corresponding predicted carbon emission factor value and predicted electricity demand value in the future set time period as output to obtain a future data prediction model.

5. The distributed energy storage operation scheduling method according to claim 3 is characterized in that: The operating status is shutdown, charging or discharging.

6. The distributed energy storage operation scheduling method according to claim 3 is characterized in that: Preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain a processed historical carbon emission factor and a processed historical electricity demand, specifically including: The historical carbon emission factor of the grid side and the historical electricity demand of each load in the historical set period are processed by linear interpolation method to obtain the filled historical carbon emission factor and the filled historical electricity demand; Abnormal data in the filled historical carbon emission factor and the filled historical electricity demand are eliminated or corrected to obtain a processed historical carbon emission factor and a processed historical electricity demand.

7. The distributed energy storage operation scheduling method according to claim 6, characterized in that: Preprocessing the historical carbon emission factor of the grid side and the historical electricity demand of each load to obtain the processed historical carbon emission factor and the processed historical electricity demand, and then further comprising: Determine whether the processed data volume of the historical carbon emission factor is less than the data volume setting value and whether the processed data volume of the historical electricity demand is less than the data volume setting value; the data volume setting value is the total number of hours in the historical setting period; If so, the processed historical carbon emission factor or the processed historical electricity demand is expanded to obtain an expanded historical carbon emission factor or an expanded historical electricity demand; Convert the format of the expanded historical carbon emission factor or the expanded historical electricity demand to obtain a converted historical carbon emission factor or a converted historical electricity demand; If not, no expansion and format conversion processing is performed.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the distributed energy storage operation and scheduling method described in any one of claims 3 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the distributed energy storage operation scheduling method described in any one of claims 3 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the distributed energy storage operation scheduling method described in any one of claims 3 to 7 is implemented.

Images