Control method and system of containerized energy storage system

Abstract

The present invention relates to the field of energy storage control technology, and in particular to a control method and system for a containerized energy storage system. The method comprises the following steps: acquiring energy storage system structure data and energy storage system demand data; constructing a perception network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent perception network; transmitting energy flow through the sensor intelligent perception network to generate standard transmission energy flow data; performing system abstract analysis based on the standard transmission energy flow data to generate system abstract description data; performing multi-scale model coupling based on the system abstract description data to generate a multi-scale coupling model; constructing a control strategy for a battery state control model to generate an energy storage control strategy. The present invention improves the efficiency and reliability of energy storage system control by performing multi-scale model coupling and control strategy construction on the energy storage system through containerized modeling.

Description

Technical Field

[0001] The present invention relates to the field of energy storage control technology, and in particular to a control method and system for a containerized energy storage system. Background Art

[0002] Early energy storage systems were mainly based on mechanical energy storage, such as water pump energy storage and flywheel energy storage. The control methods of these systems are relatively simple, and are mainly adjusted through mechanical devices, such as adjusting the flow of water pumps or the speed of flywheels. However, these systems have certain limitations in energy density and efficiency. With the popularization of smart grids and renewable energy, the control methods of energy storage systems have further developed. The emergence of intelligent control systems enables energy storage systems to be better integrated with the power grid and achieve precise control of energy flow. Control methods have gradually evolved towards technical directions such as model prediction, optimization algorithms and artificial intelligence to achieve optimal operation of energy storage systems. In addition, targeted control methods have also emerged for different types of energy storage technologies, such as compressed air energy storage and supercapacitors. However, the current energy storage system control methods lack multi-scale coupling, making it difficult to accurately describe the complex dynamic characteristics of the system. At the same time, there is a lack of effective control models and optimized control strategies for battery status, resulting in low system operation efficiency or battery damage, which in turn leads to low efficiency and reliability of energy storage system control. Summary of the invention

[0003] Based on this, it is necessary to provide a control method and system for a containerized energy storage system to solve at least one of the above technical problems.

[0004] To achieve the above object, a control method for a containerized energy storage system is provided, the method comprising the following steps:

[0005] Step S1: Acquire energy storage system structure data and energy storage system demand data; construct a perception network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent perception network; transmit energy flow through the sensor intelligent perception network to generate standard transmission energy flow data;

[0006] Step S2: performing system abstract analysis based on standard transmission energy flow data to generate system abstract description data; performing multi-scale model coupling based on the system abstract description data to generate a multi-scale coupling model;

[0007] Step S3: constructing a control strategy for the battery state control model to generate an energy storage control strategy; performing state response analysis according to the energy storage control strategy to generate a system state optimization response curve; performing real-time cloud computing monitoring of the energy storage control strategy through the system state optimization response curve to generate system state control information data;

[0008] Step S4: Perform model training on the system state control information data to generate an energy storage control performance evaluation model; import the system state control information data into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report.

[0009] The present invention obtains the energy storage system structure data and the energy storage system demand data; based on these data, a perception network is constructed, that is, a sensor intelligent perception network. The purpose of this step is to establish a network in which the system can perceive and monitor the energy flow, thereby generating standard energy flow data and providing a basis for subsequent analysis. A perception network is established, and the system can monitor the operating status and energy flow of the energy storage system in real time, providing a data basis for subsequent optimization and control. According to the standard transmission energy flow data, the system is abstractly analyzed to generate system abstract description data; then multi-scale model coupling is performed to generate a multi-scale coupling model. This step is to analyze and model the system in an abstract manner in order to better understand the system behavior. A multi-scale coupling model is generated, which can understand and analyze the energy storage system from different scales and angles, providing a more comprehensive perspective for system optimization and control. The control strategy of the battery state control model is constructed to generate an energy storage control strategy; the state response analysis is performed according to the energy storage control strategy to generate a system state optimization response curve; the energy storage control strategy is monitored by cloud computing in real time through the system state optimization response curve to generate system state control information data. This step is the process of designing the control strategy and analyzing the state response of the energy storage system. An energy storage control strategy and state response curve have been established, and the control strategy can be adjusted in real time according to the system state to improve the response speed and efficiency of the system. Model training is performed on the system state control information data to generate an energy storage control performance evaluation model; the system state control information data is imported into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report. This step is the process of performance evaluation and optimization of the system. An energy storage control performance evaluation model and an evaluation report are generated, which can evaluate the control performance of the energy storage system, identify potential problems and propose improvement measures, thereby improving the efficiency and stability of the energy storage system. Therefore, the present invention conducts multi-scale model coupling and control strategy construction on the energy storage system through container-type modeling, thereby improving the efficiency and reliability of energy storage system control.

[0010] In this specification, a containerized energy storage system is provided, which is used to execute the control method of the containerized energy storage system. The containerized energy storage system includes:

[0011] Intelligent sensing module, used to obtain energy storage system structure data and energy storage system demand data; construct a sensing network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent sensing network; transmit energy flow through the sensor intelligent sensing network to generate standard transmission energy flow data;

[0012] The multi-scale model coupling module is used to perform system abstract analysis based on standard transmission energy flow data and generate system abstract description data; perform multi-scale model coupling based on system abstract description data and generate a multi-scale coupling model;

[0013] The intelligent control strategy module is used to construct the control strategy for the battery state control model and generate the energy storage control strategy; perform state response analysis based on the energy storage control strategy and generate the system state optimization response curve; perform real-time cloud computing monitoring of the energy storage control strategy through the system state optimization response curve, thereby generating system state control information data;

[0014] The control performance evaluation module is used to perform model training on the system state control information data and generate an energy storage control performance evaluation model; the system state control information data is imported into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report.

[0015] The beneficial effect of the present invention is that by using the intelligent sensor perception network and standard transmission energy flow data, accurate monitoring and management of energy flow can be achieved, thereby optimizing the energy transmission efficiency of the energy storage system. Based on the system abstract description data and multi-scale coupling model, the complex structure and behavior of the energy storage system can be better understood and described, providing in-depth insights for system optimization and decision-making. By constructing a control strategy and analyzing the state response of the battery state control model, a more intelligent and efficient energy storage control strategy can be generated to improve system performance and stability. Based on the system state optimization response curve, real-time cloud computing monitoring can timely detect system state changes and make response adjustments to ensure the normal operation and performance optimization of the energy storage system. By training and evaluating the system state control information data through the energy storage control performance evaluation model, the performance of the energy storage system can be more accurately evaluated, and a corresponding evaluation report can be generated to provide guidance and reference for system optimization and improvement. Therefore, the present invention uses container-type modeling to couple multi-scale models and construct control strategies for the energy storage system, thereby increasing the efficiency and reliability of energy storage system control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of the steps of a control method for a containerized energy storage system;

[0017] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0018] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0019] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0023] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0024] To achieve this, please refer to Figures 1 to 4 , a control method for a containerized energy storage system, the method comprising the following steps:

[0025] Step S1: Acquire energy storage system structure data and energy storage system demand data; construct a perception network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent perception network; transmit energy flow through the sensor intelligent perception network to generate standard transmission energy flow data;

[0026] Step S2: performing system abstract analysis based on standard transmission energy flow data to generate system abstract description data; performing multi-scale model coupling based on the system abstract description data to generate a multi-scale coupling model;

[0027] Step S3: constructing a control strategy for the battery state control model to generate an energy storage control strategy; performing state response analysis according to the energy storage control strategy to generate a system state optimization response curve; performing real-time cloud computing monitoring of the energy storage control strategy through the system state optimization response curve to generate system state control information data;

[0028] Step S4: Perform model training on the system state control information data to generate an energy storage control performance evaluation model; import the system state control information data into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report.

[0029] The present invention obtains the energy storage system structure data and the energy storage system demand data; based on these data, a perception network is constructed, that is, a sensor intelligent perception network. The purpose of this step is to establish a network in which the system can perceive and monitor the energy flow, thereby generating standard energy flow data and providing a basis for subsequent analysis. A perception network is established, and the system can monitor the operating status and energy flow of the energy storage system in real time, providing a data basis for subsequent optimization and control. According to the standard transmission energy flow data, the system is abstractly analyzed to generate system abstract description data; then multi-scale model coupling is performed to generate a multi-scale coupling model. This step is to analyze and model the system in an abstract manner in order to better understand the system behavior. A multi-scale coupling model is generated, which can understand and analyze the energy storage system from different scales and angles, providing a more comprehensive perspective for system optimization and control. The control strategy of the battery state control model is constructed to generate an energy storage control strategy; the state response analysis is performed according to the energy storage control strategy to generate a system state optimization response curve; the energy storage control strategy is monitored by cloud computing in real time through the system state optimization response curve to generate system state control information data. This step is the process of designing the control strategy and analyzing the state response of the energy storage system. An energy storage control strategy and state response curve have been established, and the control strategy can be adjusted in real time according to the system state to improve the response speed and efficiency of the system. Model training is performed on the system state control information data to generate an energy storage control performance evaluation model; the system state control information data is imported into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report. This step is the process of performance evaluation and optimization of the system. An energy storage control performance evaluation model and an evaluation report are generated, which can evaluate the control performance of the energy storage system, identify potential problems and propose improvement measures, thereby improving the efficiency and stability of the energy storage system. Therefore, the present invention conducts multi-scale model coupling and control strategy construction on the energy storage system through container-type modeling, thereby improving the efficiency and reliability of energy storage system control.

[0030] In the embodiment of the present invention, reference Figure 1The above is a schematic flow chart of the steps of a control method of a containerized energy storage system of the present invention. In this example, the control method of a containerized energy storage system includes the following steps:

[0031] Step S1: Acquire energy storage system structure data and energy storage system demand data; construct a perception network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent perception network; transmit energy flow through the sensor intelligent perception network to generate standard transmission energy flow data;

[0032] In an embodiment of the present invention, by collecting structural data of the energy storage system, including information such as the type, quantity, and layout of the energy storage equipment. Obtain demand data of the energy storage system, including data on energy demand, power demand, and periodic demand. Based on the collected structural data and demand data of the energy storage system, a perception network is constructed. This may involve the use of sensors, monitoring equipment, or other perception technologies to monitor various parameters and environmental conditions of the energy storage system in real time. Using perception technology and data processing algorithms, the collected data is integrated and a sensor intelligent perception network is established. This network can monitor the state of the energy storage system, environmental changes, and energy flow in real time. Based on the sensor intelligent perception network, transmission monitoring and management of energy flow are realized. This may include monitoring and control of battery charging and discharging processes, energy transmission between energy storage devices, etc. Based on the data collected by the sensor intelligent perception network, standard transmission energy flow data is generated. These data may include information such as the starting point, end point, transmission rate, energy loss, etc. of the energy flow, providing accurate energy flow information for subsequent steps.

[0033] Step S2: performing system abstract analysis based on standard transmission energy flow data to generate system abstract description data; performing multi-scale model coupling based on the system abstract description data to generate a multi-scale coupling model;

[0034] In an embodiment of the present invention, an abstract analysis of the energy storage system is performed by using standard transmission energy flow data as a basis. This includes identifying important information such as key components of the system, energy flow paths, and energy conversion processes. Based on the analysis results, system abstract description data is generated to describe the structure, function, and behavioral characteristics of the system. These description data can be textual descriptions or graphical representations. Based on the generated system abstract description data, a multi-scale model is established. The multi-scale model takes into account the characteristics and interactions of the system at different scales, from micro to macro levels. Models of different scales are coupled to ensure information exchange and mutual influence between them. This may involve establishing mathematical models, physical models, or computational models, and integrating them using appropriate coupling techniques.

[0035] Step S3: constructing a control strategy for the battery state control model to generate an energy storage control strategy; performing state response analysis according to the energy storage control strategy to generate a system state optimization response curve; performing real-time cloud computing monitoring of the energy storage control strategy through the system state optimization response curve to generate system state control information data;

[0036] In an embodiment of the present invention, an energy storage control strategy is designed based on a battery state control model. This includes charge and discharge control strategies, temperature control strategies, etc., which are intended to maximize the performance and life of the battery. Taking into account the working environment and application requirements of the energy storage system, a suitable control strategy is formulated, such as scheduling according to grid demand, optimizing considering energy market prices, etc. According to the formulated energy storage control strategy, the state response of the system is analyzed. This includes changes in battery charge state, temperature, voltage and other parameters, as well as the impact on system performance. Through simulation or experiment, a system state optimization response curve is generated to show the changes in system state under different control strategies for subsequent optimization and adjustment. Based on the system state optimization response curve, a real-time cloud computing monitoring system is established. This can utilize the computing resources and data storage capabilities provided by the cloud computing platform to achieve real-time monitoring and analysis of the state of the energy storage system. Through the monitoring system, system state control information data is generated, including current state, predicted state, control suggestions, etc., to provide real-time support for system operation and management.

[0037] Step S4: Perform model training on the system state control information data to generate an energy storage control performance evaluation model; import the system state control information data into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report.

[0038] In an embodiment of the present invention, the system state control information data is organized into a format suitable for model training, including features and labels. A suitable evaluation model is selected according to the nature of the problem and the characteristics of the data. Common ones include regression models, classification models, neural networks, etc. The selected model is trained using a training data set to learn the evaluation rules of energy storage control performance. The new system state control information data is imported into the trained evaluation model. The model performs performance evaluation based on the imported data and generates an energy storage control performance evaluation report. The evaluation report may include evaluation results on the effectiveness of the control strategy, improvement of system performance, etc.

[0039] Preferably, step S1 comprises the following steps:

[0040] Step S11: Acquire energy storage system structure data and energy storage system demand data; perform sensor deployment based on the energy storage system structure data and energy storage system demand data, and generate sensor location data and sensor type data;

[0041] Step S12: setting a sensor transmission protocol based on the sensor position data and the sensor type data to generate sensor communication protocol data; collecting sensor data using the sensor communication protocol data to generate original sensor collection data;

[0042] Step S13: constructing a perception network based on the original sensor collection data to generate a sensor intelligent perception network;

[0043] Step S14: Perform energy flow transmission on the original sensor collected data through the sensor intelligent perception network to generate transmission energy flow data; perform data preprocessing on the transmission energy flow data to generate standard transmission energy flow data, wherein the data preprocessing includes data outlier removal, data missing value filling and data standardization.

[0044] The present invention can ensure the accuracy of sensor location and type by acquiring energy storage system structure data and demand data, as well as deploying sensors and setting communication protocols, thereby improving the accuracy of data collection. The construction of the perception network enables sensors to communicate and collaborate with each other to form an intelligent perception network, thereby improving the efficiency of data analysis and utilization, and enabling the system to better perceive environmental conditions. The transmission and processing of data by the sensor intelligent perception network can optimize energy flow transmission, ensure the timeliness and accuracy of data transmission, and improve the response speed and energy utilization efficiency of the system. Data preprocessing includes operations such as outlier removal, missing value filling, and data standardization, which can effectively improve data quality, ensure data integrity and reliability, and provide a reliable foundation for subsequent data analysis and application.

[0045] In an embodiment of the present invention, the energy storage system structure data and demand data are obtained from system design documents, actual equipment parameter tables, etc. The acquired data is cleaned and preprocessed to ensure the accuracy and completeness of the data. Sensors are arranged in the system according to the system structure and demand data, and their positions and types are recorded. The communication protocol between sensors is set, including transmission protocol, data format, etc., to ensure that the sensors can collect and transmit data normally. Data collected by sensors includes relevant parameters such as voltage, current, and temperature. The original collected data is processed, including data cleaning, filtering, denoising, etc., to improve data quality. Based on the processed data, a network connection between sensors is constructed to form an intelligent perception network. Using the intelligent perception network, data transmission and exchange are realized to ensure that data can be transmitted to the specified location in a timely and accurate manner. The transmitted energy flow data is preprocessed, including operations such as outlier removal, missing value filling, and data standardization to improve data quality and availability.

[0046] Preferably, step S13 includes the following steps:

[0047] Step S131: performing data cleaning on the original sensor acquisition data to generate sensor acquisition cleaning data;

[0048] Step S132: classifying sensor characteristic information of the sensor collected cleaning data according to the sensor type to generate sensor characteristic classification data, wherein the sensor characteristic classification data includes sensor temperature characteristic data and sensor humidity characteristic data; extracting daily average temperature characteristics based on the sensor temperature characteristic data to generate daily average temperature data; performing temperature change rate analysis on the sensor temperature characteristic data using the daily average temperature data to generate temperature change rate data;

[0049] Step S133: performing humidity change analysis on the sensor humidity characteristic data based on the temperature change rate data to generate humidity change rate data; performing humidity gradient characteristic analysis based on the humidity change rate to generate humidity gradient characteristic data; performing similarity calculation on the sensor through the humidity gradient characteristic data and the temperature change rate data to obtain sensor similarity data; clustering the sensors using the sensor similarity data to generate sensor clustering data;

[0050] Step S134: constructing a sensor perception network topology structure according to the sensor clustering data and the sensor similarity data to generate a sensor network topology structure; performing unsupervised learning on the sensor network topology structure to generate a sensor intelligent perception network.

[0051] The present invention can effectively remove noise and abnormal data by cleaning and classifying the original sensor data, and extract key sensor feature information, such as temperature and humidity, to provide an accurate and reliable data basis for subsequent analysis. Analysis of characteristic data such as temperature and humidity can reveal the changing trend and correlation between sensors. Based on features such as humidity change rate and temperature change rate, similarity data between sensors are calculated, which helps to discover the correlation and pattern between sensors. Cluster analysis is performed based on the similarity data of the sensors, and sensors with similar characteristics and behavior patterns are classified into one category, thereby constructing the sensor perception network topology. This clustering and network construction method helps to understand the relationship between sensors and provide a basis for system optimization and management. Through unsupervised learning, intelligent perception networks are generated using sensor clustering data and similarity data. Such a network structure can help the system monitor and respond to environmental changes in real time, and improve the intelligence and adaptability of the system.

[0052] In an embodiment of the present invention, data quality is ensured by using a data cleaning algorithm, such as removing duplicate data, processing missing values, outliers and noise, etc. The cleaned data is classified according to the sensor type, for example, distinguishing between temperature sensors and humidity sensors. Feature information, such as temperature and humidity, and other possible features, is extracted for each type of sensor data. The daily average temperature is extracted from the temperature feature data, and the temperature change rate data is calculated. The humidity change rate is analyzed for the humidity feature data based on the temperature change rate data, and the humidity gradient feature data is extracted. The similarity between sensors is calculated using the humidity gradient feature data and the temperature change rate data, and the sensor similarity data is obtained. The sensors are clustered using the sensor similarity data, and a clustering algorithm such as K-means clustering or hierarchical clustering can be used. The topological structure of the sensor perception network is constructed based on the sensor clustering data and the similarity data. The sensor network topology is unsupervisedly learned, and methods such as neural networks and self-organizing maps can be used to generate a sensor intelligent perception network.

[0053] Preferably, step S2 comprises the following steps:

[0054] Step S21: Perform system abstract analysis based on standard transmission energy flow data to generate system abstract description data;

[0055] Step S22: Perform energy flow modeling based on the system abstract description data to generate an energy flow control model;

[0056] Step S23: Perform temperature distribution modeling based on the energy flow control module to generate a temperature distribution control model;

[0057] Step S24: performing battery state estimation modeling based on the temperature distribution control module and the energy flow control module to generate a battery state control model;

[0058] Step S25: performing multi-scale model coupling on the energy flow control model, the temperature distribution control model and the battery state control model to generate a multi-scale coupling model.

[0059] The present invention generates system abstract description data by abstract analysis of standard transmission energy flow data, which helps to understand the overall structure and function of the system. Such abstract analysis can help identify key energy flow paths and components, and provide a basis for subsequent modeling. Energy flow modeling based on system abstract description data and generating an energy flow control model are helpful to understand the transmission and conversion process of energy in the system. This model can be used to optimize the energy flow path, improve the energy utilization efficiency of the system, and evaluate the stability and reliability of the system. Based on the energy flow control model, temperature distribution modeling is performed to generate a temperature distribution control model, which helps to understand the distribution law and change trend of temperature in the system. The temperature distribution control model can be used to optimize the heat dissipation design, improve the working efficiency and stability of the system, and protect the system from overheating. Based on the temperature distribution control module and the energy flow control module, battery state estimation modeling is performed to generate a battery state control model, which helps to monitor and manage the health status and performance of the battery. This model can be used to optimize the charging and discharging strategy, extend the service life of the battery, and improve the energy utilization efficiency of the system. Multi-scale model coupling of the energy flow control model, the temperature distribution control model and the battery state control model can comprehensively consider the influencing factors at different levels and aspects, and improve the comprehensiveness and accuracy of the model. This multi-scale coupling model can provide more comprehensive and accurate guidance for the design, optimization and control of the system, thereby achieving efficient operation and long-term stability of the system.

[0060] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0061] Step S21: Perform system abstract analysis based on standard transmission energy flow data to generate system abstract description data;

[0062] In an embodiment of the present invention, data related to energy flow in the system is collected. These data may include information on electricity, heat, mechanical energy, etc., depending on the nature of the system. Ensure that the collected energy flow data conforms to a certain standard format or specification, which is helpful for subsequent processing and analysis. Industry standards or custom standards can be used to standardize data. The collected energy flow data is subjected to system abstract analysis. This includes identifying key components in the system, energy flow paths, energy conversion processes, etc. Through this step, an abstract description of the overall structure of the system and the energy flow situation can be established. Based on the results of the abstract analysis, abstract description data of the system is generated. These data can be system structure and energy flow information presented in the form of graphics, tables, text, etc., providing a basis for subsequent modeling and analysis. Verify and correct the generated system abstract description data

[0063] Step S22: Perform energy flow modeling based on the system abstract description data to generate an energy flow control model;

[0064] In an embodiment of the present invention, the abstract description data of the system is collected, including information such as system composition, component parameters, connection relationships, etc. These data can be obtained through system design documents, technical specifications or field surveys. An energy flow model is established based on the abstract description data of the system. This includes determining the energy input, output and energy conversion process of each component in the system. The abstract description data of the system is converted into a mathematical model, for example, using a set of equations, graph theory and other methods to describe the flow relationship of energy in the system. Based on the energy flow model, an energy flow control strategy is designed. This can be achieved through control theory, optimization algorithms and other methods. The energy flow control strategy is converted into a mathematical model and combined with the energy flow model to form a complete energy flow control model.

[0065] Step S23: Perform temperature distribution modeling based on the energy flow control module to generate a temperature distribution control model;

[0066] In an embodiment of the present invention, a temperature distribution model is established based on the energy flow control model of the system in combination with the structure and material properties of the system. This includes determining factors such as the heat conduction characteristics, heat capacity, and the influence of the external environment on the temperature of each component in the system. Use heat transfer theory and mathematical models to describe the transfer and distribution of heat in the system. This may involve heat conduction equations, boundary conditions, and the like. Based on the temperature distribution model, a temperature distribution control strategy is designed. This may include controlling the heat input and output of the system, adjusting the heat transfer path within the system, and the like. The temperature distribution control strategy is converted into a mathematical model and combined with the temperature distribution model to form a complete temperature distribution control model.

[0067] Step S24: performing battery state estimation modeling based on the temperature distribution control module and the energy flow control module to generate a battery state control model;

[0068] In an embodiment of the present invention, a battery state estimation model is established by combining a temperature distribution control model and an energy flow control model according to the characteristics and working conditions of the battery. This includes factors such as the chemical characteristics of the battery, internal electrochemical reactions, and the effect of temperature on battery performance. Theoretical and mathematical models such as electrochemical models and heat conduction models are used to describe processes such as charge transfer, ion diffusion, and temperature change inside the battery, as well as the relationship between these processes and the battery state. Based on the battery state estimation model, a battery state control strategy is designed. This may include battery charge and discharge control strategies, temperature control strategies, safety protection strategies, and the like. The battery state control strategy is converted into a mathematical model and combined with the battery state estimation model to form a complete battery state control model.

[0069] Step S25: performing multi-scale model coupling on the energy flow control model, the temperature distribution control model and the battery state control model to generate a multi-scale coupling model.

[0070] In an embodiment of the present invention, an energy flow control model, a temperature distribution control model and a battery state control model are coupled to form a comprehensive multi-scale model. In the coupling process, it is necessary to consider the mutual influence and interaction between the models to ensure the consistency and accuracy between the models. The models can be coupled by a physical coupling method, a mathematical coupling method or a hybrid coupling method. The physical coupling method is to couple the models based on physical laws and principles, while the mathematical coupling method is to couple the models through mathematical equations. When coupling, it is necessary to consider the time lag, nonlinear effects and correlation between the models to ensure the accuracy and stability of the coupling model. After the coupling is completed, the multi-scale coupling model needs to be verified and adjusted. This includes simulation verification of the model, parameter adjustment, and analysis and evaluation of the model output. By comparing and verifying with actual data, it is ensured that the multi-scale coupling model can accurately reflect the dynamic characteristics and performance of the battery system.

[0071] Preferably, step S22 includes the following steps:

[0072] Step S221: performing battery charging characteristic analysis based on the system abstract description data to generate battery charging characteristic analysis data, wherein the battery charging characteristic analysis data includes charging rate data and charging voltage curve data; performing battery charging characteristic curve conversion on the charging rate data and the charging voltage curve data to generate a battery charging characteristic curve;

[0073] Step S222: performing battery discharge characteristic analysis based on the system abstraction module to generate battery discharge characteristic analysis data, wherein the battery discharge characteristic analysis data includes discharge rate data and discharge voltage curve data; performing battery discharge characteristic curve conversion on the discharge rate data and the discharge voltage curve data to generate a battery discharge characteristic curve;

[0074] Step S223: performing battery charge and discharge efficiency loss analysis based on the battery charge characteristic curve and the battery discharge characteristic curve to generate battery charge and discharge efficiency loss analysis data; establishing a charge and discharge energy balance equation based on the battery charge and discharge efficiency loss analysis data to generate a battery charge and discharge energy balance equation;

[0075] Step S224: Perform energy flow modeling based on the battery charge and discharge energy balance equation data to generate an energy flow control model.

[0076] The present invention generates charging rate data and charging voltage curve data by analyzing the charging characteristics of the battery, which helps to understand the performance of the battery during the charging process. The present invention generates discharge rate data and discharge voltage curve data by analyzing the discharge characteristics of the battery, which helps to understand the performance of the battery during the discharge process. Based on the charging and discharging characteristic curves, the charging and discharging efficiency loss of the battery is analyzed, so as to establish the charging and discharging energy balance equation to further understand the energy conversion efficiency of the battery. According to the charging and discharging energy balance equation data, energy flow modeling is performed to generate an energy flow control model, which helps to design a battery energy management system and optimize the use and performance of the battery.

[0077] In an embodiment of the present invention, the charging rate data and charging voltage curve data of the battery are collected. The charging characteristics analysis is performed using the system abstract description data, which may involve factors such as battery type, chemical composition, temperature, etc. The collected data is processed and converted to generate a battery charging characteristic curve. The discharge rate data and discharge voltage curve data of the battery are collected. The discharge characteristics analysis is performed using the system abstract module, taking into account the characteristics and environmental conditions of the battery. The collected data is processed and converted to generate a battery discharge characteristic curve. Based on the battery charging characteristic curve and discharge characteristic curve, the charge and discharge efficiency loss analysis is performed. The charge and discharge energy balance equation is established using the analysis results, taking into account the loss in the energy conversion process. The battery charge and discharge efficiency loss analysis data and the charge and discharge energy balance equation are generated. Energy flow modeling is performed based on the charge and discharge energy balance equation data. Factors such as the energy flow path and conversion efficiency in the battery system are considered. An energy flow control model is generated to optimize the energy management and control of the battery.

[0078] Preferably, step S23 includes the following steps:

[0079] Step S231: Analyze the thermal conductivity characteristics of the battery using the energy flow control model to generate the thermal conductivity characteristics analysis data of the battery, wherein the thermal conductivity characteristics analysis data of the battery includes the thermal conductivity coefficient of the battery and the thermal capacity data of the battery; convert the thermal conductivity characteristics curve of the battery according to the thermal conductivity coefficient of the battery and the thermal capacity data of the battery to generate the thermal conductivity characteristics curve of the battery;

[0080] Step S232: extracting the extreme value points of the battery heat conduction characteristic curve to obtain the battery heat conduction minimum point data and the battery heat conduction maximum point data; adjusting the battery heat generation model of the energy flow control model according to the battery heat conduction minimum point data and the battery heat conduction maximum point data to generate the battery heat generation model;

[0081] Step S233: extracting ambient temperature data from the standard transmission energy flow data to obtain ambient temperature data; calculating the battery charge and discharge heat generation temperature difference based on the battery heat generation model to obtain ambient-battery internal temperature difference data; performing curve conversion on the ambient-battery internal temperature difference data to generate an ambient temperature change curve;

[0082] Step S234: Establish a thermal balance equation for the battery heat generation model and the ambient temperature change curve to generate a battery thermal balance equation; perform temperature distribution simulation based on the battery thermal balance equation to generate battery temperature distribution simulation data; perform temperature distribution modeling using the battery thermal balance equation and the battery temperature distribution simulation data to generate a temperature distribution control model.

[0083] By analyzing the thermal conductivity characteristics of the battery, the present invention can understand the heat generated by the battery during the charging and discharging process and how the heat is conducted to the surrounding environment. This helps to design the heat dissipation system and predict the temperature changes of the battery. By extracting the extreme points of the battery thermal conductivity characteristic curve, the energy flow control model can be adjusted to establish a more accurate battery heat generation model. This helps to more accurately predict the heat generation and distribution of the battery. Combining the ambient temperature data and the battery heat generation model, the temperature difference between the environment and the inside of the battery can be calculated. This helps to understand the impact of ambient temperature on battery performance and life. Establishing a battery thermal balance equation can take into account factors such as heat generation, heat dissipation and ambient temperature inside the battery, thereby more comprehensively analyzing the temperature changes of the battery. Using the battery thermal balance equation and temperature distribution simulation data to establish a temperature distribution control model can optimize the temperature distribution of the battery system and improve the efficiency and safety of the battery.

[0084] In an embodiment of the present invention, the thermal conductivity characteristics of the battery are analyzed by using an energy flow control model to obtain the battery thermal conductivity coefficient and heat capacity data. Based on these data, the battery thermal conductivity characteristic curve is converted to understand the thermal conductivity characteristics of the battery at different temperatures. The extreme points are extracted from the battery thermal conductivity characteristic curve to determine the lowest and highest points of the battery thermal conduction. The energy flow control model is adjusted using these data to generate a more accurate battery heat generation model to consider the influence of heat generation inside the battery. The ambient temperature data in the standard transmission energy flow data is extracted. The temperature difference between the environment and the inside of the battery is calculated based on the battery heat generation model, and converted into an ambient temperature change curve. The battery heat generation model and the ambient temperature change curve are combined to establish a battery thermal balance equation. The battery thermal balance equation is used to simulate the temperature distribution and generate battery temperature distribution simulation data. Finally, the battery thermal balance equation and the battery temperature distribution simulation data are used to establish a temperature distribution control model to achieve precise control of the battery temperature distribution.

[0085] Preferably, step S24 includes the following steps:

[0086] Step S241: performing battery response characteristic analysis on the energy flow control model based on the temperature distribution control model to generate battery response characteristic analysis data; performing battery characteristic modeling based on the battery response characteristic analysis data to generate a battery charge and discharge characteristic model;

[0087] Step S242: Analyze the charge and discharge evolution law according to the battery charge and discharge characteristic analysis data to generate a battery state equation; observe the relationship between the battery measurement output and the system state of the battery charge and discharge characteristic analysis data through the battery state equation to generate a battery observation equation; perform state space conversion on the battery charge and discharge characteristic model based on the battery state equation and the battery observation equation to generate a battery state space model;

[0088] Step S243: measuring the battery noise through the battery state space model to obtain battery noise measurement data; using the Kalman filter to estimate the battery noise on the battery state space model to obtain battery noise estimation data; calculating the noise variance of the battery noise estimation data and the battery noise measurement data to generate battery measurement noise variance data;

[0089] Step S244: Use the battery measurement noise variance data and the battery state equation to perform battery state estimation modeling to generate a battery state control model.

[0090] The present invention performs battery characteristic modeling through battery response characteristic analysis data, which can better understand the battery charging and discharging behavior and generate a battery charging and discharging characteristic model. Such a model can be used to predict the performance, life and safety of the battery, and provide an important reference for the battery management system. The battery state equation is generated according to the battery charging and discharging characteristic analysis data, which can reveal the evolution law of the internal state of the battery and conduct an in-depth analysis of the battery charging and discharging process. By establishing the battery state equation and the observation equation, a battery state space model can be established, providing a mathematical framework for describing the evolution of the battery state. By measuring and estimating battery noise through the battery state space model, the uncertainty and measurement error of the battery state can be accurately evaluated. By using the Kalman filter to estimate the noise of the battery state space model, the estimation accuracy of the battery state can be improved, and more reliable data support can be provided for system control. By using the battery measurement noise variance data and the battery state equation to perform battery state estimation modeling, a battery state control model can be generated. This model can be used to monitor the battery state in real time, predict battery performance and safety, and adopt corresponding control strategies to ensure the stability and reliability of the battery system.

[0091] In an embodiment of the present invention, the energy flow control model is analyzed by using a temperature distribution control model to obtain battery response characteristic analysis data. According to the analysis data, a suitable modeling technology, such as mathematical modeling or machine learning method, is used to generate a battery charge and discharge characteristic model. Based on the battery charge and discharge characteristic analysis data, the charge and discharge evolution law is analyzed to generate a battery state equation. The battery charge and discharge characteristic analysis data is observed through the battery state equation to establish a battery observation equation. Based on the state equation and the observation equation, a state space conversion is performed to generate a battery state space model. The battery state space model is used to measure battery noise and obtain battery noise measurement data. The Kalman filter is used to estimate the noise of the battery state space model to obtain battery noise estimation data. The noise variance of the battery noise estimation data and the battery noise measurement data is calculated to generate battery measurement noise variance data. Combined with the battery measurement noise variance data and the battery state equation, battery state estimation modeling is performed to generate a battery state control model.

[0092] Preferably, step S3 comprises the following steps:

[0093] Step S31: performing multi-physics field coupling on the battery state control model to generate multi-physics field coupling data; constructing a control strategy for the multi-scale coupling model based on the multi-physics field coupling data to generate an energy storage control strategy;

[0094] The control strategy construction steps include:

[0095] Based on the multi-physical field coupling data, the power supply of the multi-scale coupling model is analyzed to obtain the power supply data; the power supply data is compared with the preset standard power supply demand threshold, and when the power supply data is greater than or equal to the preset standard power supply demand threshold, the first power conversion is performed through the energy flow module to generate direct current power storage data; when the power supply data is less than the preset standard power supply demand threshold, the second power conversion is performed through the energy flow module according to the inverter to generate alternating current power storage data;

[0096] Based on the multi-physics field coupling data, the multi-scale coupling model is used to perform a battery component temperature analysis to obtain the battery component temperature data; the DC power storage data and the AC power storage data are used to perform a power conversion frequency analysis to generate power conversion rate data; the battery component temperature data is compared with a preset optimal temperature threshold, and when the battery component temperature data is greater than or equal to the preset optimal temperature threshold, the battery charge and discharge rate of the power conversion rate data is reduced to generate first temperature adjustment data; when the battery component temperature data is less than the preset optimal temperature threshold, the fan speed is adjusted through the temperature distribution control model to generate second temperature adjustment data;

[0097] Based on the battery state control model, the battery charge and discharge state of the DC power storage data and the AC power storage data is controlled to generate a battery charge and discharge control strategy; based on the battery state control model, the battery temperature is controlled to the first temperature adjustment data and the second temperature adjustment data to generate a battery temperature control strategy; the battery charge and discharge control strategy and the battery temperature control strategy are merged to generate an energy storage control strategy;

[0098] Step S32: performing state response analysis on the battery state control model according to the energy storage control strategy to generate a system state response curve; performing robust optimization on the system state response data using a simulated annealing algorithm to generate a system state optimization response curve;

[0099] Step S33: searching the optimal control strategy parameter space for the energy storage control strategy through the system state optimization response curve to generate control search data;

[0100] Step S34: Design a cloud computing architecture based on the control search data to generate a cloud computing architecture diagram; use the cloud computing architecture diagram to monitor the control strategy of the control search data in real time, thereby generating system status control information data.

[0101] The present invention can more comprehensively understand the behavior of the battery system by performing multi-physics field coupling analysis on the battery state control model. Based on the multi-physics field coupling data, the energy storage control strategy is constructed to achieve more effective energy management and optimization control. By analyzing and comparing the power supply data, the battery charging and discharging strategy can be effectively determined to meet the preset power supply demand threshold. According to the battery component temperature data and the power conversion rate data, the battery charging and discharging rate and the power conversion frequency are optimized to improve the system efficiency and extend the battery life. Based on the battery state control model, the battery charging and discharging state is accurately controlled to ensure system stability and performance optimization. Through the battery temperature control strategy, the battery component temperature is effectively managed to improve the system safety and stability. Through state response analysis and optimization, the system response speed can be improved and the performance can be optimized. Using the simulated annealing algorithm to optimize the system state, the optimal control strategy can be found in a complex environment. Based on the cloud computing architecture design, efficient management and optimization of the control strategy can be achieved, while improving the scalability and flexibility of the system. Using the cloud computing architecture for real-time monitoring, system failures or anomalies can be discovered and resolved in a timely manner, and the stability and reliability of the system can be improved.

[0102] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0103] Step S31: performing multi-physics field coupling on the battery state control model to generate multi-physics field coupling data; constructing a control strategy for the multi-scale coupling model based on the multi-physics field coupling data to generate an energy storage control strategy;

[0104] In an embodiment of the present invention, a battery state control model is established, including an electrochemical model, a thermal model, a mechanical model, etc. of the battery. The electrochemical, thermal and mechanical characteristics of the battery are coupled to each other, and the mutual influence and action between them are considered to form a multi-physics coupling model. The multi-physics coupling model is calculated using numerical methods or simulation software to obtain simulation data. Through experiments, tests or simulation calculations, the multi-physics coupling data of the battery under different working conditions are obtained, including voltage, current, temperature, stress, etc. The collected data are processed and analyzed to form a multi-physics coupling data set. The multi-physics coupling data is input into the multi-scale coupling model. The power supply of the battery system is analyzed, including predicting the future power supply and the current power supply status. When the power supply data is greater than or equal to the preset standard power supply demand threshold: the first power conversion is performed through the energy flow module to generate DC power storage data. When the power supply data is less than the preset standard power supply demand threshold: the second power conversion is performed through the energy flow module according to the inverter to generate AC power storage data. The battery component temperature analysis is performed based on the multi-physics coupling data. The battery component temperature data is obtained. Perform power conversion frequency analysis on DC power storage data and AC power storage data. Generate power conversion rate data. Compare battery assembly temperature data with a preset optimal temperature threshold. According to the comparison result: when the battery assembly temperature data is greater than or equal to the preset optimal temperature threshold, reduce the battery charge and discharge rate and generate first temperature adjustment data. When the battery assembly temperature data is less than the preset optimal temperature threshold, adjust the fan speed through the temperature distribution control model and generate second temperature adjustment data. Based on the battery status control model, perform battery charge and discharge status control on DC power storage data and AC power storage data. Based on the battery status control model, perform battery temperature control on the first temperature adjustment data and the second temperature adjustment data. Combine the battery charge and discharge control strategy and the battery temperature control strategy to form a comprehensive energy storage control strategy.

[0105] Step S32: performing state response analysis on the battery state control model according to the energy storage control strategy to generate a system state response curve; performing robust optimization on the system state response data using a simulated annealing algorithm to generate a system state optimization response curve;

[0106] In an embodiment of the present invention, the energy storage control strategy is input as an input into the battery state control model. The battery state control model is used for simulation calculation to simulate the battery system state response under different working conditions, including changes in parameters such as voltage, current, and temperature. The system state response data for each time step is recorded. The system state response data obtained by simulation calculation is sorted out, including changes in parameters such as voltage, current, and temperature over time. Using data visualization tools or software, a system state response curve is drawn to intuitively display the response of the system under different working conditions. The simulated annealing algorithm is selected as the optimization algorithm for optimizing the system state response curve. An initial solution, that is, the initial state of the system state response curve, is randomly generated. An objective function is defined to evaluate the pros and cons of the system state response curve, such as minimizing the system response time, maximizing the system stability, etc. The initial solution is iteratively optimized by the simulated annealing algorithm, and the state response curve is continuously updated until the optimization goal is reached or the stop condition is met. The system state response curve obtained after the simulated annealing algorithm is optimized is recorded. Using data visualization tools or software, a system state optimization response curve is drawn to display the response of the optimized system under different working conditions.

[0107] Step S33: searching the optimal control strategy parameter space for the energy storage control strategy through the system state optimization response curve to generate control search data;

[0108] In an embodiment of the present invention, the current state of the system is analyzed, including grid load demand, renewable energy generation, energy storage system state, etc. According to the system state analysis, the response curve that needs to be optimized is determined, such as the charge and discharge power curve and charge and discharge state curve of the energy storage system. These curves can be optimized based on information such as grid load forecast and renewable energy forecast. The parameter space of the energy storage control strategy is determined, including parameters such as charge and discharge power limit, charge and discharge time limit, SOC (State of Charge) control strategy, etc. An optimization algorithm (such as genetic algorithm, particle swarm algorithm, simulated annealing algorithm, etc.) is used to search in the parameter space to find the optimal control strategy parameter combination. During the search process, the feedback information of the system state optimization response curve can be used to guide the adjustment direction of the parameters. According to the search results, the search data of the control strategy parameter space is generated, including the optimal parameter combination, the corresponding system state response curve and other information. These data can be used for energy storage system control in practical applications.

[0109] Step S34: Design a cloud computing architecture based on the control search data to generate a cloud computing architecture diagram; use the cloud computing architecture diagram to monitor the control strategy of the control search data in real time, thereby generating system status control information data.

[0110] In the embodiment of the present invention, the requirements for control search data are analyzed, including requirements for data processing, storage, and computing. According to the demand analysis, a suitable cloud computing architecture is designed, including a cloud service module, a data storage module, a computing resource module, and the like. Suitable cloud computing platforms (such as AWS, Azure, Google Cloud, etc.), databases (such as MySQL, MongoDB, InfluxDB, etc.), message queues (such as Kafka, RabbitMQ, etc.), real-time computing engines (such as Apache Flink, Apache Spark, etc.) and other technologies are selected. A security mechanism is designed to ensure the security of data during transmission and storage, including measures such as data encryption and access control. A design tool or drawing software is used to generate a corresponding architecture diagram according to the cloud computing architecture design. The architecture diagram should clearly show the relationship between each module, the data flow path, and the data processing flow. The control search data is obtained from the energy storage system and transmitted to the cloud computing platform. A monitoring system is built on the cloud computing platform to monitor the control search data in real time. This includes receiving, processing, and analyzing data, and generating real-time control strategy monitoring results. An exception handling mechanism is designed to promptly detect and handle data anomalies or system failures to ensure the stability and reliability of the monitoring system. Based on the real-time monitoring results, system status control information data is generated, including optimized control strategy parameters, system status prediction, adjustment suggestions, etc. The generated system status control information data is transmitted back to the energy storage system to adjust the control strategy and realize real-time control and optimization of the system status.

[0111] Preferably, step S4 comprises the following steps:

[0112] Step S41: collecting historical data of the system state control information data to generate historical system state control information data; dividing the system state control information data into data sets to generate a model training set and a model test set;

[0113] Step S42: Performing model training on the model training set using a convolutional neural network algorithm to generate an energy storage control performance evaluation training model; performing model testing on the energy storage control performance evaluation training model according to the model test set to generate an energy storage control performance evaluation model;

[0114] Step S43: importing the system state control information data into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate energy storage control performance evaluation data; visualizing the energy storage control performance evaluation data and generating an energy storage control performance evaluation report.

[0115] The present invention can establish a comprehensive data foundation by collecting historical system state control information data and dividing it into a training set and a test set, providing reliable data support for subsequent model training and evaluation. By using the convolutional neural network algorithm to train the model on the training set and evaluating the performance of the model through the test set, an evaluation model that can accurately predict the control performance of the energy storage system can be established to provide a basis for system optimization. The system state control information data is imported into the evaluation model for performance evaluation. The obtained evaluation data can intuitively show the pros and cons of the system control performance. Through data visualization, the evaluation results can be clearly presented to provide a basis for decision-making. Through the energy storage control performance evaluation report, system managers can understand the actual operation of the system, identify problems and bottlenecks, and formulate corresponding optimization strategies and decisions based on the evaluation results to improve the performance and efficiency of the energy storage system. Based on the results and reports of the energy storage control performance evaluation, continuous system improvement and optimization can be carried out to continuously improve the performance and operating efficiency of the energy storage system and achieve continuous improvement and optimization of the system.

[0116] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0117] Step S41: collecting historical data of the system state control information data to generate historical system state control information data; dividing the system state control information data into data sets to generate a model training set and a model test set;

[0118] In an embodiment of the present invention, the system state control information data to be collected is determined, including but not limited to sensor data, control commands, system operation status, etc. A data collection device or system is configured to ensure that the system state control information data can be continuously collected. The collected data is recorded and stored to ensure the integrity and traceability of the data. The collected system state control information data is sorted and processed to ensure the uniformity and standardization of the data format. The data is cleaned and denoised to exclude abnormal data and invalid data. The cleaned data is sorted and archived in chronological order to generate a historical system state control information data set. The historical system state control information data set is divided into a training set and a test set according to a certain ratio. The common ratio is 70% training set and 30% test set, but it can also be adjusted according to actual conditions. Ensure that the data distribution of the training set and the test set is representative to avoid data skew and deviation. Ensure that there is no overlap between the training set and the test set to ensure the objectivity and accuracy of the model evaluation. The divided training set and test set data are saved as corresponding data files or database tables to ensure easy access and management of the data. Identify the label or classification information of each data in the data set for use in subsequent model training and testing.

[0119] Step S42: Performing model training on the model training set using a convolutional neural network algorithm to generate an energy storage control performance evaluation training model; performing model testing on the energy storage control performance evaluation training model according to the model test set to generate an energy storage control performance evaluation model;

[0120] In an embodiment of the present invention, a model training set is trained by using a convolutional neural network (CNN) algorithm. The network structure of the CNN model is defined, including a convolutional layer, a pooling layer, a fully connected layer, etc., and the network parameters are adjusted according to the actual situation. The model training set is input into the CNN model, and the model parameters are updated by a back propagation algorithm and an optimizer (such as a gradient descent algorithm) to minimize the loss function on the training set. During the training process, the performance indicators of the model, such as the loss value and the accuracy, are monitored to ensure that the model gradually converges and optimizes on the training set. The model test set is tested using a trained energy storage control performance evaluation training model. The test set is input into the trained CNN model to obtain the prediction results of the model for the test set samples. Performance evaluation is performed based on the prediction results and the true labels of the test set. Common evaluation indicators include accuracy, precision, recall, F1 score, etc. The performance of the model on the test set is analyzed, and the generalization ability and accuracy of the model are evaluated to determine the actual application effect of the model. According to the results of the model test, the model is tuned and improved, such as adjusting the network structure, adjusting the hyperparameters, and increasing regularization. The robustness and reliability of the model can be verified through cross-validation and other techniques to further improve the performance of the model. After completing model training and testing, the final evaluation model is deployed to the actual energy storage control system. During the deployment process, it is necessary to consider the integration and calling method of the model, as well as the interface and interaction method with the actual system.

[0121] Step S43: importing the system state control information data into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate energy storage control performance evaluation data; visualizing the energy storage control performance evaluation data and generating an energy storage control performance evaluation report.

[0122] In an embodiment of the present invention, the system state control information data is imported into the trained energy storage control performance evaluation model. To ensure that the imported data format matches the model input requirements, data preprocessing and format conversion may be required. The imported data is input into the evaluation model for energy storage control performance evaluation. The model predicts the performance of energy storage control based on the input system state control information data, such as predicting the charging and discharging state, efficiency, response speed, etc. of the energy storage system. The imported data is input into the evaluation model for energy storage control performance evaluation. The model predicts the performance of energy storage control based on the input system state control information data, such as predicting the charging and discharging state, efficiency, response speed, etc. of the energy storage system. The generated energy storage control performance evaluation data is visualized using a data visualization tool or programming library. The performance of the energy storage system under different conditions can be displayed in the form of a line chart, a bar chart, a scatter plot, etc. Visual analysis can be used to observe the performance change trend of the energy storage system, compare the performance differences of different schemes or strategies, etc. Based on the visualization results and evaluation data, an energy storage control performance evaluation report is generated. The report should include quantitative evaluation results of the energy storage system performance, visualization charts, analysis conclusions, etc. The report can help decision makers understand the actual performance of the energy storage system and guide subsequent optimization and decision-making processes.

[0123] In this specification, a containerized energy storage system is provided, which is used to execute the control method of the containerized energy storage system. The containerized energy storage system includes:

[0124] Intelligent sensing module, used to obtain energy storage system structure data and energy storage system demand data; construct a sensing network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent sensing network; transmit energy flow through the sensor intelligent sensing network to generate standard transmission energy flow data;

[0125] The multi-scale model coupling module is used to perform system abstract analysis based on standard transmission energy flow data and generate system abstract description data; perform multi-scale model coupling based on system abstract description data and generate a multi-scale coupling model;

[0126] The intelligent control strategy module is used to construct the control strategy for the battery state control model and generate the energy storage control strategy; perform state response analysis based on the energy storage control strategy and generate the system state optimization response curve; perform real-time cloud computing monitoring of the energy storage control strategy through the system state optimization response curve, thereby generating system state control information data;

[0127] The control performance evaluation module is used to perform model training on the system state control information data and generate an energy storage control performance evaluation model; the system state control information data is imported into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report.

[0128] The beneficial effect of the present invention is that by using the intelligent sensor perception network and standard transmission energy flow data, accurate monitoring and management of energy flow can be achieved, thereby optimizing the energy transmission efficiency of the energy storage system. Based on the system abstract description data and multi-scale coupling model, the complex structure and behavior of the energy storage system can be better understood and described, providing in-depth insights for system optimization and decision-making. By constructing a control strategy and analyzing the state response of the battery state control model, a more intelligent and efficient energy storage control strategy can be generated to improve system performance and stability. Based on the system state optimization response curve, real-time cloud computing monitoring can timely detect system state changes and make response adjustments to ensure the normal operation and performance optimization of the energy storage system. By training and evaluating the system state control information data through the energy storage control performance evaluation model, the performance of the energy storage system can be more accurately evaluated, and a corresponding evaluation report can be generated to provide guidance and reference for system optimization and improvement. Therefore, the present invention uses container-type modeling to couple multi-scale models and construct control strategies for the energy storage system, thereby increasing the efficiency and reliability of energy storage system control.

[0129] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0130] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A control method for a containerized energy storage system, characterized in that: The following steps are involved: Step S1: Obtain energy storage system structure data and energy storage system demand data; Construct a perception network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent perception network; Energy flow transmission is performed through the sensor intelligent perception network to generate standard transmission energy flow data; Step S2: Perform system abstract analysis based on standard transmission energy flow data to generate system abstract description data; Based on the system abstract description data, multi-scale model coupling is performed to generate a multi-scale coupling model; Step S2 includes the following steps: Step S21: performing system abstract analysis according to standard transmission energy flow data to generate system abstract description data; Step S22: Perform energy flow modeling based on the system abstract description data to generate an energy flow control model; Step S23: Perform temperature distribution modeling based on the energy flow control module to generate a temperature distribution control model; Step S24: Perform battery state estimation modeling based on the temperature distribution control module and the energy flow control module to generate a battery state control model; Step S24 includes the following steps: Step S241: performing battery response characteristic analysis on the energy flow control model based on the temperature distribution control model to generate battery response characteristic analysis data; performing battery characteristic modeling based on the battery response characteristic analysis data to generate a battery charge and discharge characteristic model; Step S242: Analyze the charge and discharge evolution law according to the battery charge and discharge characteristic analysis data to generate a battery state equation; observe the relationship between the battery measurement output and the system state of the battery charge and discharge characteristic analysis data through the battery state equation to generate a battery observation equation; perform state space conversion on the battery charge and discharge characteristic model based on the battery state equation and the battery observation equation to generate a battery state space model; Step S243: measuring the battery noise through the battery state space model to obtain battery noise measurement data; using the Kalman filter to estimate the battery noise on the battery state space model to obtain battery noise estimation data; calculating the noise variance of the battery noise estimation data and the battery noise measurement data to generate battery measurement noise variance data; Step S244: using the battery measurement noise variance data and the battery state equation to perform battery state estimation modeling and generate a battery state control model; Step S25: performing multi-scale model coupling on the energy flow control model, the temperature distribution control model and the battery state control model to generate a multi-scale coupling model; Step S3: constructing a control strategy for the battery state control model to generate an energy storage control strategy; performing state response analysis according to the energy storage control strategy to generate a system state optimization response curve; performing real-time cloud computing monitoring of the energy storage control strategy through the system state optimization response curve to generate system state control information data; Step S4: Perform model training on the system state control information data to generate an energy storage control performance evaluation model; import the system state control information data into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report.

2. The control method of the containerized energy storage system according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire energy storage system structure data and energy storage system demand data; perform sensor deployment based on the energy storage system structure data and energy storage system demand data, and generate sensor location data and sensor type data; Step S12: setting a sensor transmission protocol based on the sensor position data and the sensor type data to generate sensor communication protocol data; collecting sensor data using the sensor communication protocol data to generate original sensor collection data; Step S13: constructing a perception network based on the original sensor collection data to generate a sensor intelligent perception network; Step S14: Perform energy flow transmission on the original sensor collected data through the sensor intelligent perception network to generate transmission energy flow data; perform data preprocessing on the transmission energy flow data to generate standard transmission energy flow data, wherein the data preprocessing includes data outlier removal, data missing value filling and data standardization.

3. The control method of the containerized energy storage system according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: performing data cleaning on the original sensor acquisition data to generate sensor acquisition cleaning data; Step S132: classifying sensor characteristic information of the sensor collected cleaning data according to the sensor type to generate sensor characteristic classification data, wherein the sensor characteristic classification data includes sensor temperature characteristic data and sensor humidity characteristic data; extracting daily average temperature characteristics based on the sensor temperature characteristic data to generate daily average temperature data; performing temperature change rate analysis on the sensor temperature characteristic data using the daily average temperature data to generate temperature change rate data; Step S133: performing humidity change analysis on the sensor humidity characteristic data based on the temperature change rate data to generate humidity change rate data; performing humidity gradient characteristic analysis based on the humidity change rate to generate humidity gradient characteristic data; performing similarity calculation on the sensor through the humidity gradient characteristic data and the temperature change rate data to obtain sensor similarity data; clustering the sensors using the sensor similarity data to generate sensor clustering data; Step S134: constructing a sensor perception network topology structure according to the sensor clustering data and the sensor similarity data to generate a sensor network topology structure; performing unsupervised learning on the sensor network topology structure to generate a sensor intelligent perception network.

4. The control method of the containerized energy storage system according to claim 1, characterized in that: Step S22 includes the following steps: Step S221: performing battery charging characteristic analysis based on the system abstract description data to generate battery charging characteristic analysis data, wherein the battery charging characteristic analysis data includes charging rate data and charging voltage curve data; performing battery charging characteristic curve conversion on the charging rate data and the charging voltage curve data to generate a battery charging characteristic curve; Step S222: performing battery discharge characteristic analysis based on the system abstraction module to generate battery discharge characteristic analysis data, wherein the battery discharge characteristic analysis data includes discharge rate data and discharge voltage curve data; performing battery discharge characteristic curve conversion on the discharge rate data and the discharge voltage curve data to generate a battery discharge characteristic curve; Step S223: performing battery charge and discharge efficiency loss analysis based on the battery charge characteristic curve and the battery discharge characteristic curve to generate battery charge and discharge efficiency loss analysis data; establishing a charge and discharge energy balance equation based on the battery charge and discharge efficiency loss analysis data to generate a battery charge and discharge energy balance equation; Step S224: Perform energy flow modeling based on the battery charge and discharge energy balance equation data to generate an energy flow control model.

5. The control method of the containerized energy storage system according to claim 1, characterized in that: Step S23 includes the following steps: Step S231: Analyze the thermal conductivity characteristics of the battery using the energy flow control model to generate the thermal conductivity characteristics analysis data of the battery, wherein the thermal conductivity characteristics analysis data of the battery includes the thermal conductivity coefficient of the battery and the thermal capacity data of the battery; convert the thermal conductivity characteristics curve of the battery according to the thermal conductivity coefficient of the battery and the thermal capacity data of the battery to generate the thermal conductivity characteristics curve of the battery; Step S232: extracting the extreme value points of the battery heat conduction characteristic curve to obtain the battery heat conduction minimum point data and the battery heat conduction maximum point data; adjusting the battery heat generation model of the energy flow control model according to the battery heat conduction minimum point data and the battery heat conduction maximum point data to generate the battery heat generation model; Step S233: extracting ambient temperature data from the standard transmission energy flow data to obtain ambient temperature data; calculating the battery charge and discharge heat generation temperature difference based on the battery heat generation model to obtain ambient-battery internal temperature difference data; performing curve conversion on the ambient-battery internal temperature difference data to generate an ambient temperature change curve; Step S234: Establish a thermal balance equation for the battery heat generation model and the ambient temperature change curve to generate a battery thermal balance equation; perform temperature distribution simulation based on the battery thermal balance equation to generate battery temperature distribution simulation data; perform temperature distribution modeling using the battery thermal balance equation and the battery temperature distribution simulation data to generate a temperature distribution control model.

6. The control method of the containerized energy storage system according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing multi-physics field coupling on the battery state control model to generate multi-physics field coupling data; constructing a control strategy for the multi-scale coupling model based on the multi-physics field coupling data to generate an energy storage control strategy; The control strategy construction steps include: Based on the multi-physical field coupling data, the power supply of the multi-scale coupling model is analyzed to obtain the power supply data; the power supply data is compared with the preset standard power supply demand threshold, and when the power supply data is greater than or equal to the preset standard power supply demand threshold, the first power conversion is performed through the energy flow module to generate direct current power storage data; when the power supply data is less than the preset standard power supply demand threshold, the second power conversion is performed through the energy flow module according to the inverter to generate alternating current power storage data; Based on the multi-physics field coupling data, the multi-scale coupling model is used to perform a battery component temperature analysis to obtain the battery component temperature data; the DC power storage data and the AC power storage data are used to perform a power conversion frequency analysis to generate power conversion rate data; the battery component temperature data is compared with a preset optimal temperature threshold, and when the battery component temperature data is greater than or equal to the preset optimal temperature threshold, the battery charge and discharge rate of the power conversion rate data is reduced to generate first temperature adjustment data; when the battery component temperature data is less than the preset optimal temperature threshold, the fan speed is adjusted through the temperature distribution control model to generate second temperature adjustment data; Based on the battery state control model, the battery charge and discharge state of the DC power storage data and the AC power storage data is controlled to generate a battery charge and discharge control strategy; based on the battery state control model, the battery temperature is controlled to the first temperature adjustment data and the second temperature adjustment data to generate a battery temperature control strategy; the battery charge and discharge control strategy and the battery temperature control strategy are merged to generate an energy storage control strategy; Step S32: performing state response analysis on the battery state control model according to the energy storage control strategy to generate a system state response curve; performing robust optimization on the system state response data using a simulated annealing algorithm to generate a system state optimization response curve; Step S33: searching the optimal control strategy parameter space for the energy storage control strategy through the system state optimization response curve to generate control search data; Step S34: Design a cloud computing architecture based on the control search data to generate a cloud computing architecture diagram; use the cloud computing architecture diagram to monitor the control strategy of the control search data in real time, thereby generating system status control information data.

7. The control method of the containerized energy storage system according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: collecting historical data of the system state control information data to generate historical system state control information data; dividing the system state control information data into data sets to generate a model training set and a model test set; Step S42: Performing model training on the model training set using a convolutional neural network algorithm to generate an energy storage control performance evaluation training model; performing model testing on the energy storage control performance evaluation training model according to the model test set to generate an energy storage control performance evaluation model; Step S43: importing the system state control information data into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate energy storage control performance evaluation data; visualizing the energy storage control performance evaluation data and generating an energy storage control performance evaluation report.

8. A containerized energy storage system, characterized in that: Used to execute the control method of the containerized energy storage system according to claim 1, the containerized energy storage system comprising: Intelligent sensing module, used to obtain energy storage system structure data and energy storage system demand data; construct a sensing network based on the energy storage system structure data and energy storage system demand data to generate a sensor intelligent sensing network; transmit energy flow through the sensor intelligent sensing network to generate standard transmission energy flow data; The multi-scale model coupling module is used to perform system abstract analysis based on standard transmission energy flow data and generate system abstract description data; perform multi-scale model coupling based on system abstract description data and generate a multi-scale coupling model; The intelligent control strategy module is used to construct the control strategy for the battery state control model and generate the energy storage control strategy; perform state response analysis based on the energy storage control strategy and generate the system state optimization response curve; perform real-time cloud computing monitoring of the energy storage control strategy through the system state optimization response curve, thereby generating system state control information data; The control performance evaluation module is used to perform model training on the system state control information data and generate an energy storage control performance evaluation model; the system state control information data is imported into the energy storage control performance evaluation model to perform energy storage control performance evaluation and generate an energy storage control performance evaluation report.

Images