Energy storage management method and device based on intelligent cloud and storage medium

Through intelligent cloud energy storage management methods, energy storage system data is collected and analyzed and optimization suggestions are generated, and the problems of intelligent management of energy storage systems and low energy efficiency are solved, and efficient energy management and fault prediction are achieved.

CN119027087APending Publication Date: 2024-11-26CYG & CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410877830.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-01
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The lack of intelligent management of existing energy storage systems has led to low energy utilization and the inability to effectively optimize energy management.

Method used

Adopt the energy storage management method based on the intelligent cloud, collect the operating data of the energy storage system, upload it to the cloud server, use the intelligent operation and maintenance model to call the knowledge base for energy optimization analysis, generate energy optimization suggestions, and realize intelligent management of the energy storage system. and improve energy conversion efficiency.

Benefits of technology

It realizes intelligent management of energy storage systems, improves energy conversion efficiency, can adapt to different environments and electricity needs, provides fault diagnosis and prediction, optimizes energy use, and reduces electricity costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027087A_ABST
    Figure CN119027087A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of energy storage systems, and particularly relates to an energy storage management method and device based on an intelligent cloud and a storage medium. Operation data of an energy storage system are collected; uploading the operation data to a cloud server; calling a knowledge base by utilizing an intelligent operation and maintenance model to carry out energy optimization analysis on the operation data to obtain an energy optimization suggestion; the intelligent management of the energy storage system is realized, and the energy conversion efficiency of the energy storage system is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the technical field of energy storage systems, and in particular, relates to an energy storage management method, device and storage medium based on an intelligent cloud. Background Art

[0002] With the continuous growth of global energy demand and the increasing attention to environmental protection, the use of renewable energy, especially solar energy, has become an important part of the global energy strategy. Existing energy storage systems mainly rely on basic battery storage technology. These systems usually lack effective energy management and optimization methods, and their energy utilization rate is low.

[0003] Therefore, improving energy efficiency and intelligent management has become an urgent issue that needs to be addressed. Summary of the invention

[0004] In view of this, the embodiments of the present application provide an energy storage management method, device and storage medium based on an intelligent cloud to solve the technical problems that traditional energy storage systems cannot achieve intelligent management and have low energy conversion efficiency.

[0005] A first aspect of an embodiment of the present application provides an energy storage management method based on an intelligent cloud, comprising:

[0006] Collect operating data of energy storage system;

[0007] Uploading the operating data to a cloud server;

[0008] Using the intelligent operation and maintenance model to call the knowledge base to perform energy optimization analysis on the operation data to obtain energy optimization suggestions;

[0009] Outputting the energy optimization suggestion;

[0010] The knowledge base is a pre-built database based on at least one of historical operation data and environment-related data of the energy storage system.

[0011] A second aspect of an embodiment of the present application provides an intelligent cloud-based energy storage management device, comprising:

[0012] A collection unit, used to collect operating data of the energy storage system;

[0013] A communication unit, used to upload the operation data to a cloud server;

[0014] An analysis unit, configured to use an intelligent operation and maintenance model to call a knowledge base to perform energy optimization analysis on the operation data and obtain energy optimization suggestions;

[0015] An output unit, used for outputting the energy optimization suggestion;

[0016] The knowledge base is a pre-built database based on at least one of historical operation data and environment-related data of the energy storage system.

[0017] A third aspect of an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the intelligent cloud-based energy storage management method provided in the first aspect of the embodiment of the present application.

[0018] The first aspect of the embodiment of the present application provides an intelligent cloud-based energy storage management method, which collects operating data of the energy storage system; uploads the operating data to a cloud server; uses an intelligent operation and maintenance model to call a knowledge base to perform energy optimization analysis on the operating data to obtain energy optimization suggestions; and outputs the energy optimization suggestions, thereby realizing intelligent management of the energy storage system and improving the energy conversion efficiency of the energy storage system.

[0019] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of a smart cloud-based energy storage management method provided in one embodiment of the present application;

[0022] Figure 2 This is a flow chart of an intelligent cloud-based energy storage management method provided by another embodiment of the present application;

[0023] Figure 3 This is a flow chart of an intelligent cloud-based energy storage management method provided by another embodiment of the present application;

[0024] Figure 4 This is a flow chart of an intelligent cloud-based energy storage management method provided by another embodiment of the present application;

[0025] Figure 5 This is a flow chart of an intelligent cloud-based energy storage management method provided by another embodiment of the present application;

[0026] Figure 6This is a flow chart of an intelligent cloud-based energy storage management method provided by another embodiment of the present application;

[0027] Figure 7 This is a structural diagram of an intelligent cloud-based energy storage management device provided in one embodiment of the present application;

[0028] Figure 8 It is a structural diagram of an intelligent cloud-based energy storage management device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0029] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0030] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0031] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0032] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0033] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0034] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0035] The intelligent cloud-based energy storage management method provided in the embodiment of the present application collects operating data of the energy storage system and uploads the operating data to a cloud server; uses an intelligent operation and maintenance model to call a knowledge base to perform energy optimization analysis on the operating data to obtain energy optimization suggestions; and outputs the energy optimization suggestions, thereby realizing intelligent management of the energy storage system and improving the energy conversion efficiency of the energy storage system.

[0036] In application, the energy storage management method based on the smart cloud can be widely used in household and commercial energy storage system products, including but not limited to household photovoltaic storage integrated systems, commercial microgrid energy storage systems, mobile energy storage power supply vehicles, and off-grid power supply systems. The energy storage management device based on the smart cloud integrates functions such as photovoltaic power generation, energy storage batteries, hybrid inverters, and intelligent energy management. The energy storage management device based on the smart cloud can be a computing device with at least one function of energy storage, conversion, management, and interaction with the user end, such as a tablet computer, a laptop computer, a personal computer (Personal Computer, PC), a netbook, a server, etc. The embodiment of the present application does not impose any restrictions on the specific type of the energy storage management device based on the smart cloud.

[0037] In the application, the intelligent operation and maintenance model integrates a large language model and an energy optimization model, and can also integrate at least one of a fault diagnosis model and a fault prediction model. Among them, large language models (LLMs) are models with large parameter scales obtained by pre-training through deep learning technology, especially advanced neural network architectures such as transformer architecture, in the field of natural language processing. Its core ability lies in understanding and generating human language, and can be applied to multiple natural language processing tasks such as text generation, translation, question and answer, dialogue system, document summarization, etc. The energy optimization model is a model that conducts a comprehensive analysis of the energy system to find the most economical, efficient and environmentally friendly energy configuration, scheduling and use plan. The fault diagnosis model is an algorithmic model that uses data analysis, signal processing, machine learning or deep learning technology to identify, locate and explain faults in the system or equipment. The fault prediction model is a model that uses data analysis, statistical methods, machine learning or deep learning technology to predict possible future faults of equipment or systems.

[0038] like Figure 1 As shown, a smart cloud-based energy storage management method of this embodiment includes the following steps S101 to S103:

[0039] Step S101, collecting operating data of the energy storage system.

[0040] In application, the energy storage system includes at least a battery module and a hybrid inverter. The battery module can store electrical energy generated from renewable energy and release this energy when needed to supply the system or home use, and send the real-time battery data to the hybrid inverter. The battery module is usually composed of multiple batteries connected in series or in parallel to provide the required voltage and current. The battery can be a lithium-ion battery, a lead-acid battery, a nickel-metal hydride battery, etc. The hybrid inverter is used to convert the direct current stored in the battery into alternating current for use in homes or commercial facilities. At the same time, it also supports the conversion of alternating current into direct current, stores it in the battery, and samples the operating data. It usually includes multiple input interfaces, a DC-DC converter, an inverter circuit, a controller, a protection circuit, a user interface, a communication interface, and a grid-connected / off-grid switching function. In addition to the above forms, the battery module and the hybrid inverter can also adopt other forms, which are not limited in this embodiment.

[0041] In applications, the operating data of the energy storage system can be obtained by connecting the battery and inverter to the data collector respectively, or by connecting the battery, inverter, and data collector in sequence. The specific means of obtaining the operating data of the energy storage system are not limited. The operating data of the energy storage system mainly includes inverter data and battery data. Among them, the inverter data includes at least one of its own operating parameters such as serial number, model, status, voltage, current, and power, and the battery data includes the battery's voltage, current, SOC, temperature and other state parameters and at least one of its inherent parameters such as capacity and charge and discharge rate.

[0042] In the application, after receiving the operating data of the energy storage system, the cloud server parses it according to the set data format and stores the data in a time series database, such as InfluxDB, to facilitate subsequent trend analysis, real-time monitoring of important parameter settings, and timely alarms when thresholds are exceeded, such as battery voltage and temperature. Finally, users can connect to the cloud server through the network to view the status information of the battery and inverter.

[0043] Step S102, uploading the operating data to a cloud server.

[0044] In the application, after obtaining the operation data, the operation data can be uploaded to the cloud server through any one or more combinations of wifi, mobile data network, wired network connection, Bluetooth, near field communication, offline storage, etc.

[0045] Step S103, using the intelligent operation and maintenance model to call the knowledge base to perform energy optimization analysis on the operation data to obtain energy optimization suggestions.

[0046] In the application, the knowledge base is a database pre-built by developers based on at least one of the historical operating data and environment-related data of the energy storage system. Among them, the historical operating data and environment-related data may include at least one of energy consumption, equipment status, maintenance records, case analysis, fault diagnosis information, and maintenance strategies, as well as a rule base and an algorithm base. The knowledge base is used to store strategies and rules for energy optimization and equipment maintenance, as well as various data processing and analysis algorithms, so as to support the computational needs of the intelligent operation and maintenance model. The intelligent operation and maintenance model is used to process the operating data of the energy storage system obtained from the cloud server based on the knowledge base, and use advanced machine learning and natural language processing technologies to provide energy optimization suggestions for the system. In addition to providing energy optimization suggestions, the intelligent operation and maintenance model can also provide fault diagnosis, fault prediction suggestions, and perform adaptive optimization based on the fault handling results fed back by users.

[0047] In applications, the intelligent operation and maintenance model can first preprocess the data obtained from the cloud server. The preprocessing can be any one or more of data format unification, cleaning, noise removal, and filling in missing values. The preprocessed data is then analyzed using machine learning and natural language processing techniques.

[0048] Step S104, outputting the energy optimization suggestion;

[0049] In the application, energy optimization suggestions can be directly output to the user terminal, and can also be output to the cloud server, so as to be output to the user terminal through the cloud server. Users can optimize and adjust the operating status of the equipment according to the energy optimization suggestions. For energy optimization suggestions that do not require user operation, they can also be translated into a series of device-level control instructions with user authorization and sent to execution units such as inverters and battery management systems. After receiving the instructions, the device will adjust its own operating conditions accordingly, such as changing the charging and discharging power, switching the working mode, etc., so as to complete the deployment of the entire system and optimize energy release.

[0050] In the application, the intelligent operation and maintenance model can generate the power load curve for a period of time in the future by analyzing the user's historical power consumption data, combining influencing factors such as weather, holidays, and economic prosperity index, using time series prediction algorithms such as Prophet and DeepAR. Since the output of new energy sources such as photovoltaic and wind power will be significantly affected by weather conditions. The intelligent operation and maintenance model can also generate the predicted value of the power generation of new energy by analyzing local weather forecasts (such as irradiance, wind speed, etc.) and equipment characteristic parameters, and using machine learning regression algorithms such as XGBoost and LightGBM. The intelligent operation and maintenance model can also obtain the price market, tiered electricity price and time-of-use electricity price policy, demand response and quotation information of the auxiliary service market in real time, as a reference for the formulation of grid interaction strategy. When conducting analysis, the intelligent operation and maintenance model can also take into account parameters such as the battery state of charge (SoC), health state (SoH), cycle life, and the real-time load rate of the inverter and transmission line. Based on the above data, the intelligent operation and maintenance model can make an overall assessment of the energy supply and demand situation in the future. Compared with traditional optimization algorithms, the intelligent operation and maintenance model can consider more real-world constraints and capture the complex nonlinear patterns contained in the data, thereby obtaining more accurate, long-term, and globally optimal decision-making solutions.

[0051] In one embodiment, Figure 2 As shown, step S102 includes the following steps S201 to S203 and / or steps S204-S206:

[0052] Step S201, obtaining peak and valley electricity price data from the knowledge base.

[0053] In the application, Kaiyuan personnel can obtain peak and valley electricity price data from official announcements, official websites, WeChat public accounts, customer service information, electricity bills and other sources of local power companies, and store them in the knowledge base.

[0054] Step S202: Analyze the peak and valley electricity price data using the intelligent operation and maintenance model to obtain peak electricity price periods and valley electricity price periods.

[0055] In the application, the intelligent operation and maintenance model analyzes the peak and valley electricity price data to obtain the peak and valley electricity price periods. The time period can be flexibly set to any length within 12 hours, such as half an hour, 1 hour, 3 hours, etc.

[0056] Step S203, generating energy optimization suggestions, including discharging during the peak electricity price period and charging during the low electricity price period.

[0057] In the application, when the intelligent operation and maintenance model obtains the peak and low electricity price periods, it can generate energy optimization suggestions for discharging during peak electricity price periods and charging during low electricity price periods, thereby saving electricity costs and achieving higher economic benefits.

[0058] Step S204, obtaining historical peak power consumption data from the knowledge base.

[0059] In the application, Kaiyuan personnel can obtain historical peak power consumption data through power supply companies, smart meters, third-party energy management services, public data, research materials and other channels, and store them in the knowledge base. Historical peak power consumption data mainly refers to the peak load moment of the power system and its related data, including but not limited to time, load, weather conditions, holidays and other factors.

[0060] Step S205: using the intelligent operation and maintenance model to predict future peak power consumption periods based on the historical peak power consumption data.

[0061] In the application, the intelligent operation and maintenance model performs data preprocessing and conversion on historical peak power consumption data, including but not limited to structured data adaptation and time series feature fusion. It then conducts specific downstream task training to identify factors and patterns related to peak power consumption, thereby obtaining differences in power consumption behavior under different scenarios such as weekdays and weekends, seasonal changes, and special events (such as the World Cup final), and then predicting future peak power demand.

[0062] Step S206, generating energy optimization suggestions, including adjusting resource allocation before the future peak electricity consumption period to reduce dependence on the ground power grid during the future peak electricity consumption period.

[0063] In the application, when the intelligent operation and maintenance model predicts the peak of electricity demand in the future, it can generate energy optimization suggestions to deal with the peak of electricity demand in advance to ensure the power supply reliability of the energy storage system. For example, it can adjust the resource ratio in advance to reduce the dependence on the ground power grid, participate in demand response when necessary, and shift the peak to fill the valley; it can also optimize the combination of multiple energy sources such as photovoltaic, wind power, energy storage, and backup power to meet the load demand while pursuing maximum benefits and minimum emissions; it can also encourage users to use high-energy-consuming appliances such as washing machines and dryers during non-peak hours to shift the peak to fill the valley.

[0064] In one embodiment, Figure 3 As shown, after step S101, the following steps S111 to S113 are also included:

[0065] Step S111, extracting features from the operating data to obtain feature data.

[0066] In applications, feature extraction is used to extract key indicators or feature vectors from operating data. These features represent a quantitative summary of the equipment's operating status for subsequent analysis.

[0067] Step S112: using the intelligent operation and maintenance model, the characteristic data is compared and analyzed with the fault mode obtained from the knowledge base to perform fault diagnosis.

[0068] In the application, the feature data is matched and inferred with the existing knowledge base. By identifying the key features and failure modes contained in the data, the intelligent operation and maintenance model can quickly determine whether the operating status of the equipment is abnormal, and give a preliminary analysis of the cause of the failure based on similar cases. Among them, the failure mode is obtained by training historical operation data and learning the association between different fault types and features. For example, if the output voltage fluctuation of the inverter exceeds the normal range and is similar to the characteristics of certain historical failure cases, the intelligent operation and maintenance model will infer that this may be caused by capacitor aging or IGBT damage.

[0069] Step S113: outputting the result of the fault diagnosis.

[0070] In the application, the intelligent operation and maintenance model feeds back the results of fault diagnosis to the user in a form that is easy to understand and operate. This includes any one or more of the fault type, fault severity, recommended repair measures, or strategies to prevent future faults. The output can be in various forms, such as fault reports, charts, alarm notifications, or direct displays on the user interface.

[0071] This embodiment can reduce system downtime, extend equipment life, and improve system reliability and safety by diagnosing faults of the energy storage system.

[0072] In one embodiment, Figure 4 As shown, after step S103, the following steps S301 to S304 are also included:

[0073] Step S301: receiving the fault handling result fed back by the user.

[0074] In the application, after receiving the feedback of the fault diagnosis results, the user can refer to the fault diagnosis results to repair the equipment fault, and after the fault repair is completed, the user can feedback the fault handling results for the intelligent operation and maintenance model to perform adaptive learning.

[0075] Step S302: Analyze the accuracy of the fault diagnosis result using the fault handling result.

[0076] In the application, after receiving the fault handling result fed back by the user, the accuracy of the fault diagnosis result is analyzed according to the actual fault data in the fault handling result to determine whether the fault diagnosis is accurate.

[0077] Step S303: adaptively learning the intelligent operation and maintenance model based on the analysis results.

[0078] In applications, when the fault diagnosis is accurate, the intelligent operation and maintenance model can be subjected to reinforcement learning or weighted learning. When the fault diagnosis is inaccurate, the model can be adjusted, such as increasing or adjusting model parameters, introducing new features, modifying or adding rules, etc. In applications, the model can also be adjusted based on the information provided by experts to improve the reliability of the model.

[0079] This embodiment uses real fault handling results to analyze the accuracy of fault diagnosis and performs adaptive learning, which can improve the reliability of the intelligent operation and maintenance model when performing fault diagnosis.

[0080] In one embodiment, in order to balance the learning of new samples and the retention of historical knowledge, the knowledge base is pruned and compressed regularly to remove redundant or low-confidence information.

[0081] Step S304: when the real fault reflected by the fault handling result is inconsistent with the result of the fault diagnosis, the real fault and the operating data associated with the real fault are updated to the knowledge base.

[0082] In the application, when a fault occurs that the intelligent operation and maintenance model cannot accurately diagnose, the fault can be treated as a new type of fault, and the data related to the fault can be expanded to the knowledge base. Expert opinions related to the fault can also be expanded to the knowledge base.

[0083] In one embodiment, at least one of the user's operating habits and usage habits is recorded; and corresponding equipment in the energy storage system is controlled according to at least one of the recorded operating habits and usage habits.

[0084] In the application, the user's usage habits or operating habits can also be stored and memorized, so as to perform intelligent control according to the user's usage / operating habits. For example, for lighting equipment with multiple tones such as cold, warm, and neutral light, the light tone that the user uses most frequently or last used can be memorized, and the next time the lighting equipment is turned on, it will be illuminated with the memorized light tone, so that the user does not need to manually switch the switch to adjust the tone of the lighting equipment to the preferred tone, which improves the user's experience. In addition, for other equipment, the user's preferences can also be memorized and stored, so that when the user turns on the equipment, the output can be based on the user's preferences.

[0085] In one embodiment, Figure 5 As shown, after step S101, the following steps S121 to S123 are also included:

[0086] Step S121, extracting features from the operating data to obtain feature data.

[0087] Step S122: input the characteristic data into an intelligent operation and maintenance model, and use the intelligent operation and maintenance model to calculate the fault probability distribution.

[0088] Step S123, outputting the fault probability distribution calculation result;

[0089] The intelligent operation and maintenance model is obtained by training using at least one of inspection logs, maintenance records, fault reports, power grid accident notifications, and product data manuals.

[0090] In the application, fault probability distribution calculation is a means of fault prediction. In addition to fault probability distribution calculation, other means can also be used for fault prediction. The fault prediction in this embodiment is based on the massive historical operation data and fault cases in the knowledge base. These data come from multiple channels, including the operation data of the energy storage system, as well as unstructured text data such as inspection logs, maintenance records, and fault reports that are continuously updated and maintained in the knowledge base. It can also be an external data source such as a public power grid accident notice on the Internet and a product data manual. The above data together constitute the data set used for fault prediction in the knowledge base.

[0091] After preprocessing steps such as cleaning, alignment, and labeling, these heterogeneous data are imported into the intelligent operation and maintenance model. Using machine learning algorithms, the data are deeply mined and feature engineered. These preliminary feature vectors and risk scores are input into the fault prediction model to generate the probability distribution of fault occurrence.

[0092] The fault prediction model of the intelligent operation and maintenance model can use any one or more of the support vector machine (SVM), random forest (RF), and long short-term memory network (LSTM) models. For specific equipment and failure modes, expert knowledge and physical constraints can also be added to build a more sophisticated model. The system will regularly retrain the model with newly collected data to continuously optimize the prediction effect. The model ensemble strategy helps to improve the accuracy and robustness of the prediction.

[0093] After the fault prediction model is trained, it can be deployed online to start monitoring real-time data streams. Once certain indicators are found to exceed the preset threshold, or the probability of a fault increases significantly, the system will automatically issue an early warning to prompt the operation and maintenance personnel to intervene in advance. The early warning information will be notified to the relevant person in charge through various means such as email, SMS, and voice calls.

[0094] In one embodiment, Figure 6 As shown, step S103 includes the following steps S311 to S313:

[0095] Step S311: performing edge computing on the energy optimization suggestion.

[0096] In applications, computing tasks can be performed on edge devices (such as smart gateways, local servers, or embedded systems) close to the data source. The advantage of edge computing is that it can process data quickly, reduce the time delay of data transmission to the cloud, and improve response speed.

[0097] Step S312: transmitting the data obtained by the edge computing to a cloud server, and the cloud server is used to provide energy optimization suggestions to the end user.

[0098] In applications, after edge devices process data, they upload the processing results or key data to the cloud server. This action helps the cloud system obtain a global view and accumulate data for further analysis, model training, or long-term strategy planning. The data sent back may include details of optimization suggestions, execution effect evaluation indicators, or reports of abnormal situations found on the edge side.

[0099] In the application, after receiving the feedback from edge computing, the cloud server will further process the information, convert it into a form that is easy for users to understand (such as charts, text suggestions, etc.), and notify the end user through a web interface, mobile application, email or other communication methods. Users can adjust their energy usage habits, optimize equipment configuration or implement energy-saving measures based on these suggestions, thereby achieving the goal of energy conservation, emission reduction and cost reduction.

[0100] In this embodiment, after the intelligent operation and maintenance model obtains energy optimization suggestions, it further processes and analyzes the energy optimization suggestions through edge computing, summarizes the key information and transmits it back to the cloud server, thereby reducing dependence on the cloud and improving the response speed and robustness of the system.

[0101] The embodiment of the present application also provides an intelligent cloud-based energy storage management device, which is used to execute the steps in the above-mentioned intelligent cloud-based energy storage management method embodiment. The intelligent cloud-based energy storage management device can be a virtual appliance in the intelligent cloud-based energy storage management device, which is run by a processor of the intelligent cloud-based energy storage management device, or it can be the intelligent cloud-based energy storage management device itself.

[0102] like Figure 7 As shown, an intelligent cloud-based energy storage management device 100 of this embodiment includes:

[0103] A collection unit 101 is used to collect operating data of the energy storage system;

[0104] The communication unit 102 is used to upload the operation data to a cloud server;

[0105] An analysis unit 103 is used to use an intelligent operation and maintenance model to call a knowledge base to perform energy optimization analysis on the operation data to obtain energy optimization suggestions;

[0106] An output unit 104, used to output the energy optimization suggestion;

[0107] The knowledge base is a pre-built database based on at least one of historical operation data and environment-related data of the energy storage system.

[0108] In one embodiment, the collection unit 101 includes a battery module 1011 , a hybrid inverter 1012 , and a collector 1013 ;

[0109] The output end of the battery module 1011 is connected to the input end of the hybrid inverter 1012, the output end of the hybrid inverter is connected to the input end of the collector 1013, and the output end of the collector 1013 is connected to the cloud server for communication;

[0110] The battery module 1011 is used for storing energy and outputting at least one data of battery voltage, current and battery charge state to the hybrid inverter 1012;

[0111] The hybrid inverter 1012 is used to output its own operating data and the data input by the battery module 1011 to the collector 1013;

[0112] The collector 1013 is used to transmit the received data to the communication unit 102 .

[0113] In the application, the battery module can realize serial communication and collaborative work between modules through the Link in / out port. The CAN / RS485 / RS232 interface of the battery module communicates with the inverter to transmit battery data. The communication mode is the master-slave communication with the inverter as the master device and the battery module as the slave device. The inverter obtains battery data through this interface and sends charge and discharge control instructions to the battery module. The RS485 interface of the inverter communicates with the data collector to transmit various data of the inverter and the battery. The communication protocol adopts the Modbus RTU protocol. The inverter is a slave station and the data collector is a master station. The data collector collects data by reading the Modbus register address allocation mapping information of the inverter. The main collected data includes inverter data and battery data. The data collector uploads the collected data to the cloud server through the built-in WiFi module. The data is temporarily stored in the memory of the data collector and uploaded once every period of time. If the communication is abnormal, the data will be cached in the Flash of the data collector and re-uploaded after recovery. In addition to using a full-bridge inverter circuit, the hybrid inverter 1012 may also use other topologies such as a half-bridge and push-pull to achieve DC-AC conversion.

[0114] In one embodiment, the analysis unit 103 is further configured to:

[0115] Obtaining peak and valley electricity price data from the knowledge base;

[0116] Analyze the peak and valley electricity price data to obtain peak electricity price periods and valley electricity price periods;

[0117] Generate energy optimization suggestions, including discharging during the peak electricity price period and charging during the low electricity price period;

[0118] and / or

[0119] Acquiring historical peak power consumption data from the knowledge base;

[0120] Using the intelligent operation and maintenance model to predict future peak power consumption periods based on the historical peak power consumption data;

[0121] Generate energy optimization suggestions, including adjusting resource allocation before the future peak electricity consumption period to reduce dependence on the ground power grid during the future peak electricity consumption period.

[0122] In one embodiment, the analysis unit 103 is further configured to:

[0123] Extracting features from the operating data to obtain feature data;

[0124] Using the intelligent operation and maintenance model, the characteristic data is compared and analyzed with the fault mode obtained from the knowledge base to perform fault diagnosis;

[0125] Outputting the result of the fault diagnosis;

[0126] The fault mode is obtained by training historical operation data and learning the association between different fault types and characteristics.

[0127] In one embodiment, the analysis unit 103 is further configured to:

[0128] Receive troubleshooting results from users;

[0129] Analyzing the accuracy of the fault diagnosis result using the fault handling result;

[0130] Performing adaptive learning on the intelligent operation and maintenance model based on the analysis results;

[0131] When the real fault reflected by the fault processing result is inconsistent with the result of the fault diagnosis, the real fault and the operating data associated with the real fault are updated to the knowledge base.

[0132] In one embodiment, the analysis unit 103 is further configured to:

[0133] Extracting features from the operating data to obtain feature data;

[0134] Inputting the characteristic data into an intelligent operation and maintenance model, and using the intelligent operation and maintenance model to calculate the fault probability distribution;

[0135] Outputting the fault probability distribution calculation result;

[0136] The intelligent operation and maintenance model is obtained by training using at least one of inspection logs, maintenance records, fault reports, power grid accident notifications, and product data manuals.

[0137] In one embodiment, an edge computing unit 106 is further included, which is used to perform edge computing on the energy optimization suggestion output by the output unit 104, and transmit the data obtained by the edge computing back to the cloud server 400. After receiving the above data, the cloud server 400 can output it to the user terminal 300.

[0138] In one embodiment, the user terminal 300 is further used to receive data output by the cloud server 400 and to feed back the fault handling result to the analysis unit 103 and the knowledge base unit 105 .

[0139] In one embodiment, a knowledge base unit 105 is further included, which is used to store historical data and provide support for the analysis unit.

[0140] In one embodiment, Figure 8 As shown, the intelligent cloud-based energy storage management device 100 includes a collection unit 101, a communication unit 102, an analysis unit 103, an output unit 104, a knowledge base unit 105 and an edge computing unit 106.

[0141] In the application, the communication unit 102 is used to receive the data transmitted by the acquisition unit 101, and upload the received data to the cloud server 400. The cloud server 400 is used to receive the data from the hybrid inverter uploaded by the communication unit 102, as well as the information of other system modules, and perform in-depth analysis and processing to ultimately form intelligent decisions and control instructions. It includes a data storage unit, which is responsible for storing various types of collected data, including real-time data and historical data, to provide support for data analysis. The cloud server 400 provides data to the analysis unit 103 for deep learning and intelligent analysis. The analysis unit 103 feeds back optimization strategies and operation suggestions to the cloud server based on the learning results. At the same time, it serves as the output interface of edge computing to optimize the operating efficiency of the server, and ultimately feeds back the processed decisions and suggestions to the end user through the output unit 104.

[0142] In the application, the knowledge base unit 105 stores the historical operation data of the system, including energy consumption, equipment status, maintenance records, etc. It also contains a strategy and rule base and an algorithm base, which are used to store energy optimization, equipment maintenance strategies and rules, as well as various data processing and analysis algorithms, so as to support the operation needs of the analysis unit. The knowledge base unit 105 directly provides support for the analysis unit, and the analysis unit will use the data and information in the knowledge base unit when performing fault diagnosis, maintenance recommendations and energy optimization decisions. At the same time, the analysis results processed by the system optimization algorithm are saved in the knowledge base unit for subsequent use.

[0143] In applications, the edge computing unit 106 can be any one of a smart gateway, a local server or an embedded system close to the data source, used for real-time data processing, local decision execution, data preprocessing and filtering, preprocessing and filtering the collected data, and only sending necessary and important data to the cloud server to optimize data transmission and storage.

[0144] In the application, the user terminal 300 can be a smart speaker, a vehicle-mounted system, a wearable device, etc., providing an immersive energy management experience through voice interaction, AR display, etc.

[0145] In application, each module in the intelligent cloud-based energy storage management device can be a software program module, or it can be implemented through different logic circuits integrated in the processor, or it can be implemented through multiple distributed processors.

[0146] In application, the intelligent cloud-based energy storage management device 100 may include, but is not limited to, a collection unit 101, a communication unit 102, an analysis unit 103, an output unit 104, a knowledge base unit 105, an edge computing unit 106, a processor, and a memory. Those skilled in the art will understand that Figure 8 It is only an example of the smart cloud-based energy storage management device 100 and does not constitute a limitation on the smart cloud-based energy storage management device 100. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0147] In applications, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0148] In the application, the memory may be an internal storage unit of the energy storage management device based on the smart cloud in some embodiments, such as a hard disk or memory of the energy storage management device based on the smart cloud. In other embodiments, the memory may also be an external storage device of the energy storage management device based on the smart cloud, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the energy storage management device based on the smart cloud. Further, the memory may also include both an internal storage unit of the energy storage management device based on the smart cloud and an external storage device. The memory is used to store operating systems, applications, boot loaders (Boot Loader), data, and other programs, such as program codes of computer programs, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0149] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0150] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0151] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on at least one processor, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0152] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0153] An embodiment of the present application provides a computer program product. When the computer program product is run on an intelligent cloud-based energy storage management device, the intelligent cloud-based energy storage management device can implement the steps in the above-mentioned various method embodiments when executed.

[0154] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0155] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0156] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0157] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for energy storage management based on intelligent cloud, characterized in that: include: Collect operating data of energy storage system; Uploading the operating data to a cloud server; Using the intelligent operation and maintenance model to call the knowledge base to perform energy optimization analysis on the operation data to obtain energy optimization suggestions; Outputting the energy optimization suggestion; The knowledge base is a pre-built database based on at least one of historical operation data and environment-related data of the energy storage system.

2. The intelligent cloud-based energy storage management method according to claim 1, characterized in that: The intelligent operation and maintenance model is used to call the knowledge base to perform energy optimization analysis on the operation data to obtain energy optimization suggestions, including: Obtaining peak and valley electricity price data from the knowledge base; Analyze the peak and valley electricity price data using the intelligent operation and maintenance model to obtain peak electricity price periods and valley electricity price periods; Generate energy optimization suggestions, including discharging during the peak electricity price period and charging during the low electricity price period; and / or Acquiring historical peak power consumption data from the knowledge base; Using the intelligent operation and maintenance model to predict future peak power consumption periods based on the historical peak power consumption data; Generate energy optimization suggestions, including adjusting resource allocation before the future peak electricity consumption period to reduce dependence on the ground power grid during the future peak electricity consumption period.

3. The intelligent cloud-based energy storage management method according to claim 1, characterized in that: After uploading the operation data to the cloud server, the method further includes: Extracting features from the operating data to obtain feature data; Using the intelligent operation and maintenance model, the characteristic data is compared and analyzed with the fault mode obtained from the knowledge base to perform fault diagnosis; Outputting the result of the fault diagnosis; The fault mode is obtained by training historical operation data and learning the association between different fault types and characteristics.

4. The intelligent cloud-based energy storage management method according to claim 3, characterized in that: After outputting the energy optimization suggestion, the method further includes: Receive troubleshooting results from users; Analyzing the accuracy of the fault diagnosis result using the fault handling result; Performing adaptive learning on the intelligent operation and maintenance model based on the analysis results; When the real fault reflected by the fault processing result is inconsistent with the result of the fault diagnosis, the real fault and the operating data associated with the real fault are updated to the knowledge base.

5. The intelligent cloud-based energy storage management method according to claim 1, characterized in that: After uploading the operation data to the cloud server, the method further includes: Extracting features from the operating data to obtain feature data; Inputting the characteristic data into an intelligent operation and maintenance model, and using the intelligent operation and maintenance model to calculate the fault probability distribution; Outputting the fault probability distribution calculation result; The intelligent operation and maintenance model is obtained by training using at least one of inspection logs, maintenance records, fault reports, power grid accident notifications, and product data manuals.

6. The intelligent cloud-based energy storage management method according to any one of claims 1 to 5, characterized in that: Outputting the energy optimization suggestion includes: performing edge computing on the energy optimization suggestion; The data obtained by the edge computing is transmitted to a cloud server, and the cloud server is used to provide energy optimization suggestions to end users.

7. The intelligent cloud-based energy storage management method according to any one of claims 1 to 5, characterized in that: Also includes: Recording at least one of the user's operating habits and usage habits; The corresponding equipment in the energy storage system is controlled according to at least one of the recorded operating habits and usage habits.

8. An energy storage management device based on intelligent cloud, characterized in that: include: A collection unit, used to collect operating data of the energy storage system; A communication unit, used to upload the operation data to a cloud server; An analysis unit, configured to use an intelligent operation and maintenance model to call a knowledge base to perform energy optimization analysis on the operation data and obtain energy optimization suggestions; An output unit, used for outputting the energy optimization suggestion; The knowledge base is a pre-built database based on at least one of historical operation data and environment-related data of the energy storage system.

9. The intelligent cloud-based energy storage management device according to claim 8, characterized in that: The collection unit includes a battery module, a hybrid inverter and a collector; The output end of the battery module is connected to the input end of the hybrid inverter, the output end of the hybrid inverter is connected to the input end of the collector, and the output end of the collector is connected to the cloud server for communication; The battery module is used for storing energy and outputting at least one data of battery voltage, current and battery state of charge to the hybrid inverter; The hybrid inverter is used to output its own operating data and the data input by the battery module to the collector; The collector is used to transmit the received data to the communication unit.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the smart cloud-based energy storage management method as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Energy efficiency management system and method for controller

    CN119758960A

  • Energy efficiency management system and method for controller

    CN119758960B