Panoramic operation early warning analysis method and system for EMS full life cycle management

Abstract

The invention provides a panoramic operation early warning analysis method and system for EMS full life cycle management, and the method and system enable an EMS to manage the BMS and PCS of each energy storage node of an energy storage power station, extract the BMS feature data and PCS feature data from the BMS and PCS through ETL service, and feed back the data to the EMS, thereby reducing the operation calculation load of the EMS, and reducing the operation management risk. Data analysis and early warning under each index are performed on the BMS feature data and the PCS feature data through a model, and an analysis and early warning result is displayed on an EMS panoramic platform for a front end to perform panoramic operation management, so that panoramic management is realized, it is not required to spend much time and energy on basic data analysis, and the management efficiency of the EMS is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage management, and in particular to a panoramic operation warning analysis method for EMS full life cycle management, a panoramic operation warning analysis system for EMS full life cycle management, an electronic device and a computer-readable storage medium. Background Art

[0002] As attached Figure 1 As shown in the figure, the energy storage system is mainly composed of a battery management system (BMS), an energy management system (EMS), a battery pack, a power storage device (PCS) and other electrical equipment. The energy management system (EMS) is the core of the coordinated control of the entire energy storage system. EMS coordinates and controls each device in the energy storage system, manages and counts the charging and discharging power of the energy storage system and the operating status of each component of the energy storage system, regulates and controls the energy storage system and collects relevant operating parameters. The battery pack is connected to the PCS device, and the PCS device is connected to the load and connected to the grid through the intelligent distribution unit. The PCS device communicates with the EMS through the Ethernet interface (or RS485 interface) (reporting the charging and discharging data of the energy storage device), and the EMS communicates with the PCS device, BMS and smart meter through the RS485 interface to realize the energy scheduling of the energy storage system.

[0003] In a distributed charging and discharging energy storage system, several energy storage cabinets will be distributed in the system power grid (generally energy storage cabinets composed of battery packs, and each energy storage cabinet is controlled by a PCS and BMS). Although the energy storage system workstation can view the operating status of each device / system through the background EMS management system, in traditional energy storage systems, almost all management tasks will be performed on the EMS management system, which will bring huge computing pressure to the EMS management system, causing risks such as overload and shutdown of the EMS management system. In the face of several energy storage nodes, the EMS is required to process massive amounts of data from the PCS and BMS, which will cause a huge operating computing load on the EMS and cause operational management risks (downtime, shutdown, errors, etc.).

[0004] In addition, these system operation risks and the safety risks of the system BMS and PCS are mainly displayed based on numerical data sets in traditional EMS management systems. Users can only perform operation fault analysis based on fault codes fed back by the system. Therefore, the system cannot display a more comprehensive and visualized operating status analysis to users. This results in administrators and other users having to spend more time and energy on basic data analysis when the system performs alarm analysis.

[0005] Therefore, the traditional EMS management system is unable to achieve panoramic operation warning analysis and needs to be optimized and improved to improve its management efficiency. Summary of the invention

[0006] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a panoramic operation warning analysis method for EMS full life cycle management is provided, which is implemented based on a panoramic operation warning analysis system for EMS full life cycle management. The panoramic operation warning analysis system based on EMS full life cycle management includes: A plurality of energy storage nodes, wherein the energy storage nodes include a BMS and a PCS, and the BMS is configured with a BMS ETL template for extracting BMS feature data, and the PCS is configured with a PCS ETL template for extracting PCS feature data; EMS, used to manage each of the energy storage nodes of the energy storage power station, including: respectively building and configuring corresponding BMS ETL templates and PCS ETL templates for the BMS and PCS of each of the energy storage nodes, and performing panoramic operation early warning analysis on the BMS and PCS of each of the energy storage nodes based on the extracted BMS feature data and PCS feature data to achieve panoramic management; The method comprises the following steps: S1. EMS builds an ETL business execution template based on the ETL structure, including the BMS ETL template and the PCSETL template, wherein the BMS ETL template is used to extract BMS feature data from the BMS system data, and the PCS ETL template is used to extract PCS feature data from the PCS system data; S2. EMS configures the BMS ETL template and the PCS ETL template to the BMS and PCS of each energy storage node respectively; S3, the EMS performs sampling according to a preset sampling frequency, notifies the BMS and PCS of each energy storage node to regularly extract the corresponding BMS feature data and the PCS feature data and feeds them back to the EMS; S4. Based on preset indicators, EMS performs data analysis and early warning on the BMS characteristic data and the PCS characteristic data under various indicators, and displays the analysis and early warning results on the EMS panoramic platform for the front end to perform panoramic operation management.

[0007] Furthermore, S1, based on the ETL structure, an ETL business execution template is constructed, including: The administrator logs in to the EMS and configures the ETL execution context, including the data execution context between the EMS and the BMS, and the data execution context between the EMS and the PCS. The data execution context includes: data sampling requirements issued by the EMS to the BMS / PCS, the extraction format of the BMS / PCS feature data, data conversion requirements and data loading logic, and the storage address of the extracted BMS / PCS feature data in the EMS database; The ETL execution context is parsed through the ETL management module to obtain the ETL execution logic of the corresponding ETL execution context, including: the data execution logic between the EMS and the BMS, and the data execution logic between the EMS and the PCS; and based on the ETL execution logic, the corresponding BMS ETL template and the PCS ETL template are constructed; After the construction is completed, the ETL management module sends the BMS ETL template and the PCS ETL template to the EMS panoramic platform respectively to preview the templates and determine whether they can be put into storage: If the construction is correct, the BMS ETL template and the PCS ETL template are saved in the database; Otherwise, the ETL execution context is reconfigured, and the corresponding BMS ETL template and / or the PCS ETL template is reconstructed based on the above steps.

[0008] Furthermore, the ETL execution logic includes the following application logic: operator dependency, life cycle and basic attributes, where: The operator dependencies include: Supports the relevant encapsulation logic of operator parsing; External expression construction is required in operator parsing; The complex functions required for operator parsing are encapsulated in operator dependencies for easy use in operator parsing. The life cycle includes: The data set needs to be created / updated during the ETL execution process; Get input / output datasets; Check the output dataset; Inherited dataset; Run completion notification; Check if the input dataset is available; The basic attributes include: Provide the basic properties required for this ETL runtime, including operator network, version, BMS / PCS node information, domain, BMS / PCS energy storage node owner, priority setting, additional task parameters, and trigger path.

[0009] Further, S4, EMS performs data analysis and early warning on the BMS characteristic data and the PCS characteristic data under various indicators based on preset indicators, including: Importing the BMS characteristic data and the PCS characteristic data into the index data management module of the EMS; The indicator data management module screens the BMS characteristic data and the PCS characteristic data based on the preset operation warning analysis indicators to obtain corresponding BMS indicator characteristic data and PCS indicator characteristic data; Importing the BMS indicator characteristic data and the PCS indicator characteristic data into a preset operation warning analysis module respectively; The operation warning analysis module uses a pre-deployed operation warning analysis model to perform operation fault prediction on the BMS indicator characteristic data and the PCS indicator characteristic data, respectively, and outputs corresponding BMS operation fault prediction results and / or PCS operation fault prediction results.

[0010] Furthermore, the method for constructing the operation early warning analysis model comprises the following steps: Collecting a feature set includes: extracting BMS feature data from system data of the BMS through a BMS ETL template, extracting PCS feature data from system data of the PCS through the PCS ETL template, and constructing a feature set based on the BMS feature data and the PCS feature data; Divide the feature set into a training set and a validation set according to a preset ratio; Importing the training set into a preset machine learning model, respectively training and learning the characteristic relationship between the BMS characteristic data and the PCS characteristic data and the corresponding fault and alarm types, and generating the operation warning analysis model; The performance of the operation warning analysis model is verified using the verification set: If the verification is successful, the operation warning analysis model is deployed to the EMS; Otherwise, the feature data is re-extracted and the operation warning analysis model is optimized and trained.

[0011] On the other hand, a panoramic operation warning analysis system for EMS full life cycle management is provided, and the panoramic operation warning analysis system for EMS full life cycle management is used to implement the panoramic operation warning analysis method for EMS full life cycle management described above, and the system includes: A plurality of energy storage nodes, wherein the energy storage nodes include a BMS and a PCS, and the BMS is configured with a BMS ETL template for extracting BMS feature data, and the PCS is configured with a PCS ETL template for extracting PCS feature data; EMS, used to manage each of the energy storage nodes of the energy storage power station, including: respectively building and configuring corresponding BMS ETL templates and PCS ETL templates for the BMS and PCS of each of the energy storage nodes, and performing panoramic operation early warning analysis on the BMS and PCS of each of the energy storage nodes based on the extracted BMS feature data and PCS feature data to achieve panoramic management; The EMS is deployed with: User center, used for users to log in to EMS and perform corresponding operations; Data processing system, used to provide CPU data processing services; A data acquisition module is used to perform sampling according to a preset sampling frequency, notify the BMS and PCS of each energy storage node to regularly extract the corresponding BMS characteristic data and the PCS characteristic data and feed them back to the EMS; An indicator data management module, for filtering the BMS characteristic data and the PCS characteristic data based on preset operation warning analysis indicators, respectively, to obtain corresponding BMS indicator characteristic data and PCS indicator characteristic data; and, for importing the BMS indicator characteristic data and the PCS indicator characteristic data into a preset operation warning analysis module respectively; An ETL management module is used to construct an ETL business execution template, including the BMS ETL template and the PCS ETL template, wherein the BMS ETL template is used to extract BMS feature data from the system data of the BMS, and the PCS ETL template is used to extract PCS feature data from the system data of the PCS; and the BMS ETL template and the PCS ETL template are respectively configured to the BMS and PCS of each energy storage node; An operation warning analysis module, used to use a pre-deployed operation warning analysis model to perform operation fault prediction on the BMS indicator characteristic data and the PCS indicator characteristic data, respectively, and output corresponding BMS operation fault prediction results and / or PCS operation fault prediction results; EMS panoramic platform, used for BMS and PCS panoramic operation analysis and early warning of each energy storage node; Database, for data storage; Component / software library, which is used to provide various components / software, including ETL tools and panoramic application software; The port service module is used to provide various data transmission and data communication ports.

[0012] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, a panoramic operation warning analysis method for EMS full life cycle management as described above is implemented.

[0013] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement the panoramic operation warning analysis method for the above-mentioned EMS full life cycle management.

[0014] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention allows the EMS to manage the BMS and PCS of each energy storage node of the energy storage power station, and utilizes the ETL service to extract BMS feature data and PCS feature data on the BMS and PCS respectively and feed them back to the EMS, thereby reducing the operation calculation load of the EMS and reducing the operation management risk.

[0015] In addition, the present invention performs data analysis and early warning on the BMS characteristic data and the PCS characteristic data under various indicators through a model, and displays the analysis and early warning results on the EMS panoramic platform for the front-end to perform panoramic operation management, thereby realizing panoramic management without spending a lot of time and energy on basic data analysis, thereby improving the management efficiency of EMS. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 It is a schematic diagram of the composition of the energy storage system; Figure 2 It is a structural diagram of a panoramic operation early warning analysis system based on EMS full life cycle management provided by an embodiment of the present invention; Figure 3 This is a flow chart of a panoramic operation early warning analysis method for EMS full life cycle management provided by an embodiment of the present invention; Figure 4 This is a schematic diagram of the ETL structure; Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0019] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0020] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0021] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0022] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0023] An embodiment of the present invention provides a panoramic operation warning analysis method for EMS full life cycle management. The method can be implemented by an electronic device, which can be a terminal or a server.

[0024] The present invention is based on Figure 2 The panoramic operation warning analysis system based on EMS full life cycle management shown in the figure includes: A plurality of energy storage nodes, wherein the energy storage nodes include a BMS and a PCS, and the BMS is configured with a BMS ETL template for extracting BMS feature data, and the PCS is configured with a PCS ETL template for extracting PCS feature data; The EMS is used to manage each of the energy storage nodes of the energy storage power station, including: respectively building and configuring corresponding BMS ETL templates and PCS ETL templates for the BMS and PCS of each of the energy storage nodes, and performing panoramic operation early warning analysis on the BMS and PCS of each of the energy storage nodes based on the extracted BMS feature data and PCS feature data to achieve panoramic management.

[0025] The present invention is mainly aimed at the operation and management of distributed energy storage systems. Distributed energy storage systems include several energy storage nodes, each of which is an energy storage power station. Each energy storage power station is equipped with a corresponding battery pack, as well as a BMS and a PCS for power management and charge and discharge management. BMS and PCS each have their own control modules and corresponding data processing and control chips, such as a controller or a single-chip microcomputer, or an MCU chip, etc. The specific chip used in this invention is determined by the hardware system of each power station.

[0026] In order to reduce the data processing load of EMS in the present invention, the corresponding ETL template is configured on the control modules of BMS and PCS to extract and clean the corresponding BMS system data and PCS system data, so as to reduce the data processing load of EMS. The ETL template is constructed based on the ETL structure, and the template content (including corresponding data processing conditions, formats, types, extraction, processing rules, etc.) is constructed for the control logic of BMS and PCS respectively based on EMS. EMS configures the constructed ETL template on the control modules of BMS and PCS, so that BMS and PCS can perform data pre-processing, share the data processing pressure of EMS (data post-processing burden), and improve the processing efficiency of EMS.

[0027] Furthermore, the EMS system is equipped with a corresponding panoramic operation warning analysis platform, which can visualize the characteristic data under each indicator based on the panoramic application software (the panoramic system installed by the software library, such as a 360-degree panoramic view or a panoramic platform built for the energy storage EMS system based on digital twin technology (involving dynamic data mapping)). This allows administrators to view the BMS and PCS system data of each energy storage node through the EMS visual panoramic view.

[0028] Furthermore, the present invention deploys corresponding machine learning models on the system at the same time, constructs corresponding feature training sets through BMS feature data and PCS feature data extracted and collected by ETL, optimizes iterative training conditions through preset models, and trains and constructs corresponding operation warning analysis models to perform operation warning analysis, output corresponding fault and alarm information prediction results, and display them on a panoramic platform, so that administrators can intelligently manage the EMS system and conduct full life cycle management, use artificial intelligence to replace manual inspections, save time and energy, and improve the operation and management efficiency of the energy storage power grid.

[0029] The communication control between the EMS and each energy storage node BMS and PCS in this article can refer to the communication configuration scheme of the existing energy storage system, which will not be described in detail in this embodiment.

[0030] Administrators can log in to the backend server where EMS is located through inspection terminals, such as PDA terminals, to achieve corresponding online panoramic management. The administrator can log in and perform corresponding operations on corresponding model and template construction, indicator setting, and docking management of the panoramic platform (EMS platform configures corresponding component libraries and software libraries, and can pre-download corresponding components / software).

[0031] like Figure 3 The flowchart of the panoramic operation warning analysis method for EMS full life cycle management is shown. The processing flow of the method may include the following steps: S1. EMS builds an ETL business execution template based on the ETL structure, including the BMS ETL template and the PCSETL template, wherein the BMS ETL template is used to extract BMS feature data from the BMS system data, and the PCS ETL template is used to extract PCS feature data from the PCS system data; S2. EMS configures the BMS ETL template and the PCS ETL template to the BMS and PCS of each energy storage node respectively; S3, the EMS performs sampling according to a preset sampling frequency, notifies the BMS and PCS of each energy storage node to regularly extract the corresponding BMS feature data and the PCS feature data and feeds them back to the EMS; S4. Based on preset indicators, EMS performs data analysis and early warning on the BMS characteristic data and the PCS characteristic data under various indicators, and displays the analysis and early warning results on the EMS panoramic platform for the front end to perform panoramic operation management.

[0032] The above steps can be understood in conjunction with the description of the system above. Some configuration work can be done through the user center to configure parameters, such as building an ETL blank template, setting the sampling frequency, setting model training conditions, etc.

[0033] BMS system data and PCS system data can include the following contents respectively: BMS system data: total voltage, current, average temperature, SOC, SOH, charge and discharge current and power limit of each battery group, maximum battery voltage of a single cell, maximum battery temperature of a single cell, fault and alarm information, historical charge and discharge power, historical charge and discharge energy and other common information.

[0034] PCS system data, including: voltage / current / power of each branch on the DC side, active power, reactive power, voltage, current, power factor, frequency and temperature of each phase on the AC side, cabinet temperature, operating status, alarm and fault information and other common information, as well as daily charging amount, daily discharging amount, cumulative charging amount and cumulative discharging amount.

[0035] The extracted BMS characteristic data and PCS characteristic data may be the following characteristic data respectively: BMS characteristic data: total voltage, current, average temperature, SOC, SOH, charge and discharge current, fault and alarm information of each battery group.

[0036] PCS characteristic data, including: voltage / current / power of each branch on the DC side, voltage, current, temperature, cabinet temperature, operating status, alarm and fault information on the AC side, as well as daily charging amount, daily discharging amount, cumulative charging amount, and cumulative discharging amount.

[0037] Each characteristic data may be the fault / alarm type when a fault or alarm occurs and the characteristic data range value at the corresponding time point.

[0038] ETL is the abbreviation of Extract-Transform-Load, which is used to describe the process of extracting, transforming and loading data from the source to the destination. Figure 4 shown.

[0039] Furthermore, S1, based on the ETL structure, an ETL business execution template is constructed, including: The administrator logs in to the EMS and configures the ETL execution context, including the data execution context between the EMS and the BMS, and the data execution context between the EMS and the PCS. The data execution context includes: data sampling requirements issued by the EMS to the BMS / PCS, the extraction format of the BMS / PCS feature data, data conversion requirements and data loading logic, and the storage address of the extracted BMS / PCS feature data in the EMS database; The ETL execution context is parsed through the ETL management module to obtain the ETL execution logic of the corresponding ETL execution context, including: the data execution logic between the EMS and the BMS, and the data execution logic between the EMS and the PCS; and based on the ETL execution logic, the corresponding BMS ETL template and the PCS ETL template are constructed; After the construction is completed, the ETL management module sends the BMS ETL template and the PCS ETL template to the EMS panoramic platform respectively to preview the templates and determine whether they can be put into storage: If the construction is correct, the BMS ETL template and the PCS ETL template are saved in the database; Otherwise, the ETL execution context is reconfigured, and the corresponding BMS ETL template and / or the PCS ETL template is reconstructed based on the above steps.

[0040] Combination Figure 4 As shown, ETL needs to extract, transform, and load data according to the execution logic. Therefore, when building an ETL template, it is necessary to determine the template content according to a certain execution logic.

[0041] The data context between EMS and each energy storage node can refer to the description of the above system and method steps. In the data interaction process of the data execution context, EMS will set and configure the data sampling requirements of the corresponding system and the extraction format, conversion requirements, loading logic, etc. of the feature data to be extracted, and can also assign it a storage address in the EMS database. Therefore, after constructing the ETL template according to these logics of the context, the BMS and PCS of each energy storage node can implement the corresponding data extraction pre-processing calculations according to their configured ETL templates, extract the feature data of each system according to the execution logic in the ETL template, and feed it back to the EMS. The data acquisition module of EMS will sample, receive responses, and store data.

[0042] On the EMS, when building a template by calling components through the ETL management module, you can interact with the panoramic platform, transfer the template to the panoramic platform for preview, and determine whether the logical program of the constructed ET template conforms to the data processing logic of the EMS and the BMS and PCS of each energy storage node, and perform a panoramic visualization display for easy review. If the template is built correctly, it can be saved to the template library in the database. After the construction is completed, the two constructed ETL templates can be configured in the BMS and PCS of each energy storage node through the ETL management module, and sampling can be performed by setting the working parameters.

[0043] Furthermore, the ETL execution logic includes the following application logic: operator dependency, life cycle and basic attributes, where: The operator dependencies include: Supports the relevant encapsulation logic of operator parsing; External expression construction is required in operator parsing; The complex functions required for operator parsing are encapsulated in operator dependencies for easy use in operator parsing. The life cycle includes: The data set needs to be created / updated during the ETL execution process; Get input / output datasets; Check the output dataset; Inherited dataset; Run completion notification; Check if the input dataset is available; The basic attributes include: Provide the basic properties required for this ETL runtime, including operator network, version, BMS / PCS node information, domain, BMS / PCS energy storage node owner, priority setting, additional task parameters, and trigger path.

[0044] In the present invention, the method for constructing an ETL business execution template can refer to the relevant content of the method for performing data conversion based on an ETL module developed based on low-code proposed in the invention patent with publication number CN117111894A.

[0045] The above-mentioned ETL execution logic includes descriptions of operator dependencies, lifecycles, and basic properties, which can be understood in conjunction with the above-mentioned public technologies and will not be described in detail in this embodiment.

[0046] EMS can configure the basic attributes of the corresponding ETL template for the BMS and PCS of the energy storage nodes that need to run early warning analysis, so that EMS can know the attributes of the data processing tasks of the BMS and PCS of each energy storage node, and let the background clearly understand the operation status of the BMS and PCS of each energy storage node (operator network, version, BMS / PCS node information, domain, BMS / PCS energy storage node owner, priority setting, additional task parameters and trigger path). These attribute information are very clear, thus realizing panoramic management of the entire life cycle.

[0047] Further, S4, EMS performs data analysis and early warning on the BMS characteristic data and the PCS characteristic data under various indicators based on preset indicators, including: Importing the BMS characteristic data and the PCS characteristic data into the index data management module of the EMS; The indicator data management module screens the BMS characteristic data and the PCS characteristic data based on the preset operation warning analysis indicators to obtain corresponding BMS indicator characteristic data and PCS indicator characteristic data; Importing the BMS indicator characteristic data and the PCS indicator characteristic data into a preset operation warning analysis module respectively; The operation warning analysis module uses a pre-deployed operation warning analysis model to perform operation fault prediction on the BMS indicator characteristic data and the PCS indicator characteristic data, respectively, and outputs corresponding BMS operation fault prediction results and / or PCS operation fault prediction results.

[0048] In order to reduce the difficulty of system operation warning monitoring, the EMS system can set the corresponding operation indicator monitoring warning through the indicator data management module. For example, for the BMS of each energy storage node, the corresponding current, voltage, and temperature warning analysis indicators can be set. In this way, after the EMS collects the characteristic data of the BMS system of the corresponding energy storage node, the characteristic data can be filtered based on the set indicators to filter out other characteristic data and only retain the characteristic data under the set indicators to obtain the corresponding indicator characteristic data. Subsequently, the operation warning analysis module is used to perform indicator warning analysis on the indicator characteristic data using the machine learning model, and the characteristic data under the indicator is intelligently predicted, and the corresponding operation fault prediction results are output. If the indicator characteristic data is qualified, the operation fault prediction result is displayed as no fault; if the corresponding indicator characteristic data exceeds the threshold set by the system to trigger the operation warning fault, the model predicts and outputs the corresponding operation fault analysis results. The EMS system visualizes the operation fault prediction results that trigger the alarm on the panoramic platform to remind the administrator to perform operation warning analysis and troubleshooting on the EMS or PCS under the corresponding indicators.

[0049] Because the corresponding basic attributes are set in the early stage when building ETL, EMS can perform detailed analysis on the BMS and PCS of each node and display the system characteristic data of each node on the panoramic platform. It can locate and track based on the basic attribute information and trace faults.

[0050] Furthermore, the method for constructing the operation early warning analysis model comprises the following steps: Collecting a feature set includes: extracting BMS feature data from system data of the BMS through a BMS ETL template, extracting PCS feature data from system data of the PCS through the PCS ETL template, and constructing a feature set based on the BMS feature data and the PCS feature data; Divide the feature set into a training set and a validation set according to a preset ratio; Importing the training set into a preset machine learning model, respectively training and learning the characteristic relationship between the BMS characteristic data and the PCS characteristic data and the corresponding fault and alarm types, and generating the operation warning analysis model; The performance of the operation warning analysis model is verified using the verification set: If the verification is successful, the operation warning analysis model is deployed to the EMS; Otherwise, the feature data is re-extracted and the operation warning analysis model is optimized and trained.

[0051] Machine learning models can be: decision trees, random forests, support vector machines, neural networks, clustering algorithms, logistic regression, gradient boosting trees, deep learning models, ensemble learning, etc.

[0052] The training steps for the prediction model using the machine learning model can be as follows: 1. Data collection: Collect enough training data to ensure data diversity and cover a variety of situations.

[0053] 2. Data preprocessing: Normalization: Normalize the image pixel values ​​to between 0 and 1.

[0054] Data enhancement: Increase data diversity through rotation, scaling, cropping, etc.

[0055] Label Encoding: Convert the classification labels into One-Hot Encoding.

[0056] Feature engineering: This embodiment extracts the corresponding BMS feature data and PCS feature data through the ETL template, so the ETL template can continue to be used for feature engineering to collect the corresponding feature data set.

[0057] 3. Design training model architecture, such as CNN: Input layer: defines the shape of the input data.

[0058] Convolutional layer: Use filters of different sizes to extract features.

[0059] Activation function: ReLU activation function is usually used.

[0060] Pooling layer: Reduce feature dimensions and extract main features.

[0061] Fully connected layer: maps the extracted features to the final output.

[0062] Output layer: Define the number of neurons and activation function of the output layer according to the task.

[0063] 4. Compile the model: Choose a loss function: For example, for classification tasks, use cross entropy loss.

[0064] Choose an optimizer: such as Adam or SGD.

[0065] Define evaluation indicators: such as accuracy.

[0066] 5. Training Model: Divide the data set: Divide the data into training set, validation set and test set.

[0067] Set batch size and number of iterations: according to the amount of data and hardware capabilities.

[0068] Use callback functions: such as ModelCheckpoint and EarlyStopping.

[0069] 6. Evaluate the model: Evaluate model performance on the test set.

[0070] The evaluation was performed using indicators such as confusion matrix, precision, and recall.

[0071] 7. Model tuning: Hyperparameter tuning: Adjust learning rate, batch size, number of convolutional layers, etc.

[0072] Feature Engineering: Try different data preprocessing and augmentation methods.

[0073] Network structure adjustment: increase or decrease the number of neurons in the convolutional layer and the fully connected layer.

[0074] 8. Model deployment: Model saving: Save the trained model.

[0075] Model loading: loading the model in actual application (the present invention is to load the model file and install it on the EMS).

[0076] Prediction Interface: Create an API or integrate into your application for real-time predictions.

[0077] 9. Monitoring and maintenance: Continuously monitor model performance: Ensure that the model performs stably in real-world applications.

[0078] Update models regularly: Update models based on new data to maintain accuracy.

[0079] The above specific training process can be performed by an administrator, and the model verification can be verified by f1 or ROC curve.

[0080] Figure 2 The present invention is a block diagram of a panoramic operation early warning analysis system for EMS full life cycle management according to an exemplary embodiment. The system is used for a panoramic operation early warning analysis method for EMS full life cycle management. Figure 2 On the other hand, a panoramic operation warning analysis system for EMS full life cycle management is provided, and the panoramic operation warning analysis system for EMS full life cycle management is used to implement the panoramic operation warning analysis method for EMS full life cycle management described above, and the system includes: A plurality of energy storage nodes, wherein the energy storage nodes include a BMS and a PCS, and the BMS is configured with a BMS ETL template for extracting BMS feature data, and the PCS is configured with a PCS ETL template for extracting PCS feature data; EMS, used to manage each of the energy storage nodes of the energy storage power station, including: respectively building and configuring corresponding BMS ETL templates and PCS ETL templates for the BMS and PCS of each of the energy storage nodes, and performing panoramic operation early warning analysis on the BMS and PCS of each of the energy storage nodes based on the extracted BMS feature data and PCS feature data to achieve panoramic management; The EMS is deployed with: User center, used for users to log in to EMS and perform corresponding operations; Data processing system, used to provide CPU data processing services; A data acquisition module is used to perform sampling according to a preset sampling frequency, notify the BMS and PCS of each energy storage node to regularly extract the corresponding BMS characteristic data and the PCS characteristic data and feed them back to the EMS; An indicator data management module, for filtering the BMS characteristic data and the PCS characteristic data based on preset operation warning analysis indicators, respectively, to obtain corresponding BMS indicator characteristic data and PCS indicator characteristic data; and, for importing the BMS indicator characteristic data and the PCS indicator characteristic data into a preset operation warning analysis module respectively; An ETL management module is used to construct an ETL business execution template, including the BMS ETL template and the PCS ETL template, wherein the BMS ETL template is used to extract BMS feature data from the system data of the BMS, and the PCS ETL template is used to extract PCS feature data from the system data of the PCS; and the BMS ETL template and the PCS ETL template are respectively configured to the BMS and PCS of each energy storage node; An operation warning analysis module, used to use a pre-deployed operation warning analysis model to perform operation fault prediction on the BMS indicator characteristic data and the PCS indicator characteristic data, respectively, and output corresponding BMS operation fault prediction results and / or PCS operation fault prediction results; EMS panoramic platform, used for BMS and PCS panoramic operation analysis and early warning of each energy storage node; Database, for data storage; Component / software library, which is used to provide various components / software, including ETL tools and panoramic application software; The port service module is used to provide various data transmission and data communication ports.

[0081] Please understand the architecture and functional services of this system in conjunction with the description of the above methods and systems. I will not go into details here.

[0082] The component / software library, which contains installed components and software, such as ETL tool components, digital twin application software, or visual panoramic analysis systems, can be installed by administrator users.

[0083] The port service module provides various data interaction, transmission, and communication ports, such as USB, API, etc., providing port services for the EMS system.

[0084] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the electronic device may include the above Figure 2 The panoramic operation warning analysis system for EMS full life cycle management is shown. Optionally, the electronic device 410 may include a first processor 2001 .

[0085] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0086] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0087] Combine the following Figure 5 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0088] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0089] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 5 CPU0 and CPU1 are shown in FIG.

[0090] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 5 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits and / or processing cores for processing data (e.g., computer program instructions).

[0091] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0092] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0093] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0094] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0095] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0096] It should be noted that Figure 5 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0097] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the panoramic operation warning analysis method for EMS full life cycle management described in the above method embodiment, which will not be repeated here.

[0098] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0099] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0100] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0101] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0102] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0103] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0104] Those skilled 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 the present invention.

[0105] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0106] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the 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 device, 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 the system or unit, which can be electrical, mechanical or other forms.

[0107] 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.

[0108] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0109] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0110] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A panoramic operation early warning analysis method for EMS full life cycle management, implemented based on the panoramic operation early warning analysis system for EMS full life cycle management, It is characterized in that The panoramic operation warning analysis system based on EMS full life cycle management includes: A plurality of energy storage nodes, wherein the energy storage nodes include a BMS and a PCS, and the BMS is configured with a BMS ETL template for extracting BMS feature data, and the PCS is configured with a PCS ETL template for extracting PCS feature data; EMS, used to manage each of the energy storage nodes of the energy storage power station, including: respectively building and configuring corresponding BMS ETL templates and PCS ETL templates for the BMS and PCS of each of the energy storage nodes, and performing panoramic operation early warning analysis on the BMS and PCS of each of the energy storage nodes based on the extracted BMS feature data and PCS feature data to achieve panoramic management; The method comprises the following steps: S1. EMS builds an ETL business execution template based on the ETL structure, including the BMS ETL template and the PCS ETL template, wherein the BMS ETL template is used to extract BMS feature data from the system data of the BMS, and the PCS ETL template is used to extract PCS feature data from the system data of the PCS; S2. EMS configures the BMS ETL template and the PCS ETL template to the BMS and PCS of each energy storage node respectively; S3, the EMS performs sampling according to a preset sampling frequency, notifies the BMS and PCS of each energy storage node to regularly extract the corresponding BMS feature data and the PCS feature data and feeds them back to the EMS; S4. Based on preset indicators, EMS performs data analysis and early warning on the BMS characteristic data and the PCS characteristic data under various indicators, and displays the analysis and early warning results on the EMS panoramic platform for the front end to perform panoramic operation management.

2. According to the panoramic operation early warning analysis method for EMS full life cycle management according to claim 1, It is characterized in that S1. Based on the ETL structure, build an ETL business execution template, including: The administrator logs in to the EMS and configures the ETL execution context, including the data execution context between the EMS and the BMS, and the data execution context between the EMS and the PCS. The data execution context includes: data sampling requirements issued by the EMS to the BMS / PCS, the extraction format of the BMS / PCS feature data, data conversion requirements and data loading logic, and the storage address of the extracted BMS / PCS feature data in the EMS database; The ETL execution context is parsed through the ETL management module to obtain the ETL execution logic of the corresponding ETL execution context, including: the data execution logic between the EMS and the BMS, and the data execution logic between the EMS and the PCS; and based on the ETL execution logic, the corresponding BMS ETL template and the PCS ETL template are constructed; After the construction is completed, the ETL management module sends the BMS ETL template and the PCS ETL template to the EMS panoramic platform respectively to preview the templates and determine whether they can be put into storage: If the construction is correct, the BMS ETL template and the PCS ETL template are saved in the database; Otherwise, the ETL execution context is reconfigured, and the corresponding BMS ETL template and / or the PCS ETL template is reconstructed based on the above steps.

3. According to claim 2, the panoramic operation early warning analysis method for EMS full life cycle management, It is characterized in that The ETL execution logic includes the following application logic: operator dependency, life cycle and basic properties, where: The operator dependencies include: Supports the relevant encapsulation logic of operator parsing; External expression construction is required in operator parsing; The complex functions required for operator parsing are encapsulated in operator dependencies for easy use in operator parsing. The life cycle includes: The data set needs to be created / updated during the ETL execution process; Get input / output datasets; Check the output dataset; Inherited dataset; Run completion notification; Check if the input dataset is available; The basic attributes include: Provide the basic properties required for this ETL runtime, including operator network, version, BMS / PCS node information, domain, BMS / PCS energy storage node owner, priority setting, additional task parameters, and trigger path.

4. The panoramic operation early warning analysis method for EMS full life cycle management according to claim 1, It is characterized in that S4. Based on preset indicators, EMS performs data analysis and early warning on the BMS characteristic data and the PCS characteristic data under various indicators, including: Importing the BMS characteristic data and the PCS characteristic data into the index data management module of the EMS; The indicator data management module screens the BMS characteristic data and the PCS characteristic data based on the preset operation warning analysis indicators to obtain corresponding BMS indicator characteristic data and PCS indicator characteristic data; Importing the BMS indicator characteristic data and the PCS indicator characteristic data into a preset operation warning analysis module respectively; The operation warning analysis module uses a pre-deployed operation warning analysis model to perform operation fault prediction on the BMS indicator characteristic data and the PCS indicator characteristic data, respectively, and outputs corresponding BMS operation fault prediction results and / or PCS operation fault prediction results.

5. According to the panoramic operation early warning analysis method for EMS full life cycle management according to claim 4, It is characterized in that The method for constructing the operation early warning analysis model comprises the following steps: Collecting a feature set includes: extracting BMS feature data from system data of the BMS through a BMS ETL template, extracting PCS feature data from system data of the PCS through the PCS ETL template, and constructing a feature set based on the BMS feature data and the PCS feature data; Divide the feature set into a training set and a validation set according to a preset ratio; Importing the training set into a preset machine learning model, respectively training and learning the characteristic relationship between the BMS characteristic data and the PCS characteristic data and the corresponding fault and alarm types, and generating the operation warning analysis model; The performance of the operation warning analysis model is verified using the verification set: If the verification is successful, the operation warning analysis model is deployed to the EMS; Otherwise, the feature data is re-extracted and the operation warning analysis model is optimized and trained.

6. A panoramic operation warning analysis system for EMS full life cycle management, the panoramic operation warning analysis system for EMS full life cycle management is used to implement the panoramic operation warning analysis method for EMS full life cycle management as claimed in any one of claims 1 to 5, It is characterized in that The system comprises: A plurality of energy storage nodes, wherein the energy storage nodes include a BMS and a PCS, and the BMS is configured with a BMS ETL template for extracting BMS feature data, and the PCS is configured with a PCS ETL template for extracting PCS feature data; EMS, used to manage each of the energy storage nodes of the energy storage power station, including: respectively building and configuring corresponding BMS ETL templates and PCS ETL templates for the BMS and PCS of each of the energy storage nodes, and performing panoramic operation early warning analysis on the BMS and PCS of each of the energy storage nodes based on the extracted BMS feature data and PCS feature data to achieve panoramic management; The EMS is deployed with: User center, used for users to log in to EMS and perform corresponding operations; Data processing system, used to provide CPU data processing services; A data acquisition module is used to perform sampling according to a preset sampling frequency, notify the BMS and PCS of each energy storage node to regularly extract the corresponding BMS characteristic data and the PCS characteristic data and feed them back to the EMS; An indicator data management module, for filtering the BMS characteristic data and the PCS characteristic data based on preset operation warning analysis indicators, respectively, to obtain corresponding BMS indicator characteristic data and PCS indicator characteristic data; and, for importing the BMS indicator characteristic data and the PCS indicator characteristic data into a preset operation warning analysis module respectively; An ETL management module is used to construct an ETL business execution template, including the BMS ETL template and the PCS ETL template, wherein the BMS ETL template is used to extract BMS feature data from the system data of the BMS, and the PCS ETL template is used to extract PCS feature data from the system data of the PCS; and the BMS ETL template and the PCS ETL template are respectively configured to the BMS and PCS of each energy storage node; An operation warning analysis module, used to use a pre-deployed operation warning analysis model to perform operation fault prediction on the BMS indicator characteristic data and the PCS indicator characteristic data, respectively, and output corresponding BMS operation fault prediction results and / or PCS operation fault prediction results; EMS panoramic platform, used for BMS and PCS panoramic operation analysis and early warning of each energy storage node; Database, for data storage; Component / software library, which is used to provide various components / software, including ETL tools and panoramic application software; The port service module is used to provide various data transmission and data communication ports.

7. An electronic device, It is characterized in that The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 5.

Images