An EMS energy storage management system

Abstract

The application provides an EMS energy storage management system, and relates to the technical field of energy storage management. The application receives processed data information from the intelligent management module, performs frequency domain analysis on the input voltage and output current of the energy storage equipment, converts the time domain signals of the collected input voltage and output current into frequency domain signals through Fourier transform, extracts the amplitude value of the main frequency component and the amplitude value of each harmonic component, calculates the ripple factor of the input voltage and output current, selects the amplitude value of the main frequency component as the denominator, selects the sum of the amplitude values of the other harmonic components as the numerator, and calculates the ripple factor; the ripple factors of the input voltage and output current are weighted and averaged, or are calculated according to the system efficiency, so that the power distribution efficiency waveform ripple factor is obtained; the change trend of the VFDHF can be monitored in real time, and the operation strategy can be adjusted in time.

Description

TECHNICAL FIELD

[0001] The application relates to manufacturing of ground alternating current charging piles, underground alternating current charging piles and other power transmission and distribution and control devices, and more particularly to the technical field of energy storage management, and specifically relates to an EMS energy storage management system. BACKGROUND

[0002] An energy management system (EMS) is a key intelligent technology in the new energy storage industry, and mainly realizes safe and optimized scheduling of energy.

[0003] The energy storage management system is a software and hardware solution for collecting, monitoring, controlling, analyzing and optimizing the energy system through big data. The EMS is responsible for collecting real-time data of the energy storage unit, controlling and managing the cluster of energy storage devices through artificial intelligence (AI) algorithms and big data models, achieving the goals of power balance, peak clipping and valley filling, strategy management and the like, and guaranteeing the safe and stable operation of the energy storage power station. Meanwhile, it realizes efficient management and optimized configuration of energy through real-time monitoring and intelligent control of each link of energy production, distribution and consumption.

[0004] In the prior art, a document with the publication number CN117477728B and the name of an EMS energy storage management system is disclosed. The system includes an electric quantity monitoring module, a charging collection module, an electrical analysis module and an operation and maintenance management module. The electric quantity monitoring module is used to monitor the remaining electric quantity of the battery module in real time. When the remaining electric quantity is lower than a preset electric quantity threshold, a charging instruction is generated. When the battery module is in a charging state, the charging collection module is used to collect charging parameters of the battery module and transmit the charging parameters to the electrical analysis module for safety warning analysis to calculate a warning index and determine whether the battery module is in a dangerous state to improve power safety. The operation and maintenance management module is used to analyze a cruising deviation index according to cruising information with a time stamp stored in a database. If the cruising deviation index is greater than a preset protection threshold, a battery maintenance signal is generated to remind the management personnel to replace a new battery module, avoid safety accidents caused by battery aging and improve charging and discharging safety.

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The application aims to provide an EMS energy storage management system to solve the problems in the background.

[0007] To achieve the above-mentioned purpose, the application provides the following technical scheme.

[0008] An EMS energy storage management system comprises:

[0009] Intelligent management module: The intelligent management module integrates intelligent decision-making algorithms, which are used to analyze the operating data of energy storage equipment and formulate management strategies, and are also used for preprocessing and transmitting processed data information;

[0010] Energy optimization module: The energy optimization module is used to analyze the processed data information transmitted by the intelligent management module, that is, to perform frequency domain analysis on the input voltage and output current of the energy storage device, calculate the ripple factor, and obtain the ripple factor of the transmission and distribution efficiency waveform of the energy storage device;

[0011] Data Analysis Module: The data analysis module is responsible for in-depth analysis of the ripple factor of the transmission and distribution efficiency waveform; it uses machine learning algorithms to perform in-depth analysis of the ripple factor of the transmission and distribution efficiency waveform; it provides predictive analysis of the operating status and provides decision support.

[0012] Furthermore, it also includes a data acquisition module, a scalability module, and a user interface;

[0013] The data acquisition module is used to collect data information from the energy storage device, including the input voltage and output current of the energy storage device.

[0014] The scalability module achieves flexible scalability of the system through modular design, supporting the addition of energy storage devices or expansion of the operating environment as needed;

[0015] The user interface provides a user-friendly interface that displays the system's operating status and provides operation guidance through an intuitive user interface.

[0016] Furthermore, the data acquisition module preprocesses the acquired data information when it collects data information;

[0017] Data cleaning and noise reduction: removing noise and outliers from data.

[0018] Data normalization and standardization: converting data into a unified unit of measurement, that is, mapping data information to the range of 0 to 1;

[0019] Data dimensionality reduction and feature extraction: Extracting key features from high-dimensional data reduces data dimensionality and improves computational efficiency; reducing data dimensionality allows for the extraction of major variability and trend features; key features are extracted through machine learning algorithms.

[0020] Furthermore, the processed data information includes input voltage and output current, and frequency domain analysis is performed on the input voltage and output current;

[0021] The time-domain signals of the acquired input voltage and output current are converted into frequency-domain signals by Fourier transform.

[0022] The amplitude values ​​of the dominant frequency component and each harmonic component are extracted from the frequency domain signal, and the ripple factor is calculated using the amplitude values ​​of each harmonic component and the amplitude value of the dominant frequency component.

[0023] The ripple factor of the transmission and distribution efficiency waveform is obtained by weighted averaging of the input voltage and output current, or by calculating based on the system efficiency.

[0024] Furthermore, the energy optimization module performs the following analysis and processing steps:

[0025] Data acquisition: The input voltage and output current of the energy storage device are collected to ensure a sufficiently high sampling rate and avoid signal distortion;

[0026] Frequency domain analysis: Perform Fourier transform on the acquired input voltage and output current signals respectively to obtain their respective spectra, mark each harmonic component in the signal, and extract the amplitude value of the main frequency component and the amplitude value of each harmonic component.

[0027] Ripple factor calculation: Analyze the spectrum of the input voltage and output current to calculate their respective ripple factors; select the amplitude value of the main frequency component as the denominator and the sum of the amplitude values ​​of all other harmonic components as the numerator to calculate the ripple factor;

[0028] Transmission and distribution efficiency waveform ripple factor calculation: The ripple factor of the input voltage and output current is weighted and averaged, or calculated based on the system efficiency, to obtain VFDHF; the transmission and distribution efficiency of the energy storage system is evaluated by the VFDHF value. The lower the VFDHF value, the higher the transmission and distribution efficiency of the system, and the higher the VFDHF value, the lower the transmission and distribution efficiency of the system.

[0029] Furthermore, the data analysis module performs the following steps to extract features from the ripple factor of the transmission and distribution efficiency waveform:

[0030] Time series analysis was performed on the ripple factor of the transmission and distribution efficiency waveform to calculate the dynamic rate of change of the ripple factor.

[0031] Generate the curve of the ripple factor of the transmission and distribution efficiency waveform changing over time, and the fluctuation characteristics of the ripple factor of the transmission and distribution efficiency waveform.

[0032] The extracted fluctuation characteristics include period, amplitude, and frequency;

[0033] Anomaly detection algorithms are applied to identify abnormal fluctuations based on extracted fluctuation features, and to predict and identify abnormal states and operational statuses.

[0034] Furthermore, the steps for the intelligent management module to output management strategies are as follows:

[0035] Based on abnormal conditions or fault modes, generate intelligent management decision instructions to optimize the operation strategies of energy storage devices and systems;

[0036] Machine learning algorithms are used to optimize the operating status of energy storage devices and systems, generating optimal management strategies.

[0037] The intelligent management decision-making instructions are converted into actual control signals, and then the control signals are transmitted to the execution module through the communication module;

[0038] Control signals are sent to energy storage devices and systems to ensure stable execution of the control signals. The execution results are monitored in real time and fed back to the intelligent management module for evaluation and optimization. The system operation data is used to update the model and decision-making strategy.

[0039] Furthermore, the data acquisition module is electrically connected to the intelligent management module, the intelligent management module is electrically connected to the energy optimization module, the energy optimization module is electrically connected to the data analysis module, the data analysis module is electrically connected to the intelligent management module, and the intelligent management module is electrically connected to the scalability module and the user interface.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] This invention receives processed data from an intelligent management module and performs frequency domain analysis on the input voltage and output current of the energy storage device. It converts the time-domain signals of the acquired input voltage and output current into frequency-domain signals using Fourier transform. It extracts the amplitude values ​​of the dominant frequency component and each harmonic component. It calculates the ripple factor of the input voltage and output current, selecting the amplitude value of the dominant frequency component as the denominator and the sum of the amplitude values ​​of all other harmonic components as the numerator. Finally, it performs a weighted average of the ripple factors of the input voltage and output current, or calculates them based on system efficiency, to obtain the ripple factor of the transmission and distribution efficiency waveform.

[0042] The data analysis module is responsible for in-depth analysis of VFDHF; performing time series analysis on VFDHF and calculating the dynamic rate of change; generating VFDHF change curves over time and extracting fluctuation characteristics such as period, amplitude, and frequency; applying anomaly detection algorithms to identify abnormal fluctuations based on the extracted fluctuation characteristics and predict abnormal states and operating conditions; the intelligent management module integrates intelligent decision-making algorithms to analyze the operating data of energy storage devices and formulate management strategies; preprocessing and transmitting processed data information; generating intelligent management decision instructions based on abnormal states or fault modes to optimize the operating strategies of energy storage devices and systems; converting decision instructions into control signals and transmitting them to the execution module through the communication module; and monitoring the execution results in real time and feeding them back to the intelligent management module for evaluation and optimization;

[0043] The system, through its intelligent management module, can automatically analyze the operating data of energy storage devices and identify abnormal states or fault modes. Based on machine learning algorithms, it optimizes the operating status of energy storage devices and the system, generating optimal management strategies. The energy optimization module calculates VFDHF through frequency domain analysis to comprehensively evaluate the efficiency of the energy storage system. The data analysis module performs in-depth analysis of VFDHF, extracts dynamic fluctuation characteristics, and identifies abnormal states. By calculating and analyzing ripple factor and VFDHF, the system can evaluate the transmission and distribution efficiency of the energy storage system; the lower the VFDHF value, the higher the system's transmission and distribution efficiency; the higher the VFDHF value, the lower the system efficiency. The system can monitor the changing trend of VFDHF in real time and adjust the operating strategy in a timely manner to optimize efficiency. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the overall system structure of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0046] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0047] Example 1:

[0048] Please see Figure 1 The present invention provides a technical solution:

[0049] This invention relates to the manufacture of energy storage management systems, including ground-mounted AC and underground AC charging piles, as well as other power transmission, distribution, and control equipment; it provides an EMS energy storage management system, comprising:

[0050] Intelligent management module: The intelligent management module integrates intelligent decision-making algorithms, which are used to analyze the operating data of energy storage equipment and formulate management strategies, and are also used for preprocessing and transmitting processed data information;

[0051] Energy optimization module: The energy optimization module is used to analyze the processed data information transmitted by the intelligent management module, that is, to perform frequency domain analysis on the input voltage and output current of the energy storage device, calculate the ripple factor, and obtain the ripple factor of the transmission and distribution efficiency waveform of the energy storage device;

[0052] Data Analysis Module: The data analysis module is responsible for in-depth analysis of the ripple factor of the transmission and distribution efficiency waveform; it uses machine learning algorithms to perform in-depth analysis of the ripple factor of the transmission and distribution efficiency waveform; it provides predictive analysis of the operating status and provides decision support.

[0053] In this embodiment, preferably, it also includes a data acquisition module, a scalability module, and a user interface;

[0054] The data acquisition module is used to collect data information from the energy storage device, including the input voltage and output current of the energy storage device.

[0055] The scalability module achieves flexible scalability of the system through modular design, supporting the addition of energy storage devices or expansion of the operating environment as needed;

[0056] The user interface provides a user-friendly interface that displays the system's operating status and provides operation guidance.

[0057] It should be noted that the data acquisition module is responsible for collecting the input voltage and output current of the energy storage device, ensuring a sufficiently high sampling rate to avoid signal distortion. The user interface provides a user-friendly interface that displays the system's operating status and provides operation guidance, making it convenient for users to view and manage the system. The scalability module adopts a modular design, supporting system expansion by adding individual energy storage units. It provides flexible network connection interfaces for easy integration with other systems, facilitating system deployment and upgrades, adapting to different scenario requirements, and supporting long-term system availability and maintainability.

[0058] In this embodiment, preferably, the data acquisition module preprocesses the acquired data information when collecting data information;

[0059] Data cleaning and noise reduction: removing noise and outliers from data.

[0060] Data normalization and standardization: converting data into a unified unit of measurement, that is, mapping data information to the range of 0 to 1;

[0061] Data dimensionality reduction and feature extraction: Extracting key features from high-dimensional data, reducing data dimensionality, and improving computational efficiency; reducing data dimensionality and extracting the main variability and trend features; extracting key features through machine learning algorithms;

[0062] It should be noted that removing noise and outliers from the data ensures its accuracy and integrity; denoising and outlier removal ensures the data source is of high quality, avoiding misleading subsequent analysis and model training.

[0063] Denoising: Remove high-frequency or low-frequency noise from data using filters or waveform correction methods; eliminate electromagnetic interference or other noise using moving average filters or high-pass filters;

[0064] Outlier removal: Identify and remove outlier data points; use statistical analysis to find data points that deviate from the normal range and mark them as outliers for removal during subsequent processing;

[0065] Normalization and standardization processes can ensure that data from different devices or under different conditions are comparable, and avoid the impact of excessive data dimensionality on model training and inference.

[0066] Normalization: Mapping data to a fixed range, usually between 0 and 1; normalizing the effective value of voltage or current to the range of 0 to 1.

[0067] Standardization: In addition to normalization, it may be necessary to center or standardize the variance of the data to eliminate data bias or scale differences.

[0068] Extracting key features from high-dimensional data reduces data dimensionality and improves computational efficiency. After reducing data dimensionality, computational efficiency is significantly improved. At the same time, the extracted key features can better reflect the operating status of energy storage devices and systems, providing support for subsequent anomaly detection and fault diagnosis.

[0069] Dimensionality reduction: High-dimensional data is mapped to a low-dimensional space through dimensionality reduction techniques such as principal component analysis (PCA) and singular value decomposition (SVD).

[0070] Feature extraction: Combining machine learning algorithms, extract key features with variability and trends; extract features such as period, amplitude, and frequency, or extract dynamic change features of ripple factor (VFDHF).

[0071] In this embodiment, preferably, the processed data information includes input voltage and output current, and frequency domain analysis is performed on the input voltage and output current;

[0072] The time-domain signals of the acquired input voltage and output current are converted into frequency-domain signals by Fourier transform.

[0073] The amplitude values ​​of the dominant frequency component and each harmonic component are extracted from the frequency domain signal, and the ripple factor is calculated using the amplitude values ​​of each harmonic component and the amplitude value of the dominant frequency component.

[0074] The ripple factor of the transmission and distribution efficiency waveform is obtained by weighted averaging of the input voltage and output current, or by calculating based on the system efficiency.

[0075] It should be noted that Fourier transform is used to convert the time-domain signals of input voltage and output current into frequency-domain signals; through Fourier transform, the dominant frequency component and harmonic components in the signal can be extracted.

[0076] Amplitude of the dominant frequency component: Extract the amplitude of the dominant frequency component, which reflects the main energy component of the signal;

[0077] Amplitude values ​​of harmonic components: Extract the amplitude values ​​of each harmonic component, analyze the subharmonic components in the signal and their impact on system efficiency;

[0078] The energy optimization module achieves comprehensive evaluation and dynamic optimization of the energy storage system's transmission and distribution efficiency through Fourier transform and ripple factor calculation. By analyzing the frequency domain of the input voltage and output current, it extracts key features and calculates VFDHF, enabling real-time monitoring of the energy storage system's operating status and providing efficient management decision support. This not only enhances the system's intelligence level but also provides a scientific basis for the optimization and management of the energy storage system, ensuring its efficient and stable operation.

[0079] In this embodiment, preferably, the energy optimization module performs the analysis and processing steps as follows:

[0080] Data acquisition: The input voltage and output current of the energy storage device are collected to ensure a sufficiently high sampling rate and avoid signal distortion;

[0081] Frequency domain analysis: Perform Fourier transform on the acquired input voltage and output current signals respectively to obtain their respective spectra, mark each harmonic component in the signal, and extract the amplitude value of the main frequency component and the amplitude value of each harmonic component.

[0082] Ripple factor calculation: Analyze the spectrum of the input voltage and output current to calculate their respective ripple factors; select the amplitude value of the main frequency component as the denominator and the sum of the amplitude values ​​of all other harmonic components as the numerator to calculate the ripple factor;

[0083] Transmission and distribution efficiency waveform ripple factor calculation: The ripple factor of the input voltage and output current is weighted and averaged, or calculated based on the system efficiency, to obtain VFDHF; the transmission and distribution efficiency of the energy storage system is evaluated by the VFDHF value. The lower the VFDHF value, the higher the transmission and distribution efficiency of the system, and the higher the VFDHF value, the lower the transmission and distribution efficiency of the system.

[0084] It should be noted that the energy optimization module achieves comprehensive evaluation and dynamic optimization of the energy storage system's transmission and distribution efficiency through frequency domain analysis, ripple factor calculation, and VFDHF calculation of input voltage and output current data. By extracting frequency domain features through Fourier transform and calculating ripple factor and VFDHF, it can monitor the operating status of the energy storage system in real time and provide efficient management decision support. This not only improves the system's intelligence level but also provides a scientific basis for the optimization and management of the energy storage system, ensuring its efficient and stable operation.

[0085] Frequency domain feature extraction:

[0086] ;

[0087] in, Represented as the first The amplitude of each frequency component, This is represented by the corresponding weight value. This is expressed as the total amplitude of the frequency components;

[0088] Frequency domain feature weight calculation:

[0089] .

[0090] In this embodiment, preferably, the data analysis module performs the following steps to extract features from the ripple factor of the transmission and distribution efficiency waveform:

[0091] Time series analysis was performed on the ripple factor of the transmission and distribution efficiency waveform to calculate the dynamic rate of change of the ripple factor.

[0092] Generate the curve of the ripple factor of the transmission and distribution efficiency waveform changing over time, and the fluctuation characteristics of the ripple factor of the transmission and distribution efficiency waveform.

[0093] The extracted fluctuation characteristics include period, amplitude, and frequency;

[0094] Anomaly detection algorithms are applied to identify abnormal fluctuations based on extracted fluctuation features, and to predict and identify abnormal states and operational status.

[0095] It should be noted that the data analysis module achieves comprehensive monitoring and optimization of the energy storage system's operating status through time series analysis, fluctuation feature extraction, and anomaly detection of VFDHF. By extracting key features such as cycle, amplitude, and frequency, and combining them with anomaly detection algorithms, it can identify abnormal fluctuations and predict potential failure modes, providing decision support for the intelligent management module. This not only improves the system's intelligence level but also provides a reliable guarantee for the efficient operation of the energy storage system.

[0096] In this embodiment, preferably, the formula for calculating the ripple factor is as follows:

[0097] ;

[0098] in, Represented as the first The amplitude of each harmonic component This represents the amplitude of the main frequency component; Represented as an amplitude sequence of harmonic components. This represents the total number of amplitude sequences of harmonic components. Represented as ripple factor;

[0099] Formula for waveform ripple factor of transmission and distribution efficiency:

[0100] ;

[0101] in, Represented as the ripple factor of the transmission and distribution efficiency waveform. The ripple factor is expressed as the input voltage. The ripple factor is expressed as the output current.

[0102] The calculation formula for the anomaly detection algorithm is as follows:

[0103] ;

[0104] in, This is represented as an input feature vector, specifically a feature vector of period, amplitude, and frequency. The model is a trained classification or anomaly detection model. This is indicated as an abnormal state identification;

[0105] ,

[0106] ;

[0107] in, Represented as the center of the ellipsoid, This is represented as the input feature vector. Represented as the inverse matrix of the ellipsoidal covariance, Represented as an inverse matrix;

[0108] The ellipsoid equation describes a sphere centered at... The major axis and minor axis are formed by The determined ellipsoid is determined by substituting the feature vectors into the ellipsoid equation to determine whether the data lies inside the ellipsoid (normal data) or outside the ellipsoid (outliers); specifically:

[0109] Data points are located inside or on the surface of the ellipsoid: This indicates that the point falls within the normal data range.

[0110] Data points are outside the ellipsoid: This indicates that the point is an outlier.

[0111] It should be noted that frequency domain analysis is the process of converting time-domain signals (such as input voltage and output current) into frequency-domain signals. Commonly used methods include Fourier transform and fast Fourier transform (FFT).

[0112] ;

[0113] in, Represented as a time-domain signal, Represented as the total number of signal points. Represented as frequency, The kernel, represented as a Fourier transform, is used to transform time-domain signals. Convert to frequency domain signal In the Fourier transform, Used to extract individual frequency components from a signal, when introduced When, the expression becomes This is equivalent to performing a division operation within the frequency range; specifically:

[0114] when When =1, the expression becomes This is consistent with the standard Fourier transform;

[0115] when When >1, the expression This indicates the frequency A scaling factor was applied;

[0116] Another formula for the ripple factor of the transmission and distribution efficiency waveform:

[0117] ;

[0118] The energy conversion efficiency of a quantitative energy storage system is the ratio of system input power to output power.

[0119] ;

[0120] Wherein: Output power: The output power of the energy storage system, usually the energy stored or released;

[0121] Input power: The input power of an energy storage system is usually the energy absorbed from the power grid or other energy sources.

[0122] In this embodiment, preferably, the intelligent management module outputs the management strategy in the following steps:

[0123] Based on abnormal conditions or fault modes, generate intelligent management decision instructions to optimize the operation strategies of energy storage devices and systems;

[0124] Machine learning algorithms are used to optimize the operating status of energy storage devices and systems, generating optimal management strategies.

[0125] The intelligent management decision-making instructions are converted into actual control signals, and then the control signals are transmitted to the execution module through the communication module;

[0126] Control signals are sent to energy storage devices and systems to ensure stable execution of the control signals, and the execution results are monitored in real time and fed back to the intelligent management module for evaluation and optimization; the model and decision-making strategy are updated through system operation data;

[0127] It should be noted that the intelligent management module realizes intelligent management of energy storage devices and systems by generating management strategies, outputting control signals, transmitting signals, executing signals, and conducting real-time monitoring and optimization. By utilizing machine learning algorithms and dynamic optimization, it can adjust management strategies in real time according to changes in operating status, ensuring the efficient and stable operation of energy storage devices and systems. This not only improves the intelligence level of the system but also provides strong support for the optimization and management of energy storage systems, ensuring the long-term reliable operation of the system.

[0128] Anomaly detection formula based on VFDHF and frequency domain features:

[0129] ;

[0130] in, This is represented as an anomaly detection function, and its specific implementation is as follows:

[0131] Anomaly detection function for Autoencoder model:

[0132] ;

[0133] in: This is represented as the input VFDHF and frequency domain feature vector; Represented as model pairs The reconstructed image after compression; Represented as VFDHF and frequency domain feature vectors of the normal state in the training set; It is represented as the norm of a vector.

[0134] In this embodiment, preferably, the data acquisition module is electrically connected to the intelligent management module, the intelligent management module is electrically connected to the energy optimization module, the energy optimization module is electrically connected to the data analysis module, the data analysis module is electrically connected to the intelligent management module, and the intelligent management module is electrically connected to the scalability module and the user interface.

[0135] It should be noted that the electrical connection between modules involves multiple aspects such as communication protocols, data formats, power management, and circuit layout. Through reasonable electrical connection design, it is ensured that each module can work efficiently and reliably, realizing intelligent management and optimization of the energy storage system. It should also have good scalability and flexibility to adapt to possible future functional upgrades and module expansions. At the same time, the user interface design should be simple and intuitive to ensure that users can easily operate and monitor the system's operating status.

[0136] It should be noted that all calculation formulas in this application employ regression analysis, including but not limited to machine learning algorithms, to deeply analyze the collected parameters and identify their natural trends and interrelationships. Specialized software, such as Python's Scikit-learn library or the R language, is used to automatically generate mathematical models that match the data. Then, cross-validation and other methods are used to objectively evaluate the model performance, and continuous feedback and optimization are combined to ensure that the created formulas truly reflect the inherent laws of the data, thereby guaranteeing their effectiveness and accuracy. In all calculation formulas in this application, the parameters in each formula undergo dimensionless processing within a consistent range to ensure that different physical quantities are compared on the same scale; dimensionless processing techniques include, but are not limited to, Min-Max Normalization and Z-Score standardization.

[0137] The technical solution of this invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of this invention.

[0138] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

Claims

1. An EMS energy storage management system, characterized by, Comprise: Intelligent management module: the intelligent management module integrates intelligent decision algorithm, is used in analyzing the operation data of energy storage equipment and formulating management strategy, and also is used in preprocessing and transmission processing data information; Energy optimization module: the energy optimization module is used for analyzing the processing data information transmitted by the intelligent management module, that is, the input voltage and output current of the energy storage equipment are analyzed in frequency domain, the ripple factor is calculated, and the input voltage and output current are analyzed in frequency domain; The time domain signals of the collected input voltage and output current are converted into frequency domain signals by Fourier transform; The amplitude value of the main frequency component and the amplitude value of each harmonic component are extracted from the frequency domain signal, and the ripple factor is calculated by the amplitude value of each harmonic component and the amplitude value of the main frequency component; The ripple factors of the input voltage and output current are weighted and averaged, or calculated according to the system efficiency, to obtain the ripple factor of the input voltage and output current; Data analysis module: the data analysis module is responsible for deep analysis of the ripple factor of the input voltage and output current; machine learning algorithm is adopted to analyze the ripple factor of the input voltage and output current; predictive analysis of running state is provided, and decision support is provided.

2. An EMS energy storage management system according to claim 1, characterized in that: Also includes data acquisition module, scalability module and user interaction interface; The data acquisition module is used for collecting data information of the energy storage equipment, and the collected data information includes the input voltage and output current of the energy storage equipment; The scalability module realizes flexible scalability of the system through modular design, and supports adding energy storage equipment or expanding running environment on demand; The user interaction interface provides a friendly human-computer interaction interface, displays the running state of the system through an intuitive user interface, and provides operation guidance.

3. An EMS energy storage management system according to claim 2, wherein: The data acquisition module pre-processes the collected data information when collecting data information; Data cleaning and denoising: remove noise and outliers from data information; Data normalization and standardization: convert data to a unified dimension, that is, map data information in the range of 0 to 1; Data dimension reduction and feature extraction: extract key features from high-dimensional data, reduce data dimension, and improve computing efficiency; reduce data dimension, extract main variability and trend characteristics; Extract key features through machine learning algorithm.

4. The EMS energy storage management system of claim 1, wherein: The steps of analysis and processing of the energy optimization module are as follows: Data acquisition: collect the input voltage and output current of the energy storage equipment, ensure that the sampling rate is high enough, and avoid signal distortion; Frequency domain analysis: Fourier transform is performed on the collected input voltage and output current signals respectively to obtain their respective frequency spectra, mark each harmonic component in the signal, and extract the amplitude value of the main frequency component and the amplitude value of each harmonic component; Ripple factor calculation: analyze the frequency spectrum of the input voltage and output current, and calculate the ripple factor of each; Select the amplitude value of the main frequency component as the denominator, and the sum of the amplitude values of the other harmonic components as the numerator to calculate the ripple factor; The input voltage and output current ripple factors are weighted and averaged, or calculated according to the system efficiency, to obtain the VFDHF; the VFDHF value is used to evaluate the transmission and distribution efficiency of the energy storage system, the lower the VFDHF value, the higher the transmission and distribution efficiency of the system, and the higher the VFDHF value, the lower the transmission and distribution efficiency of the system.

5. The EMS energy storage management system of claim 1, wherein: The data analysis module extracts the features of the transmission and distribution efficiency waveform ripple factor as follows: Time series analysis of the transmission and distribution efficiency waveform ripple factor is performed to calculate the dynamic change rate of the transmission and distribution efficiency waveform ripple factor; A curve of the transmission and distribution efficiency waveform ripple factor over time is generated, and the fluctuation characteristics of the transmission and distribution efficiency waveform ripple factor are obtained; The extracted fluctuation characteristics include period, amplitude and frequency; Anomaly detection algorithm is applied to identify abnormal fluctuations of the extracted fluctuation characteristics, and to predict abnormal state identification and operating state.

6. An EMS energy storage management system according to claim 3, wherein: The intelligent management module outputs the management strategy as follows: According to the abnormal state or fault mode, an intelligent management decision instruction is generated to optimize the operation strategy of the energy storage device and system; Machine learning algorithm is used to optimize the operating state of the energy storage device and system to generate the optimal management strategy; The intelligent management decision instruction is converted into an actual control signal, which is then transmitted to the execution module through the communication module; The control signal is sent to the energy storage device and system to realize stable execution of the control signal, and the execution result is monitored in real time and fed back to the intelligent management module for evaluation and optimization; the model and decision strategy are updated through system operation data.

7. An EMS energy storage management system according to claim 6, wherein: The data collection module is electrically connected to the intelligent management module, the intelligent management module is electrically connected to the energy optimization module, the energy optimization module is electrically connected to the data analysis module, the data analysis module is electrically connected to the intelligent management module, and the intelligent management module is electrically connected to the expandability module and the user interaction interface.

Images