Energy storage power station operation monitoring and management system and method

Abstract

The present invention relates to the technical field of electric energy storage systems, and in particular to an energy storage power station operation monitoring and management system and method. The method comprises the following steps: obtaining voltage data of each energy storage node in a static state, and performing periodic voltage sampling within a preset static time, thereby obtaining voltage rebound time series data; performing temperature correction processing on the voltage rebound time series data, thereby obtaining standardized voltage rebound characteristic data; obtaining charge state data of each energy storage node before and after operation; calculating the charge and discharge depth change value of each node based on the charge state data; constructing a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth change value, and obtaining node aging differentiation parameters. The present invention constructs a node charge and discharge power allocation model based on the node aging differentiation parameters, realizes differentiated management of energy storage nodes in different states, and avoids the problem of further expansion of the aging degree between nodes in traditional methods.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy storage systems, and in particular to an energy storage power station operation monitoring and management system and method. Background Art

[0002] Energy storage power station operation monitoring and management is a core technology for ensuring the safe, efficient, and stable operation of energy storage systems. It aims to achieve optimal performance and economic benefits through real-time monitoring, intelligent scheduling, and scientific management. Its core architecture includes data acquisition, communication transmission, an energy management system (EMS), a power conversion system (PCS), a thermal management system, a monitoring platform, and cloud services. First, sensors collect key battery parameters such as voltage, current, SOC (state of charge), SOH (state of health), and temperature in real time. These data are transmitted to the monitoring system using data loggers and communication networks (such as Industrial Ethernet and wireless communications). As the core of operational management, the energy management system dynamically adjusts the energy storage system's charging and discharging strategies through real-time monitoring, status assessment, fault diagnosis, and optimized scheduling to ensure efficiency and safety. For example, the EMS can formulate charging and discharging plans based on electricity price fluctuations, load demand, and renewable energy generation, enabling peak load shifting or participation in electricity market transactions. The PCS, meanwhile, is responsible for energy conversion between the energy storage power station and the grid or loads, improving power quality by optimizing the power factor and rapidly responding to grid fluctuations. Thermal management systems monitor temperature in real time and regulate heat dissipation to prevent battery overheating or overcooling, thereby extending equipment life. However, traditional energy storage power plants typically employ a unified power allocation strategy, evenly distributing energy storage tasks across all energy storage nodes. This approach ignores the varying degrees of aging experienced by different energy storage nodes during actual use, leading to widening performance differences between nodes within a battery pack. Over extended operating time, significant differences in capacity decay, internal resistance changes, and responsiveness emerge between energy storage nodes, and traditional methods are unable to precisely manage these variations. Previous energy storage power plant management systems primarily assessed the status of energy storage nodes through simple voltage monitoring, lacking in-depth analysis of the crucial parameter of voltage rebound characteristics. Voltage rebound is a key indicator of battery node health, but traditional methods often overlook the impact of factors such as temperature and charge / discharge history on the voltage rebound process. This results in inaccurate health assessments and an inability to accurately reflect the true degree of aging at each node. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide an energy storage power station operation monitoring and management system and method to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a method for monitoring and managing the operation of an energy storage power station includes the following steps:

[0005] Step S1: Obtaining voltage data of each energy storage node in a static state, and performing periodic voltage sampling during a preset static time to obtain voltage rebound time series data; performing temperature correction processing on the voltage rebound time series data to obtain standardized voltage rebound characteristic data;

[0006] Step S2: Obtain the state of charge data of each energy storage node before and after operation; calculate the charge and discharge depth change value of each node based on the state of charge data; construct a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth change value to obtain the node aging differentiation parameter;

[0007] Step S3: Determine the available capacity level of each node based on the node aging differentiation parameter; calculate the optimal working range of each node based on the available capacity level to obtain node operation capability classification data; and establish a node charge and discharge power allocation model using the node operation capability classification data;

[0008] Step S4: Obtaining the overall power dispatch instruction of the energy storage power station; decomposing the overall power dispatch instruction according to the node charging and discharging power allocation model to obtain a node differentiated power allocation scheme; dynamically optimizing the node differentiated power allocation scheme using the minimum power perturbation method to obtain an adaptive energy flow allocation instruction;

[0009] Step S5: Send adaptive energy flow allocation instructions to each energy storage node and monitor the real-time operating status of each node after executing the adaptive energy flow allocation instructions; update the node aging differentiation parameters based on the real-time operating status to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

[0010] The present invention further provides an energy storage power station operation monitoring and management system for executing the above-mentioned energy storage power station operation monitoring and management method, the energy storage power station operation monitoring and management system comprising:

[0011] The voltage characteristic acquisition module is used to obtain the voltage data of each energy storage node in the static state and perform periodic voltage sampling during the preset static time to obtain voltage rebound time series data; the voltage rebound time series data is temperature corrected to obtain standardized voltage rebound characteristic data;

[0012] The health status assessment module is used to obtain the state of charge data of each energy storage node before and after operation; calculate the charge and discharge depth change value of each node based on the state of charge data; construct a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth change value, and obtain the node aging differentiation parameters;

[0013] The capacity grading and allocation module is used to determine the available capacity level of each node based on the node aging differentiation parameters; calculate the optimal working range of each node based on the available capacity level to obtain node operation capacity grading data; and use the node operation capacity grading data to establish a node charging and discharging power allocation model;

[0014] The energy flow intelligent allocation module is used to obtain the overall power dispatch instructions of the energy storage power station; the overall power dispatch instructions are decomposed and processed according to the node charging and discharging power allocation model to obtain the node differentiated power allocation plan; the node differentiated power allocation plan is dynamically optimized using the minimum power perturbation method to obtain the adaptive energy flow allocation instructions;

[0015] The closed-loop monitoring and optimization module is used to issue adaptive energy flow allocation instructions to each energy storage node and monitor the real-time operating status of each node after executing the adaptive energy flow allocation instructions. Based on the real-time operating status, the node aging differentiation parameters are updated to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

[0016] The present invention achieves efficient, reliable, and safe operation of the energy storage system through refined power allocation and dynamic state monitoring. First, based on an in-depth analysis of node operating capabilities and charge-discharge efficiency, the method rationally allocates basic power weights and scheduling priorities for each energy storage node, ensuring that nodes of varying performance can reach their maximum potential and avoiding resource waste and system imbalances caused by node performance differences. This scheduling interval design, based on node efficiency curves and safe operating ranges, not only improves the overall system's energy conversion efficiency, but also extends the service life of node devices and reduces losses and failure risks caused by overload or improper operating conditions. Second, a dynamic adjustment mechanism based on the node's real-time state of charge and temperature changes enables flexible adjustment of power allocation during actual operation to adapt to node state fluctuations and external environmental changes. For example, linear attenuation adjustment is implemented based on the ratio of the state of charge to the priority scheduling interval boundary, effectively preventing performance degradation caused by nodes frequently entering and exiting extreme operating ranges. Furthermore, the introduction of a temperature correction factor enables real-time response to node temperature anomalies, reducing power output to ensure node operation within a safe temperature range, avoiding thermal runaway and further improving system safety and stability. The comprehensive adjustment of these multi-dimensional parameters significantly enhances the adaptability and self-protection capabilities of energy storage power plants. Furthermore, the analysis of power scheduling parameters and the application of node power allocation models enable the scientific determination of preliminary power allocation and constraints for energy storage nodes, ensuring that each node's power output is within its safe carrying capacity and avoiding overload risks. Adjusting the deviation between the node's state of charge and the optimal operating range makes the power allocation plan more balanced, improving the overall system load balance, reducing pressure fluctuations at local nodes, and effectively preventing accelerated battery capacity degradation and local overheating caused by unbalanced scheduling. Furthermore, dynamic temperature monitoring and risk factor adjustment mechanisms provide adaptive power allocation, enabling timely optimization of power output based on real-time node temperature changes, improving system operational flexibility and responsiveness. Setting a minimum step size for power perturbations and generating multiple perturbation plans enable the system to meticulously analyze node sensitivity to power changes, accurately identify slow-responding nodes, and achieve optimal power response through priority adjustment and iterative optimization. This process ensures that energy storage power stations can quickly and stably adjust their output in the face of external power demand fluctuations, reducing system oscillations and response lags, and improving scheduling accuracy and efficiency. The generation and execution of adaptive energy flow allocation instructions enables energy storage nodes to efficiently collaborate according to the optimal solution, enhancing the dynamic regulation capabilities and load response speed of the entire energy storage system. This is suitable for scenarios with large fluctuations in renewable energy generation, such as wind and photovoltaic power generation, to smooth power regulation.Real-time operational status monitoring and online analysis, combined with high-frequency sampling and dynamic evaluation of voltage, current, temperature, and state of charge, can capture node performance changes in real time, promptly reflecting key indicators such as power response delay, voltage fluctuation, and temperature change rate, providing a scientific basis for system operation. Dynamic updating of aging parameters based on a sliding time window ensures the timeliness and accuracy of node health assessments, effectively capturing trends in node performance degradation and guiding subsequent maintenance and scheduling decisions. Combined with closed-loop calibration of health models, energy storage power plants can precisely manage node health, minimize failure risks, extend equipment life, and improve the economic and stable operation of the system. Overall, this approach enables multi-dimensional, dynamic, and intelligent operational monitoring and power allocation for energy storage power plants. While meeting external power dispatch requirements, it fully considers the internal status and aging of nodes, ensuring safe, stable operation and efficient energy utilization. Its flexibility and adaptability enable energy storage power plants to adapt to complex and changing grid environments, effectively supporting large-scale integration of renewable energy and grid peak-shaving demands, improving the reliability and economic efficiency of grid operations, and providing solid technical support for the widespread application of energy storage technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0018] Figure 1 This is a schematic flow chart of the steps of a method for monitoring and managing the operation of an energy storage power station according to the present invention;

[0019] Figure 2 for Figure 1 Detailed step flow chart of step S1 in FIG. DETAILED DESCRIPTION

[0020] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0021] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0022] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0023] To achieve this, please refer to Figures 1 to 2 The present invention provides a method for monitoring and managing the operation of an energy storage power station, the method comprising the following steps:

[0024] Step S1: Obtaining voltage data of each energy storage node in a static state, and performing periodic voltage sampling during a preset static time to obtain voltage rebound time series data; performing temperature correction processing on the voltage rebound time series data to obtain standardized voltage rebound characteristic data;

[0025] During the pre-operational quiescent phase of the energy storage power station, the control system of this embodiment first issues a quiescent control command to all energy storage nodes (e.g., a battery cluster composed of lithium iron phosphate cells). This allows each node to stabilize for at least 30 minutes (this preset quiescent time can be set between 15 and 60 minutes depending on the battery type) without external charge or discharge disturbances. During this quiescent period, the terminal voltage of each node is periodically sampled at a 1Hz frequency for 5 minutes to obtain time series data on the natural voltage rebound over time. Voltage rebound refers to the physical process in which the voltage gradually rebounds after a battery stops charging or discharging due to the rebalancing of internal ion concentrations. The shape of the voltage rebound curve is related to the internal health of the battery. Subsequently, the corresponding temperature values ​​are recorded using the temperature sensors installed on the nodes. The time series data is normalized based on temperature. For example, using a standard temperature of 25°C as a reference, the voltage rebound curves at different temperatures are adjusted to the equivalent curve at 25°C using a temperature correction factor. This removes the influence of ambient temperature on the voltage rebound characteristics and produces standardized voltage rebound characteristic data for each node.

[0026] Step S2: Obtain the state of charge data of each energy storage node before and after operation; calculate the charge and discharge depth change value of each node based on the state of charge data; construct a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth change value to obtain the node aging differentiation parameter;

[0027] When the energy storage power station is preparing to start the operation task, the embodiment of the present invention collects the initial state of charge (SOC) data of each node, which is usually expressed as a percentage between 0% and 100%. Combined with the termination SOC data collected again after the operation is completed, the charge and discharge depth change value of the current charge and discharge process is calculated by the difference between the two SOCs. In order to improve the accuracy of the assessment, the SOC acquisition accuracy is set to ±0.5%. Then, the standardized voltage rebound characteristic data and the charge and discharge depth change value are input into the constructed node health status assessment model. The model is based on a decision tree regression algorithm and is trained with multiple rounds of historical operation data. It can output the aging differentiation parameter of each energy storage node. The parameter comprehensively reflects the aging characteristics of the node such as capacity attenuation, internal resistance growth and thermal stability degradation. It is usually expressed as a decimal between 0 and 1. The larger the value, the higher the degree of aging. The aging differentiation parameter will serve as the core input basis for subsequent energy management optimization.

[0028] Step S3: Determine the available capacity level of each node based on the node aging differentiation parameter; calculate the optimal working range of each node based on the available capacity level to obtain node operation capability classification data; and establish a node charge and discharge power allocation model using the node operation capability classification data;

[0029] The embodiment of the present invention divides each node into three available capacity levels: high, medium, and low, based on the aging differentiation parameter. For example, the aging differentiation parameter is set to be less than 0.3 as a high capacity level, between 0.3 and 0.7 as a medium capacity level, and above 0.7 as a low capacity level. Then, the typical safe operating voltage range and temperature rise curve of each node are analyzed in combination with the latest three operating data of each node to determine its optimal operating range. For example, the high-capacity level node can be set to the SOC range of 10% to 90%, the medium-level node is set to 15% to 85%, and the low-capacity level node is limited to 20% to 80%, thereby forming the node operation capacity classification data. Next, the operation capacity classification data is used to construct a node charge and discharge power allocation model. The model is designed by constrained optimization. The total power required by the power station and the node operation capacity level data are input, and a set of single-node power allocation sets that are achievable and meet the node capacity constraints are output for subsequent power scheduling. The model has the ability to flexibly adjust and can automatically update its power upper and lower limits according to changes in node health.

[0030] Step S4: Obtaining the overall power dispatch instruction of the energy storage power station; decomposing the overall power dispatch instruction according to the node charging and discharging power allocation model to obtain a node differentiated power allocation scheme; dynamically optimizing the node differentiated power allocation scheme using the minimum power perturbation method to obtain an adaptive energy flow allocation instruction;

[0031] In this embodiment of the present invention, when the grid dispatch center issues an overall power dispatch instruction to the energy storage power station (for example, in a daily load regulation scenario, issuing a control task to "output 10MW of electricity for one hour"), the system invokes the aforementioned charge and discharge power allocation model to decompose the dispatch task and obtain differentiated power allocation solutions that meet the available capacity and health level constraints of each node. For example, the 10MW task can be allocated to node A outputting 2.5MW, node B outputting 1.8MW, and node C outputting 0.7MW. Then, to further reduce node load fluctuations, the minimum power perturbation method is applied for dynamic optimization. The core of this method is to minimize the change between the current allocated power and the power at the previous moment as the objective function, ensuring that the thermal and electrical stress caused by power changes on the nodes is minimized, thereby extending the node lifespan. After iterative optimization and solution, the adaptive energy flow distribution instructions used to control each node are finally obtained. Each instruction contains parameters such as target power, current direction, and safe voltage lower limit.

[0032] Step S5: Send adaptive energy flow allocation instructions to each energy storage node and monitor the real-time operating status of each node after executing the adaptive energy flow allocation instructions; update the node aging differentiation parameters based on the real-time operating status to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

[0033] This embodiment of the present invention sends adaptive energy flow allocation instructions via the station control system to the battery management system (BMS) and power management unit (PCS) of the corresponding energy storage node. The instructions are updated every 30 seconds to ensure the system's ability to respond to real-time fluctuations. Subsequently, the system continuously monitors the node's real-time operating status data, including key indicators such as current, voltage, temperature, and SOC change rate. If a node experiences an abnormality during operation (such as a rapid temperature rise or output power deviating from a preset value by more than 5%), the system immediately records the anomaly and marks the node as an abnormal operating status node. After each complete power scheduling cycle, the system updates the aging differentiation parameters based on the actual performance data of the node in that cycle and uses a sliding window approach to reweight its historical values, achieving a dynamic closed-loop aging identification mechanism. This process is repeated within each operating cycle, implementing a closed-loop operation monitoring and management mechanism for the energy storage power station, from node health monitoring and capacity assessment to dynamic optimization scheduling and feedback correction. This significantly improves system scheduling efficiency and node lifespan in typical peak shaving and valley filling scenarios.

[0034] Preferably, step S1 includes the following steps:

[0035] Step S11: determining a rest time parameter according to pre-acquired cell model characteristics of each energy storage node, thereby obtaining rest time configuration data;

[0036] In the initial stage of deployment of the energy storage power station according to the embodiment of the present invention, the system management module will preset the battery cell model information of each energy storage node. For example, node A uses lithium iron phosphate model IFR-32700, and node B uses ternary lithium NCM-622. The rest time parameters are obtained by querying the static characteristic technical data sheet provided by the corresponding battery cell manufacturer. Rest time refers to the time required for the internal electrochemical reaction of the battery to tend to equilibrium and the surface voltage to stabilize after the battery stops charging and discharging. It generally depends on its electrochemical system, cycle life status and temperature sensitivity. Taking lithium iron phosphate as an example, the recommended rest time is 30 minutes, while the ternary lithium model is generally 20 minutes due to its high activity and fast recovery. For the convenience of management, the system sets the rest time configuration data according to the battery cell model classification, and stores the results in the operation management database in the form of a structured configuration table for subsequent rest control.

[0037] Step S12: Controlling the energy storage node to enter a rest mode according to the rest time configuration data, interrupting all charging and discharging operations, and obtaining a node rest state confirmation signal;

[0038] In this embodiment of the present invention, based on the quiescent time configuration data generated in the previous step, the system scheduling module sends an "enter quiescent mode" control instruction to all energy storage nodes through the energy storage management system (EMS). This instruction contains specific quiescent duration parameters and forcibly interrupts all current charging and discharging tasks of the node. The interruption operation controls the current to zero through the PCS module and disconnects the relay connected to the bus, thereby achieving electrical isolation. In actual scenarios, to ensure that the instructions are executed correctly, the system needs to monitor the BMS status return signal of each node. If the node returns "current no-load current, voltage curve stabilizes, and control relay is disconnected" and all three conditions are met, it is determined that the node has entered the quiescent state and generates a node quiescent state confirmation signal. The confirmation signals of all nodes are aggregated by the station control host and used as the trigger condition for starting the subsequent data collection process.

[0039] Step S13: After receiving the node static state confirmation signal, start the periodic voltage sampling process to record the voltage changes of each energy storage node based on the preset sampling frequency to obtain the original voltage time series sampling data;

[0040] In an embodiment of the present invention, when the system receives a static state confirmation signal from all energy storage nodes, it immediately starts a periodic voltage sampling program. This program is controlled by a data acquisition unit (DAQ) via a CAN bus or Modbus interface to control the node BMS module to record the node terminal voltage in real time at a frequency of 1 Hz (i.e., once per second). The duration of the sampling process is consistent with the corresponding static time. For example, the lithium iron phosphate node is sampled for 30 minutes, resulting in a total of 1,800 voltage sampling points. The terminal voltage is the DC voltage value between the positive and negative poles of the battery and is a direct indicator for evaluating its static rebound process. The collected raw voltage data is automatically arranged according to the timestamp to form the raw voltage time series sampling data, which is uploaded to the data processing module for standby use.

[0041] Step S14: performing time series arrangement and preliminary screening on the original voltage time series sampling data, removing abnormal data points, and forming voltage rebound time series data;

[0042] To improve data validity, the system of the embodiment of the present invention preprocesses the raw voltage time series sampling data. First, it sorts by timestamp to ensure consistent data intervals; then, it uses the three-point sliding average method to smooth the curve to eliminate small measurement noise; and then it removes abnormal points, mainly for sudden changes in voltage values ​​caused by sampling errors and BMS power failures. The abnormal point identification method is based on the local outlier factor (LOF) algorithm, which detects the discreteness of the data point and the previous and next points to identify and automatically remove abnormal values. After the processing is completed, stable and continuous voltage rebound time series data is formed. This data reflects the curve change of the natural recovery of the voltage after the energy storage node stops working, usually showing an upward trend that is fast at first and then slow, and is an important representation of health indicators such as battery internal resistance and electrolyte diffusion rate.

[0043] Step S15: performing temperature correction processing on the voltage rebound time series data to obtain standardized voltage rebound characteristic data.

[0044] After obtaining voltage rebound time-series data, the system in this embodiment of the present invention incorporates a temperature correction processing module to eliminate the impact of ambient temperature variations. Because battery voltage rebound is extremely sensitive to temperature, especially in low-temperature environments, slowed ion diffusion can cause a lag in the rebound curve, impacting the accuracy of health assessments. The temperature correction method first uses the node temperature sensor to collect the average ambient temperature during the static period. This temperature is then compared with a standard temperature (typically 25°C) and a voltage correction coefficient is calculated based on a temperature sensitivity function. This correction coefficient, derived from extensive experiments, reflects the average offset in voltage response per unit temperature change. The system adjusts the voltage value at each time point based on this coefficient, ultimately generating standardized voltage rebound characteristic data equivalent to 25°C. This data, used as one of the input features for the subsequent health assessment model, significantly improves the accuracy and stability of node aging status assessments.

[0045] It is particularly important that step S15 includes the following steps:

[0046] Step S151: acquiring surface and ambient temperature data of each energy storage node, and calculating the deviation between the temperature and the standard test condition based on the surface and ambient temperature data of each energy storage node, thereby obtaining a temperature correction coefficient;

[0047] Before completing the generation of standardized voltage rebound characteristic data, the embodiment of the present invention requires the system to correct for temperature variables that affect the accuracy of the voltage rebound curve. To this end, the BMS submodule installed in the energy storage node integrates two types of temperature sensors: one type is attached to the surface of the battery module housing to obtain node surface temperature data in real time; the other type is installed on the inner wall of the battery compartment or the air conditioning return vent to collect the ambient temperature of the node. The system periodically reads these sensor data and aggregates them by node. For example, when node A has a surface temperature of 28.5°C and an ambient temperature of 27.2°C during static operation, the system calculates the node's comprehensive operating temperature as the weighted average of its surface and ambient temperatures. The standard test condition is usually set at 25°C, and the system calculates the temperature deviation value for each node, which is the current node temperature minus the standard temperature value. To quantify the impact of this deviation on the voltage rebound process, the system has a built-in temperature impact model. This model is trained using a large amount of experimental data and can output a voltage rebound correction coefficient corresponding to the temperature deviation. For example, for a certain type of lithium iron phosphate battery cell, its rebound amplitude increases by an average of 2 millivolts for every 1°C increase in temperature. When the temperature deviation is +3.5°C, its temperature correction coefficient is +7 millivolts. The correction coefficients of all nodes are stored as a temperature correction coefficient dataset.

[0048] Step S152: Correcting the voltage rebound time series data according to the temperature correction coefficient to eliminate the interference of temperature on the voltage rebound process, and obtaining a normalized voltage rebound curve;

[0049] The embodiment of the present invention performs point-by-point correction on the original voltage rebound time series data according to the temperature correction coefficient obtained in the previous step, and the correction process is executed by the data correction engine. The specific method is to add the reverse offset value of the temperature correction coefficient to the original voltage value sampled at each time point, thereby eliminating the influence of temperature on the voltage reading. For example, at a certain moment, the sampled voltage of node A is 3.314 volts, and the temperature correction coefficient is +7 millivolts, then the system corrects the voltage value at this point to 3.307 volts. This operation is performed in the entire interval of the rebound curve to ensure that the voltage recovery process is presented at the assumed standard temperature. It is worth noting that the correction coefficient curve in different temperature intervals is not linear, and the system uses piecewise linear fitting or cubic spline interpolation to ensure the continuity and accuracy of the temperature correction coefficient. After the processing is completed, the normalized voltage rebound curve generated by the system is a standard rebound curve that eliminates the temperature interference factor and can truly reflect the electrochemical recovery process of the node. This curve will serve as the basis for feature extraction.

[0050] Step S153: extracting characteristic points from the normalized voltage rebound curve to obtain a voltage rebound characteristic parameter set including an initial voltage value, a stable voltage value, and a rebound rate coefficient;

[0051] In this embodiment of the present invention, the system extracts key rebound characteristic parameters from the normalized voltage rebound curve using a feature extraction module. First, the system identifies the initial voltage value corresponding to the curve's starting point. This point typically occurs at 0 seconds after the start of the static state, reflecting the battery's voltage level immediately after charging or discharging stops. Next, the system identifies the stable segment at the end of the curve, selecting the time period within the last 60 seconds where the voltage change is less than 0.5 millivolts, and taking the average value of this segment as the stable voltage value. Finally, the rebound rate coefficient (the slope of the voltage rebound per unit time) is calculated. This is typically estimated using the slope of a linear fit within the first 300 seconds of the curve. For example, node A has an initial voltage of 3.307 volts, a stable voltage of 3.332 volts, and a voltage rebound of 0.021 volts within 300 seconds, corresponding to a rate of 70 microvolts per second. These three parameters together constitute the voltage rebound characteristic parameter set for the node's current static rebound characteristics, represented as a triplet of "initial voltage value + stable voltage value + rebound rate." This is structured and stored for use in standardization and health modeling.

[0052] Step S154: performing data standardization processing according to the voltage rebound characteristic parameter set and a preset cell characteristic reference library to obtain standardized voltage rebound characteristic data.

[0053] The embodiment of the present invention calls the battery cell characteristic benchmark library to standardize the voltage rebound characteristic parameter set. The benchmark library is obtained by the system through experimental testing during the construction period, including typical rebound characteristic reference values ​​of different types of battery cells at various stages of their life cycle under standard working conditions. For example, for lithium iron phosphate IFR-32700 battery cells, the benchmark library records that its initial voltage in the new battery cell state is 3.295 volts, the stable voltage is 3.330 volts, and the rebound rate is about 65 microvolts per second. The system performs normalization processing by comparing the offset between the characteristic parameters of the current node and the benchmark value, and calculates the standardized voltage rebound characteristic data. The standardization method adopts the minimum-maximum normalization strategy, that is, each parameter is converted into a value between 0 and 1 according to its relative position within the benchmark range of the model, which facilitates the subsequent horizontal comparison and aging trend analysis between different battery cells. The standardized voltage rebound characteristic data finally formed can not only be used for single-node aging status assessment, but also supports the construction of a health trend prediction model for the entire station operation.

[0054] Preferably, step S2 includes the following steps:

[0055] Step S21: setting the state of charge detection time window parameters to be suitable for the state of charge acquisition frequency of each energy storage node type, and obtaining state of charge monitoring configuration data;

[0056] To accurately monitor the State of Charge (SOC) of battery cells in different energy storage node types during charging and discharging, the system first sets appropriate SOC detection window parameters for each type of energy storage node. In specific implementation, the system configures different SOC sampling frequencies based on the cell chemistry (e.g., lithium iron phosphate, ternary lithium), cell capacity (e.g., 50Ah, 100Ah), and node location (e.g., whether cooling and ventilation are available). For a 50Ah lithium iron phosphate node, for example, which features a stable discharge platform and slow temperature rise, the system sets the SOC detection window to "sample every 5 seconds for a continuous sampling period of 120 seconds." For an 80Ah ternary lithium ion node, which is more susceptible to sudden temperature changes, the system sets the SOC detection window to "sample every 2 seconds for a shortened sampling window of 60 seconds." The system labels all energy storage nodes through the node parameter initialization module, classifies and configures the sampling window parameters, and organizes the sampling interval, sampling cycle and data format specifications corresponding to each node into "charge state monitoring configuration data", which is stored in the operation monitoring configuration table for dynamic call in subsequent steps.

[0057] Step S22: collecting terminal voltage, current, and temperature at specific moments before and after the node charge and discharge process according to the state of charge monitoring configuration data to obtain raw data on the node state before and after operation;

[0058] This embodiment of the present invention, based on the aforementioned state-of-charge monitoring configuration data, controls the data acquisition unit in real time to trigger state data collection at specific time points before and after each node's charge or discharge event. Specifically, the system uses a PCS (power conversion system) activation signal to determine whether the node has entered the charging or discharging phase. Within 30 seconds before and 60 seconds after the event, the system collects battery terminal voltage, current, and cabin temperature at the configured frequency. For example, for a Class A node, data is collected every 5 seconds for 30 seconds before and 90 seconds after the event. The system records the collected raw data as a series of "timestamp + voltage + current + temperature" triples. This data is uploaded to the data aggregation server in real time by the distributed acquisition controller, tagged with metadata such as the current node ID, operation type (charging or discharging), time stamp, and operation phase. This data is aggregated to generate a raw dataset of node status before and after operation, which serves as input for subsequent processing.

[0059] Step S23: Preliminary filtering and calibration of the original data of the node state before and after operation to eliminate the influence of measurement interference and transient fluctuations, and obtain effective state of charge data;

[0060] To eliminate outliers and short-term fluctuations caused by electromagnetic interference, communication delays, or sudden load switching, this embodiment of the present invention utilizes a state cleaning module to perform preliminary filtering and calibration on the raw state data before and after node operation. This module employs a combined "sliding median filtering + local range determination" strategy. Within each time window, the module calculates the median of a five-point sliding window to replace the raw value, thereby suppressing spike interference. A threshold is also set: when the current difference between two adjacent sampling points exceeds 10% of the rated capacity or the voltage change exceeds 50 millivolts, the system deems that data segment disturbed and removes it. For example, at the beginning of discharge, node B experiences a sudden current jump from 8 amps to 42 amps. The system identifies this as a charge-discharge switching transient and sets a "transition mask" flag for this segment, removing it from the results. After cleaning, the data is converted into a continuous and stable series of voltage, current, and temperature, and then segmented and categorized according to time periods within the node cycle, forming a structured "effective state-of-charge dataset."

[0061] Step S24: Calculate the state of charge change of each energy storage node within a complete operation cycle based on the effective state of charge data to obtain a preliminary assessment value of the node's charge and discharge depth;

[0062] Based on the aforementioned effective state of charge data set, the embodiment of the present invention adopts an integral charge estimation method to calculate the SOC change of each node within a complete operating cycle. The process first extracts the start and end times of a complete charge and discharge cycle of the node and the corresponding current data. By multiplying the current by the sampling period and integrating it within the time window, the total charge or discharge amount of the node is approximately calculated. For example, the average current of node C in the discharge phase from 08:00 to 10:15 is 25 amperes, which lasts for a total of 135 minutes. The system estimates the integrated charge of this period to be 56.25 ampere-hours. Combined with its rated capacity, it is judged that its discharge depth is approximately 56%. At the same time, the system performs a difference analysis on the starting and ending voltages to verify whether the voltage change is consistent with the charge change trend. If they are consistent, the SOC change is confirmed to be valid. The SOC changes of all nodes are uniformly organized into a preliminary assessment value of the node charge and discharge depth, marked as "node ID + time period + charge change value + discharge ratio".

[0063] Step S25: Correcting the preliminary evaluation value of the node charge and discharge depth based on the actual operation time of the node and the charge and discharge current, thereby obtaining a charge and discharge depth change value;

[0064] The embodiment of the present invention takes into account the impact of current fluctuations and duration on the accuracy of state of charge estimation during actual operation, and introduces a multi-maintenance correction model to dynamically adjust the preliminary evaluation value of the node charge and discharge depth. The correction model makes a weighted adjustment to the SOC estimation based on the stability factor and operation time factor of the current load curve. For example, for a Class D node with a short operating time and frequent current peaks, the system detects that its discharge time is only 28 minutes and the current fluctuation exceeds ±20%, and it is determined to be a short-cycle high-pulse load scenario. The correction model corrects its initial estimated discharge depth of 56% to 42%, reflecting its insufficient effective output power. The model configures weight coefficients according to different operating modes, calibrates through historical calibration data, and finally outputs "node ID + corrected charge and discharge depth change value" as the node's true power change indicator to input into the subsequent health model.

[0065] Step S26: constructing a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth variation value to obtain node aging differentiation parameters.

[0066] This embodiment of the present invention integrates standardized voltage rebound characteristic data with charge-discharge depth variation to construct a multi-factor health status assessment model to identify the level of node performance degradation. This model utilizes a random forest regression algorithm, taking the triplet of "rebound initial voltage, stable voltage, and rebound rate" and the "charge-discharge depth variation" as input feature vectors. It outputs a health decay factor for a single node, reflecting the node's performance degradation rate during the current cycle. For example, if the system identifies a Class E node with a 15% decrease in rebound rate and a corrected depth of discharge value above 80% during the current cycle, the model outputs a node health score of 0.82 (out of a maximum score of 1). To further highlight the aging variability of nodes within a power plant, the system performs standard deviation analysis on the scores of all nodes within the same operating batch, extracting the relative offset of each node from the mean. This results in node aging differentiation parameters, which serve as a basis for load distribution and maintenance priority sorting on the dispatch side. These parameters are also regularly uploaded to the master station for station-level health trend modeling.

[0067] Preferably, step S26 includes the following steps:

[0068] Step S261: performing data fusion matching based on the standardized voltage rebound characteristic data and the charge and discharge depth change value to construct a node operation behavior characteristic matrix;

[0069] After acquiring standardized node voltage rebound characteristic data and charge / discharge depth variation values, the system uses a data fusion module to match these two types of data, constructing a node operational behavior feature matrix with a unified structure and clear dimensions. This process involves three steps: First, the system associates voltage rebound characteristics with corresponding charge / discharge depths based on node ID and time period labels. Second, the voltage rebound characteristics are quantified into three metrics: rebound onset voltage (reflecting the starting point of electrochemical reaction recovery), rebound stabilization voltage (reflecting the final stable state), and rebound duration (i.e., the time from power outage to voltage stabilization). Third, these three voltage rebound parameters are combined with the charge / discharge depth variation values ​​within the same period into a set of feature vectors, forming a six-dimensional behavioral feature record consisting of "node ID + time period + rebound onset voltage + rebound stabilization voltage + rebound duration + charge / discharge depth." The system then stacks all records by node and time order to form a node operational behavior feature matrix with the dimensions "number of nodes × number of feature items × time series length," providing the data foundation for subsequent correlation analysis.

[0070] Step S262: Analyze the correlation between voltage rebound characteristics and charge / discharge depth based on the node operation behavior characteristic matrix, thereby establishing a preliminary node health assessment model;

[0071] After constructing the node operational behavior characteristic matrix, the system of this embodiment enters the characteristic correlation analysis phase to explore the intrinsic relationship between voltage rebound behavior and the node's charge and discharge depth. The system uses a combination of Pearson correlation coefficient analysis and principal component dimensionality reduction to comprehensively analyze the strength of correlations between variables. Specifically, the system traverses the behavioral characteristic matrix node by node, calculating the correlation coefficient between the "rebound time length and charge and discharge depth" and the "rebound starting voltage and discharge depth" at each node to determine whether there are correlation trends between different parameters. For example, for node F, the system finds a significant positive correlation between its rebound time length and discharge depth (with a correlation coefficient exceeding 0.85), indicating that the chemical reaction recovery process is slower after deep discharge. Based on this analysis, the system establishes a preliminary health assessment model, using a linear weighted model with "rebound time," "start voltage offset," and "depth value" as independent variables. The system outputs a node health score for the current cycle. This score provides a preliminary indication of the degree of electrochemical performance degradation and provides a basis for subsequent model optimization.

[0072] Step S263: Calibrate the parameter weights in the preliminary node health assessment model using pre-acquired historical operation data, optimize the model response characteristics, and thus obtain a node health status assessment model;

[0073] To improve the adaptability of the preliminary health assessment model across different nodes and operating conditions, this embodiment of the present invention incorporates historical operating data to calibrate parameter weights and optimize the model's response characteristics. Specifically, the system extracts complete charging and discharging behavior records and manual maintenance results (such as cell replacement records and voltage anomaly alarm data) for all nodes over the past 180 days from the station-level database. This data is then fed into the preliminary model as a training set, and a genetic algorithm is used to optimize the weight of each feature item. For example, the system assigns an initial weight of 0.3 to the rebound time feature and 0.5 to the voltage initial offset feature. Through a successive round of genetic evolution, the weights are continuously adjusted to minimize the error between the model's predicted health score and the actual fault probability on the validation set. The optimized model weight vector is saved in the "Node Health Assessment Model" configuration table and serves as the core call module for real-time health calculations. The system also uses a 50-fold cross-validation approach to evaluate the model's generalization capabilities, ensuring stable operation across different cycles and node conditions in the future.

[0074] Step S264: Quantitatively analyze the current status of each node using the node health status assessment model, and output comparable health status difference indicators, thereby obtaining node aging difference parameters.

[0075] After optimizing the health assessment model, this embodiment of the present invention formally applies it to calculate the real-time health status of each operating node in an energy storage power plant. Specifically, the system periodically retrieves the behavioral feature matrix from the most recent cycle and inputs each node's feature vector into the optimized health assessment model. The model then outputs a health score between 0 and 1, with scores closer to 1 representing a better node health. For example, if node G's health score for the current cycle is 0.92, while node H's score is only 0.63, the system automatically calculates the mean and standard deviation of the scores for nodes in the same batch and outputs a standardized difference indicator, the "node health score deviation." All deviations are organized into a "node aging differentiation parameter," which is used not only to analyze differences in aging rates between nodes but also to provide feedback to the power plant management system for prioritizing maintenance or rotation of aging nodes. In typical scenarios, such as peak-valley electricity pricing scheduling, nodes with high health scores are prioritized to extend battery cell life and improve overall energy storage efficiency. This embodiment thus completes a comparable quantitative assessment of node health status, ensuring the dynamic closed-loop nature of the monitoring system.

[0076] Preferably, determining the available capacity level of each node according to the node aging differentiation parameter in step S3 includes:

[0077] The node aging differentiation parameters are normalized based on the 0-1 normalization method to eliminate the influence of different dimensions and obtain the standardized aging parameters;

[0078] Based on the standardized aging parameters, the aging parameter threshold interval [0.15, 0.35, 0.55, 0.75] was set as the classification boundary point, and segmented mapping was performed to obtain the preliminary aging grade classification results;

[0079] Based on the preliminary aging grade classification results and the pre-acquired node rated capacity values ​​of each energy storage node, the actual capacity loss rate is calculated based on the loss rate calculation formula, where the loss rate calculation formula is loss rate = basic loss rate + aging grade coefficient × attenuation acceleration factor;

[0080] Dynamically correct the actual capacity loss rate. For nodes with an operating time of more than 1,000 hours, add a 0.8% correction value to the original loss rate for every additional 500 hours to obtain the corrected capacity loss rate.

[0081] Calculate the actual available capacity percentage of the node based on the corrected capacity loss rate, where the actual available capacity percentage of the node = 100% - corrected capacity loss rate;

[0082] Set capacity grading standards based on the percentage of actual available capacity of nodes to form node capacity grading standards;

[0083] Based on the node capacity grading standard, the actual available capacity percentage of each node is graded and divided to obtain the node available capacity grade data;

[0084] The nodes with adjacent level boundary values ​​are extracted from the node available capacity level data, and a secondary correction is performed based on the stable voltage recovery rate in the voltage rebound feature data. When the recovery rate is lower than the threshold, the node level is lowered by one level to obtain the available capacity level.

[0085] After obtaining the "node aging differentiation parameter" for each energy storage node, the system first normalizes the parameter to a scale of 0-1 to eliminate dimensionality, facilitating subsequent grading comparisons. Since this parameter is calculated based on health score deviations and can have inconsistent distributions across different nodes, the system first performs a 0-1 normalization on the parameter to eliminate dimensionality effects. This process facilitates subsequent grading comparisons. Specifically, the system extracts the maximum and minimum aging differentiation values ​​from all nodes and adjusts each node's aging differentiation value to a proportional range between 0 and 1 according to a normalization formula. For example, if the node differentiation value range is 0.12 to 0.85, the system maps the original aging differentiation value of node K, 0.42, to a normalized value of 0.459, providing a uniform basis for comparison across nodes. This result is defined as the "normalized aging parameter" and stored in the node evaluation feature table. After calculating the normalized aging parameter, the system sets the parameter threshold interval to [0.15, 0.35, 0.55, 0.75] based on empirical aging grading, serving as the five-level cutoff points. The normalized aging parameters for all nodes are then segmented and mapped to form a preliminary aging grading result. The system defines the following grading logic: Normalized values ​​less than or equal to 0.15 are classified as "Level 1 (New State)"; values ​​greater than 0.15 and less than or equal to 0.35 are classified as "Level 2 (Mild Aging)"; values ​​greater than 0.35 and less than or equal to 0.55 are classified as "Level 3 (Moderate Aging)"; values ​​greater than 0.55 and less than or equal to 0.75 are classified as "Level 4 (Severe Aging)"; and values ​​greater than 0.75 are classified as "Level 5 (Severe Aging)." For example, if the normalized aging value of node M is 0.62, the system classifies it as Level 4 and enters this preliminary grade into the preliminary node aging grade evaluation table, forming a mapping between healthy status and aging grade. Based on the preliminary aging grade results, the system further combines the energy storage node's "rated capacity" to calculate its capacity loss in its current state. To this end, the system introduces a formula for calculating the "actual capacity loss rate" based on the aging grade. Each grade is assigned an "aging grade coefficient," and a "base loss rate" of 5% and a "decay acceleration factor" of 3% are introduced to reflect the impact of aging on capacity decline. For example, the aging level coefficient of level 2 is 0.6, and the corresponding capacity loss rate is 5% plus 0.6 times 3%, that is, the loss rate is 6.8%. Node N is level 3, and its corresponding coefficient is 1.1, so the loss rate is calculated to be 8.3%. This calculation realizes the quantitative mapping between capacity attenuation and aging level, and preliminarily characterizes the capacity performance degradation of each node due to aging. Taking into account that some nodes have been running for a long time, their actual capacity loss is not only related to the aging level, but also significantly affected by the cumulative running time. Therefore, the system introduces a dynamic correction mechanism to further adjust the "actual capacity loss rate". The specific rules are: for any node with a cumulative running time of more than 1,000 hours, for every additional 500 hours, 0.8% is added to the original loss rate as a correction value.For example, if node P is currently rated 4, with an initial loss rate of 10.25%, and its cumulative operating time is 2100 hours, two additional rounds of correction are required (i.e., an increase of 2 × 0.8%), resulting in a corrected loss rate of 11.85%. This effectively improves the assessment model's accuracy in responding to capacity loss in nodes operating under prolonged, high-load conditions, avoiding biases in operating intensity that might be overlooked by a single assessment based on aging level. After obtaining each node's corrected capacity loss rate, the system further calculates the node's "actual available capacity percentage," which represents the node's remaining available capacity relative to its rated capacity in its current state. The system calculates this percentage as a percentage, subtracting the corrected capacity loss rate from 100% to arrive at the final available capacity percentage. For example, if node P's corrected loss rate is 11.85%, its current available capacity is 88.15%. This metric serves as the basis for subsequent capacity grading, reflecting the actual performance of the node's dispatchable capacity and serving as a key basis for formulating energy storage resource scheduling strategies. To facilitate unified scheduling management and tiered maintenance, a node capacity grading standard has been developed, divided into five levels based on percentage: greater than or equal to 95% is "Capacity Level A", between 85% and 95% is "Level B", 75% to 85% is "Level C", 65% to 75% is "Level D", and below 65% is "Level E". The system uses this standard as the basis for node capacity performance grading, and the "actual available capacity percentage" of all nodes will be archived under this standard. For example, if the calculation result of node Q is 93.6%, it will be classified as capacity level B; the result of node R is 68.2%, which is classified as capacity level D and marked as capacity warning status. The system writes this level into the capacity level table and associates it with the aging level table for easy unified management and analysis. To further improve the accuracy of the rating, after completing the preliminary capacity grading of all nodes, the level correction operation of the boundary nodes will be carried out. The specific method is as follows: the system selects nodes close to the grade boundary value (i.e., within the range of ±1% of the edge value such as 85%, 75%, and 65%) from all nodes as boundary node samples, and then extracts the "stable voltage recovery rate" parameter from the "voltage rebound characteristic data" of the corresponding period. This parameter refers to the ratio of the final stable value of the rebound voltage to the discharge termination voltage, reflecting the node voltage recovery ability. The system sets the threshold to 92%, that is, a recovery rate lower than this value indicates that the electrochemical reaction is lagging. If the recovery rate of the boundary node is lower than 92%, the system will downgrade the capacity level of the node by one level. For example, node S is initially rated as grade B, but its recovery rate is 88.7%. The system downgrades it to grade C, indicating that the voltage performance does not support the original grade capacity indicator. This mechanism can effectively avoid the scheduling risk caused by inaccurate judgment of a single capacity indicator, and form a more reliable output result of the available capacity level.

[0086] Preferably, step S3 includes the following steps:

[0087] Establishing a mapping relationship between capacity level and state-of-charge operating range based on available capacity level to obtain preliminary state-of-charge operating range data;

[0088] The voltage-state of charge curve of each node under standard charge and discharge conditions is collected, and the area where the voltage change rate is less than 0.05V / 1%SOC is selected as the voltage platform area to obtain the node voltage platform interval data;

[0089] Based on the node voltage platform interval data and the preliminary state-of-charge operating range data, the operating range is optimized and adjusted to ensure that the operating range includes at least 75% of the voltage platform area, and the adjusted operating range data is obtained;

[0090] Perform constant power charge and discharge tests on each node at a 0.5C rate, record the terminal voltage change rate at different states of charge, and obtain voltage response characteristic data;

[0091] Based on the voltage response characteristic data, the internal resistance change trend of each node under different charge states is calculated. Taking the point where the internal resistance increases by 20% as the boundary, the working range boundary is further optimized to obtain the internal resistance optimized working range data;

[0092] The intersection of the adjusted working range data and the internal resistance optimized working range data is calculated as the node's safe working range. The available range width is divided into the following categories: width greater than 70% is level 1, 50%-70% is level 2, 30%-50% is level 3, and less than 30% is level 4, thus obtaining the node working range grade data.

[0093] A two-dimensional evaluation matrix is ​​established based on the node working range level data and available capacity level data to obtain the node's preliminary operating capability level;

[0094] The power response capability test is performed on the node's preliminary operational capability level to obtain a power response capability rating. The power response capability test specifically applies a pulse power of 0.8C within the safe operating range for 30 seconds and records the voltage drop. A voltage drop of less than 0.15V is considered excellent, 0.15V-0.25V is considered good, 0.25V-0.35V is considered fair, and greater than 0.35V is considered poor.

[0095] The node operation capability classification is determined based on the node's preliminary operation capability level and power response capability rating, forming node operation capability classification data including three-dimensional characteristics of capacity status, working range and power response.

[0096] After determining the available capacity level data for a node, this embodiment of the present invention establishes a mapping between capacity level and SOC operating range based on the available capacity level to achieve more accurate node state-of-charge (SOC) control. Specifically, the system pre-determines the SOC operating range based on the previously obtained four-level node available capacity level data, categorizing it as level 1 (available capacity greater than 85%), level 2 (70%-85%), level 3 (50%-70%), and level 4 (less than 50%). For example, the SOC range for level 1 nodes is set to 25% to 90%, for level 2 nodes to 30% to 85%, for level 3 nodes to 35% to 80%, and for level 4 nodes to 40% to 75%. This mapping is constructed based on historical operating data and operational experience, aiming to ensure efficient operation of nodes of different capacity levels within their remaining capacity capabilities while avoiding frequent charging and discharging or deep cycling due to insufficient capacity. This ultimately generates preliminary SOC operating range data for each node, providing a reference for subsequent voltage plateau adjustments. To further refine the state-of-charge (SOC) range of each node, this embodiment collects voltage and state-of-charge (SOC) curve data for each node under standard charge and discharge conditions. Standard charge and discharge conditions refer to testing conducted at an ambient temperature of 25°C, a 0.5C charge and discharge rate, and a voltage sampling frequency of at least 1Hz. Within the curve data, the voltage change amplitude corresponding to each 1% change in SOC is statistically analyzed. Continuous regions with a voltage change rate of less than 0.05 volts per 1% SOC are selected and defined as voltage plateaus. A voltage plateau represents a node with minimal voltage fluctuation within a specific SOC range. This region is most sensitive to battery performance and exhibits relatively stable energy output. The extracted voltage plateau range data serves as an important basis for optimizing the SOC operating range and is subsequently used to adjust the preliminary SOC range to ensure operational stability. After obtaining preliminary SOC operating range data and voltage plateau range data for each node, this embodiment optimizes and adjusts the operating range. The adjustment strategy is to ensure that the final state of charge working range of each node must cover more than 75% of its voltage platform segment, that is, the voltage platform interval is used as the core area for outward extension coverage adjustment. When the initially set SOC working range cannot meet the coverage requirements, the upper and lower limits are reset according to the start and end positions of the platform interval. For example, if the voltage platform interval of a node is SOC40% to SOC80%, and the initially set range is 35%-75%, the upper limit of the range needs to be adjusted to 80% to meet the coverage ratio requirement. The adjusted working interval data will serve as the basis for subsequent performance tests to ensure that the test results are carried out within the stable operating voltage area and to improve the evaluation accuracy. After clarifying the adjusted state of charge working interval of each node, the embodiment conducts a constant power charge and discharge test on each node within the interval to obtain voltage response characteristic data.The specific testing method involves charging from the lower limit to the upper limit of the SOC range at a 0.5C charge rate and discharging back to the lower limit at a 0.5C discharge rate. During this period, the voltage curve is recorded with a 1-second sampling period. The voltage change per unit time is extracted at different SOC points and divided by the SOC change rate ratio to calculate the voltage change rate. Voltage response characteristic data reflects the voltage sensitivity of a node at different states of charge, is used to determine battery performance degradation characteristics, and serves as an important reference for subsequent internal resistance analysis and interval boundary adjustment. After obtaining the voltage response characteristic data, this embodiment calculates and analyzes the battery internal resistance variation trend at different SOC points. By linking the voltage response characteristics with current data under constant power charge and discharge conditions, the dynamic internal resistance of the battery is calculated at different SOC points, with the internal resistance at the starting SOC point serving as a reference base point. If the internal resistance value at a particular SOC point increases by more than 20% compared to the reference point, it is marked as a safe boundary point in the operating range. For example, if the internal resistance at SOC = 75% increases by more than 20% compared to SOC = 35%, 75% is set as the upper limit. This method further compresses sections where the internal resistance rises too quickly, eliminating operating ranges with potential safety hazards, ultimately yielding the optimized operating range data. Combining the adjusted operating range data with the optimized operating range data, this embodiment calculates the intersection of the two and uses this as the node's safe operating range. The intersection is processed using a two-interval union method, where the overlapping portion of the two intervals is taken as the valid interval, ensuring operation within both the safe voltage range and the stable internal resistance range. The width of this intersection interval (i.e., the interval length divided by the total SOC range) is then used to rank the nodes. Widths greater than 70% are assigned level 1, indicating a wide operating range with high flexibility; 50%-70% is assigned level 2, indicating a largely safe and controllable area; 30%-50% is assigned level 3, indicating restricted operation; and less than 30% is assigned level 4, indicating the need for intensive monitoring. The resulting node operating range rank data serves as an important indicator for operational capability assessment. After obtaining the node's operating range rating and available capacity rating data, this embodiment establishes a two-dimensional evaluation matrix model. The horizontal axis represents the node's operating range rating, and the vertical axis represents the capacity rating. Each node can locate a level coordinate point in this matrix and receive a comprehensive score by setting scoring rules. For example, a level 1 capacity combined with a level 1 operating range receives a full score of 10 points, while a level 4 capacity combined with a level 4 range receives a minimum score of 2 points. Scoring rules are set for the remaining combinations using a weighted approach. For example, a combination with a level 2 capacity and a level 3 operating range receives a score of 6 points. This matrix model quantifies the node's comprehensive operating potential into a preliminary operating capability rating, laying the data structure foundation for subsequent response capability testing. To further improve the node's operating capability assessment, this embodiment performs a power response capability test on each node. The test method applies pulse power at a rate of 0.8C (for a duration of 30 seconds) within each node's safe operating range and records the voltage drop at the moment the load is applied.If the voltage drop is less than 0.15 volts, it is classified as "Excellent"; between 0.15 and 0.25 volts, it is "Good"; between 0.25 and 0.35 volts, it is "Fair"; and greater than 0.35 volts, it is "Poor." During the testing process, high-frequency sampling equipment monitors voltage changes in real time, sampling at least 10 times per second to ensure data accuracy. The test results are used to determine the node's dynamic response capability in high-power scenarios, providing reliable data support for adjusting the operational capability rating. After obtaining the node's preliminary operational capability rating and power response capability rating, this embodiment combines these two information to determine the final node operational capability classification. The operational capability classification uses a three-dimensional scoring method, assigning specific weights to the capacity level, operating range level, and power response rating (e.g., 40% for capacity, 30% for operating range, and 30% for response capability). The score is then combined with a weighting adjustment strategy based on actual operating conditions. Nodes are ultimately classified into four levels: operational capability level 1 (high reliability and high responsiveness), level 2 (medium and high performance), level 3 (average performance), and level 4 (low performance requiring warning). This generates structured node operational capability classification data. This data will serve as the basis for energy storage power station operation scheduling, maintenance planning and abnormality prediction, improving the overall operating efficiency and safety of the energy storage system.

[0097] Preferably, establishing a node charging and discharging power allocation model using node operation capability classification data in step S3 includes:

[0098] Based on the node operation capability classification data, a basic power weight coefficient is assigned to each node to obtain a node basic power weight coefficient table;

[0099] Collect the charge and discharge efficiency data of each node at different states of charge, perform sampling tests at intervals of 10% state of charge, record the energy conversion efficiency of each sampling point, and obtain the node charge and discharge efficiency curve;

[0100] Based on the node charge and discharge efficiency curve, the optimal charge and discharge efficiency range of each node is calculated, and the area with efficiency higher than 90% is defined as the optimal working point to obtain the node efficiency optimization range data;

[0101] Combine the node efficiency optimization interval data and the node safe working interval to calculate the intersection area of ​​the two as the node priority scheduling interval, and obtain the node priority scheduling interval data;

[0102] Design the power allocation coefficient within the interval based on the node priority scheduling interval data;

[0103] Monitor the current state of charge of the node in real time and calculate the distance ratio between the current state of charge and the boundary of the priority scheduling interval. When the distance ratio is less than 0.2, the basic power weight coefficient is linearly attenuated to obtain the boundary adjustment coefficient.

[0104] Monitor the node temperature change status and set the normal operating temperature range to 15°C-35°C. When the temperature exceeds this range, the basic power weight coefficient is attenuated by 5% for every 5°C increase or decrease to obtain the temperature correction coefficient.

[0105] A node charging and discharging power allocation model is established based on the power allocation coefficient within the interval, the boundary adjustment coefficient and the temperature correction coefficient.

[0106] In the energy storage power station operation monitoring and management method of this embodiment, a basic power weight coefficient is assigned to each energy storage node based on the previously obtained node operational capability grading data. Specifically, the grading results are used to assign basic power weights according to a four-level distribution: a level-one node is assigned a basic power weight coefficient of 1.0, representing the node with optimal operational capability; a level-two node is assigned a basic power weight coefficient of 0.8; a level-three node is assigned a basic power weight coefficient of 0.6; and a level-four node is assigned a basic power weight coefficient of 0.4. These weight coefficients serve as the initial basis for dispatching and allocating power to the power station and are recorded in a table of node basic power weight coefficients for subsequent dispatch calculations. This table, which includes the node number, operational capability level, and corresponding basic power weight, is suitable for dynamically adjusting node scheduling strategies. After establishing the basic power weights, to further improve scheduling accuracy, charge and discharge efficiency data for each node at different states of charge (SOC) is collected. Eleven sampling points are set within the range of 0%-100% at sampling intervals of every 10% of the state of charge (SOC), performing standard charging and discharging operations. During the test, input and output energy was recorded, and efficiency (the percentage of output energy divided by input energy) was calculated to form a charge and discharge efficiency curve for each node. This test used a 1C charge and discharge rate and maintained at a constant temperature of 25°C to eliminate temperature effects. The resulting data served as the basis for measuring the node's energy conversion performance at different SOCs. Based on the efficiency curves, the efficiency level of each node was calculated at different SOC ranges. The SOC range with an efficiency value above 90% was selected and defined as the "optimal charge and discharge efficiency range," indicating that the node achieved the most efficient energy conversion and minimized losses within this range. In implementation, the efficiency curves were traversed to extract SOC segments with continuous efficiencies above 90%, which were labeled as the node's efficiency optimization range. This process can be implemented using tools such as Python to perform data fitting and filtering, resulting in the optimal efficiency operating range for each node between 0% and 100% SOC. To achieve more efficient power plant operation and scheduling, the node efficiency optimization range data was intersected with the previously obtained node safe operating range data to obtain the "node priority scheduling range." This intersection area is both safe (e.g., stable voltage platform and reasonable internal resistance control) and highly energy-efficient, making it suitable as a priority energy regulation window during power plant operation. The intersection calculation can be completed using a data interval comparison algorithm. The priority scheduling interval is usually expressed in SOC values. For example, the priority scheduling interval for node A is 30% to 80%. After obtaining the priority scheduling interval, it is necessary to design a power allocation coefficient within the interval to refine the scheduling strategy. In implementation, the priority scheduling interval is further subdivided into three sub-segments: the leading edge (e.g., the first 20%), the core (the middle 60%), and the tail (the last 20%). These are assigned allocation coefficients of 0.8, 1.0, and 0.9, respectively. This guides the scheduling system to prioritize scheduling this node to achieve high power output when the SOC is in the core zone, while slightly more conservative scheduling is performed in the leading edge or tail zones.This coefficient is used to dynamically adjust the base power weight to adapt the node's scheduling responsiveness within the preferred interval. The system then monitors each node's current state of charge (SOC) in real time and calculates its distance ratio from the boundary of the priority interval. Specifically, the difference between the current SOC value and the nearest boundary of the priority interval is divided by the width of the priority interval. For example, if a node's priority interval is 30%-80% and its current SOC is 32%, its distance ratio is 2% / 50% = 0.04. If the distance ratio is less than 0.2, it indicates that the current state is close to the edge of the preferred interval and risk mitigation should be implemented. Therefore, in this case, the base power weight coefficient is linearly decayed to a maximum of 0.5. For example, if the initial coefficient is 1.0 and the distance ratio is 0.1, the final boundary adjustment coefficient is 0.75. To further consider the impact of temperature on battery node performance, the operating temperature of each node is monitored in real time, with a normal operating range set to 15°C to 35°C. When the temperature exceeds this range, the base power weight coefficient is decayed by 5% for every 5°C above or below. For example, if the current temperature of the node is 40°C, which exceeds the upper limit by 5°C, its temperature correction coefficient is 0.95. This correction is used to simulate the impact of high or low temperatures on battery reaction efficiency and life, and is a key safety parameter adjustment item in the operation monitoring of energy storage power stations. Finally, based on the above three weight factors: the power allocation coefficient within the interval, the boundary adjustment coefficient, and the temperature correction coefficient, the current basic power weight coefficient of each node is multiplied to form a real-time charging and discharging power allocation model for the node. During implementation, the system accesses the real-time operation data of all nodes through the dispatching and control platform, and automatically calls the above model to dynamically update the power allocation instructions of each node, thereby achieving optimal configuration of the overall power output of the power station and dynamic load response adjustment. The model supports scheduling decisions at the minute level or finer granularity, and has good response effects and economy in scenarios such as peak and valley electricity price strategies and grid load regulation.

[0107] Preferably, step S4 includes the following steps:

[0108] Step S41: Obtain the overall power dispatch instruction of the energy storage power station, parse the instruction and extract the charging and discharging power demand value, duration parameter and response time requirement to obtain a power dispatch parameter set;

[0109] In response to the real-time operation requirements of the energy storage power station, the embodiment of the present invention first executes step S41 to obtain the overall power dispatch instruction issued by the superior dispatching platform or the power grid operator. This instruction is usually accessed through the energy management system (EMS) or the dispatching communication interface, and includes the target power value for charging and discharging (for example, the dispatching requires the energy storage power station to output 5MW of electricity), duration parameters (such as 10 minutes), and response time requirements (such as a response time of less than 30 seconds). The system parses the dispatch instruction, extracts key control parameters to form a power dispatch parameter set, and the parameter set is used as the basis for the calculation of subsequent node power allocation. In actual applications, such as during grid frequency regulation or peak regulation, the power station may receive multiple dispatch instructions with different strategies within 1 minute, and the system needs to quickly parse and classify them into the database.

[0110] Step S42: Calculate the preliminary power allocation coefficient of each energy storage node based on the power scheduling parameter set and the node charge and discharge power allocation model to obtain a preliminary power allocation plan;

[0111] The embodiment of the present invention calls the charging and discharging power allocation model of each node established above, and calculates the preliminary power allocation coefficient of each energy storage node in combination with the target power value and response time in the scheduling instruction. The specific method is: the target power is allocated according to the node basic power weight multiplied by the comprehensive weight ratio composed of its interval power allocation coefficient, boundary adjustment coefficient and temperature correction coefficient. For example, if the target output power is 5MW and the comprehensive allocation weight of node A is 0.25, then its preliminary allocated power is 1.25MW, and the allocation results of all nodes constitute a preliminary power allocation plan. This plan is an initial estimate based on the current state of the node, and the maximum / minimum carrying capacity of the node has not yet been considered.

[0112] Step S43: Calculate the upper and lower limits of the loadable power of each node based on the preliminary power allocation plan and the node operation capability classification data of each energy storage node to obtain the node power constraint conditions;

[0113] To ensure that power allocation complies with the physical limitations of nodes, the present invention further calculates the maximum and minimum power capacity of each energy storage node in its current state based on its operating capability level data and rated capacity information. For example, if a node has a level 2 operating capability and a rated power of 2MW, and a power safety factor of 0.85 under the current SOC and temperature conditions, its maximum power capacity is 1.7MW and its minimum is -1.7MW (for charging). The system traverses all nodes to form a complete node power constraint table for subsequent correction processing to avoid problems such as overload, abnormal heating, or power feedback during the power allocation process.

[0114] Step S44: Correcting the preliminary power allocation plan according to the node power constraint conditions to ensure that the power value allocated to each node does not exceed its safe operating range, thereby obtaining a safe corrected power allocation plan;

[0115] The embodiment of the present invention corrects the allocation values ​​that exceed the upper and lower limits of a single node in the preliminary power allocation scheme based on the power constraint conditions obtained in step S43. Specifically, if the preliminary allocated power of node A is 1.9MW and its maximum carrying capacity is 1.7MW, its power is reduced to 1.7MW, and the extra 0.2MW is proportionally reallocated to other nodes with remaining carrying capacity. This process can achieve dynamic iterative adjustment through a recursive algorithm, and ultimately form a safe and corrected power allocation scheme in which the power values ​​of all nodes are within a safe range. This scheme serves as the basis for subsequent refined optimization.

[0116] Step S45: Calculate the deviation between the current state of charge of each node and its optimal working range, calculate the interval deviation adjustment coefficient, optimize the safety correction power allocation plan, and obtain a balanced optimized power allocation plan;

[0117] The embodiment of the present invention further calculates the deviation between the current state of charge (SOC) of each node and the center position of its aforementioned preferred scheduling interval. If the node SOC deviates significantly from the center area of ​​the preferred area, it is necessary to guide it back to the center area by adjusting its allocated power. The "interval deviation adjustment coefficient" is defined here and is calculated by dividing the SOC deviation value by the interval width. The larger the deviation, the lower the adjustment coefficient. For example, if the preferred area of ​​node B is 30%-80% and the current SOC is 85%, then its deviation is 5% and the adjustment coefficient is 0.9. This coefficient is used to lower or increase the power allocation value of the corresponding node in the safety correction scheme to push the node state of charge to balance to the optimal efficiency interval, forming a balanced optimized power allocation scheme.

[0118] Step S46: Monitor the real-time temperature change trend of each node. When the temperature change rate exceeds a preset threshold, calculate the temperature risk coefficient and dynamically adjust the balance optimization power allocation scheme to obtain a temperature adaptive power allocation scheme.

[0119] The embodiment of the present invention continuously monitors the operating temperature change trend of each node. If the temperature rise or fall rate is detected to exceed a preset threshold (such as 1°C / min), it is regarded as a temperature fluctuation risk, and the temperature risk coefficient is calculated. This coefficient is the inverse of the ratio of the temperature change rate to the threshold multiplied by a preset proportional attenuation factor. For example, if the temperature rises by 2°C / min, the temperature risk coefficient is 0.5. For nodes in a temperature risk state, their power allocation value needs to be dynamically attenuated according to the risk coefficient to prevent battery cell expansion, life degradation or thermal runaway caused by temperature changes. The resulting temperature-adaptive power allocation scheme has certain real-time and risk tolerance, and can achieve scheduling adaptation to the dynamic safety state of the node.

[0120] Step S47: forming a node-differentiated power allocation scheme based on the temperature-adaptive power allocation scheme, including power allocation values ​​for each node and an execution order;

[0121] The present invention further refines the temperature-adaptive solution into a node-differentiated power allocation scheme. This scheme, in addition to specifying the specific power allocation value for each node, also specifies the execution order and scheduling priority of the nodes. For example, under the same allocation weight and status conditions, nodes with the current SOC in the optimal mid-range, the temperature in the normal temperature range, and high operating capacity are prioritized for scheduling; while nodes at the state boundary or with temperature rise are delayed. This differentiated solution is distributed to the node controller via a sorted list or scheduling task queue, guiding each node to complete scheduling tasks in order, thus helping to form an orderly and reliable power response chain.

[0122] Step S48: Dynamically optimize the node differentiated power allocation scheme using the minimum power perturbation method to obtain an adaptive energy flow allocation instruction.

[0123] This embodiment of the present invention introduces a "minimum power perturbation method" to dynamically optimize differentiated power allocation schemes. This method involves fine-tuning the power values ​​of individual nodes to minimize overall load perturbations while ensuring that the total target power remains unchanged. Specifically, the system uses the current scheme as a benchmark, fine-tunes the node power values ​​one by one (e.g., ±0.05MW), and then re-evaluates power stability, total energy efficiency, and temperature risk indicators. The allocation result with the least perturbation is selected as the final execution instruction. This optimization process can be executed using local search or gradient descent methods, ultimately generating adaptive energy flow allocation instructions that are sent to the execution system of the energy storage power station, achieving real-time, efficient, and safe energy scheduling.

[0124] It is particularly important that step S48 includes the following steps:

[0125] Step S481: Setting the power perturbation minimum step size parameter, determining the minimum change in power adjustment for each node, and obtaining perturbation step size configuration data;

[0126] The embodiment of the present invention sets a minimum step size parameter for power disturbance based on the adjustment accuracy and response capability of the power controllers at each node in the energy storage power station. This parameter is the minimum change in each node power adjustment and is typically set to 1% to 3% of the rated power. For example, if the rated power of the node is 2MW, the minimum disturbance step size is between 0.02MW and 0.06MW. By investigating the minimum adjustment unit and communication delay of the node equipment, the disturbance step size is determined to ensure that adjustment operations are neither too frequent, thereby overburdening the control system, nor too large, affecting the fine-grained control of power distribution. Ultimately, complete disturbance step size configuration data is formed for subsequent fine-tuning.

[0127] Step S482: slightly adjusting the node power allocation value based on the disturbance step configuration data, generating multiple groups of disturbance solutions, and performing a comparison of the response effects before and after the disturbance to obtain disturbance response effect data;

[0128] This embodiment of the present invention makes minor adjustments to previously determined node power allocation values ​​based on the perturbation step size configuration data. The perturbation step size is added to and subtracted from each node's power value to generate multiple perturbation scenarios. These scenarios are executed in an actual energy storage control system through a simulation platform or real-time online testing. Key performance indicators, such as power plant output power stability, energy efficiency, temperature changes, and response time, are compared before and after the perturbation, and data on the perturbation response effect is collected. In a specific test, for example, after adjusting node A by 0.04 MW, the total power fluctuation is monitored to see if it is within the allowable range (±0.1 MW) and if the system response is less than a preset 100 ms. This data is then recorded for subsequent analysis.

[0129] Step S483: Calculate the power adjustment sensitivity coefficient based on the disturbance response effect data, evaluate the response sensitivity of each node to the power disturbance, and obtain a node power sensitivity table;

[0130] The embodiment of the present invention uses disturbance response effect data to calculate the power adjustment sensitivity coefficient for each node. This coefficient reflects the node's sensitivity to power disturbances, that is, the ratio of the overall system response change after power adjustment. For example, if a 0.05MW power adjustment of node B causes a 0.02MW fluctuation in system output, the sensitivity coefficient is low; otherwise, it is high. By comparing the sensitivity of each node, the system forms a node power sensitivity table. This table reveals which nodes' power adjustments have a greater impact on the overall system, and which nodes have slow or ineffective responses, facilitating targeted optimization of scheduling strategies.

[0131] Step S484: Identify the power response hysteresis nodes in the system based on the node power sensitivity table, adjust the power allocation priorities of the nodes, and obtain a priority-adjusted power allocation solution;

[0132] In an embodiment of the present invention, based on the node power sensitivity table, the system identifies nodes with power response hysteresis, that is, nodes that respond slowly to power disturbances or have a small impact. These nodes are caused by hardware aging, controller performance differences, or communication delays. For these nodes, the system adjusts their power allocation priority, preferentially reducing the scheduling weight of the hysteresis nodes, and assigning more scheduling tasks to nodes with high response sensitivity, forming a priority-adjusted power allocation scheme. For example, the power weight of the least sensitive node is reduced by 20%, and the weight of the highly sensitive node is increased by a corresponding proportion to improve the overall scheduling efficiency and system response speed.

[0133] Step S485: performing iterative optimization on the priority-adjusted power allocation scheme, finding the optimal point of the overall power response of the system through multiple consecutive small perturbations, and obtaining an iteratively optimized power allocation scheme;

[0134] The embodiment of the present invention performs iterative optimization based on a priority adjustment scheme. This process gradually approaches the optimal point of the system's overall power response by repeatedly making small perturbations to the node power (e.g., adjusting the perturbation step size up or down by 0.5 to 1 times), combined with simulation calculation of the system's power response index. After each iteration, the system compares the power fluctuation range, energy efficiency loss, and temperature safety index, and selects the optimal solution as the benchmark for the next iteration until the adjustment result meets the preset convergence conditions, such as when the power response index improves by less than 0.1%. This method effectively improves the robustness and response speed of energy storage power station scheduling, and obtains an iteratively optimized power allocation scheme.

[0135] Step S486: converting the iteratively optimized power allocation scheme into a specific node power execution instruction to form an adaptive energy flow allocation instruction including power value, execution timing and response time requirements.

[0136] The embodiment of the present invention converts the iterative optimization power allocation scheme into specific execution instructions. Each instruction contains a node identifier, an allocated power value, an execution sequence (for example, node A executes 2 seconds after the start of scheduling and lasts for 10 minutes), and a response time requirement (such as a response time of less than 200ms). The instructions are sent to the power control unit of each energy storage node through the control communication network of the energy storage power station to achieve precise power regulation and energy flow distribution. This adaptive energy flow distribution instruction ensures that the energy storage power station meets the scheduling requirements in a dynamic operating environment while ensuring system safety and efficiency. It is suitable for specific application scenarios such as grid peak regulation, emergency standby, and smooth output of new energy.

[0137] Preferably, step S5 includes the following steps:

[0138] Step S51: Generate an operation control command for each energy storage node including a specific charge and discharge power setting value and a timing execution arrangement according to the adaptive energy flow distribution instruction, and send the operation control command to each energy storage node to trigger the node to perform the corresponding charge and discharge operation;

[0139] In an embodiment of the present invention, the charging and discharging power setting values ​​and specific execution timing parameters corresponding to each energy storage node are converted into operation control commands based on the adaptive energy flow distribution instructions obtained in the previous step. During the specific conversion, the control system refines the power value to the charging and discharging module of a single node. For example, the charging power of node A is set to 1.2 megawatts, the charging start time is 5 seconds after the current scheduling time point, and the duration is 15 minutes, to ensure accurate matching of scheduling requirements. The operation control commands are sent down to each node controller one by one through the control network of the energy storage power station (such as industrial Ethernet or a dedicated communication protocol), triggering the power electronic devices and control units inside the node to perform charging and discharging actions according to the instructions. This process includes confirming that the node receives the command and feedback on the execution status to ensure that the command takes effect in a timely manner. It is suitable for actual scenarios such as grid peak regulation and new energy smooth output.

[0140] Step S52: Start the energy storage node real-time operation status monitoring program, collect the voltage, current, temperature and charge state of each node, and form a node real-time operation status data stream;

[0141] The energy storage power station in this embodiment of the present invention starts a real-time operating status monitoring program for nodes, utilizing a distributed sensor network to collect key operating parameters of each node, including voltage, current, temperature, and state of charge (SOC). This data is sampled at high frequency (e.g., 10 times per second) to form a continuous data stream, reflecting the node's power output and internal status in real time. The monitoring program is deployed in the energy storage station control center and utilizes industrial IoT technology to ensure the real-time and integrity of the data, providing fundamental data support for subsequent operating status analysis. Application scenarios include energy storage equipment safety monitoring and operational efficiency evaluation.

[0142] Step S53: Perform online analysis on the node real-time operation status data stream, calculate the power response delay time, voltage fluctuation amplitude and temperature change rate of each node, and generate a node operation characteristic evaluation report;

[0143] The embodiment of the present invention performs online analysis on the node operation status data stream collected in real time. Through timestamp synchronization and signal processing technology, the power response delay time of each node is calculated, that is, the time required from receiving the charge and discharge instructions to the actual power output reaching the set value, which is usually required to be less than 200 milliseconds; at the same time, the voltage fluctuation amplitude is analyzed to reflect the smoothness of the node load change; and the temperature change rate is calculated to evaluate the node heat dissipation and thermal stability to ensure that the temperature rise does not exceed 0.5 degrees Celsius per minute. Based on the above parameters, the system automatically generates a node operation characteristic evaluation report, providing detailed indicators of node performance and potential anomalies, which facilitates operation and maintenance personnel to quickly locate problems and ensure the stable operation of energy storage power stations.

[0144] Step S54: updating the node aging differentiation parameter using a sliding time window method according to the node operation characteristic evaluation report, dynamically evaluating the aging rate, and obtaining the node aging differentiation update parameter;

[0145] In an embodiment of the present invention, based on the operation characteristic evaluation report, the system uses a sliding time window method to dynamically update the node's aging differentiation parameters. The specific operation is to select the node operation data in the most recent period of time (for example, the past 24 hours), and to count the node performance indicator change trends within the window, such as the increase in response delay, the intensification of voltage fluctuations, and the frequency of temperature anomalies, and to infer the actual aging rate of the node in combination with the historical aging model. The sliding time window method is characterized by the continuous forward movement of the window and the continuous updating of parameters to ensure the timeliness and accuracy of the aging evaluation. The resulting node aging differentiation update parameters reflect the changes in the health status of different nodes during use, which facilitates targeted maintenance and scheduling optimization.

[0146] Step S55: calibrate and optimize the node health status assessment model using node aging differentiation update parameters to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

[0147] The embodiments of the present invention utilize dynamically updated node aging differentiation parameters to calibrate and optimize the node health status assessment model. The specific method involves inputting the latest aging parameters into the health model and adjusting the performance decay weights and risk thresholds of each node in the model to produce accurate health assessment results. Through this closed-loop mechanism, energy storage power stations can provide real-time feedback on node status changes, dynamically adjust operating strategies and maintenance plans, and achieve full lifecycle management of node health. This mechanism effectively improves the reliability and cost-effectiveness of energy storage systems and is suitable for long-term operation monitoring and management of large-scale energy storage power stations.

[0148] The present invention further provides an energy storage power station operation monitoring and management system for executing the above-mentioned energy storage power station operation monitoring and management method, the energy storage power station operation monitoring and management system comprising:

[0149] The voltage characteristic acquisition module is used to obtain the voltage data of each energy storage node in the static state and perform periodic voltage sampling during the preset static time to obtain voltage rebound time series data; the voltage rebound time series data is temperature corrected to obtain standardized voltage rebound characteristic data;

[0150] The health status assessment module is used to obtain the state of charge data of each energy storage node before and after operation; calculate the charge and discharge depth change value of each node based on the state of charge data; construct a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth change value, and obtain the node aging differentiation parameters;

[0151] The capacity grading and allocation module is used to determine the available capacity level of each node based on the node aging differentiation parameters; calculate the optimal working range of each node based on the available capacity level to obtain node operation capacity grading data; and use the node operation capacity grading data to establish a node charging and discharging power allocation model;

[0152] The energy flow intelligent allocation module is used to obtain the overall power dispatch instructions of the energy storage power station; the overall power dispatch instructions are decomposed and processed according to the node charging and discharging power allocation model to obtain the node differentiated power allocation plan; the node differentiated power allocation plan is dynamically optimized using the minimum power perturbation method to obtain the adaptive energy flow allocation instructions;

[0153] The closed-loop monitoring and optimization module is used to issue adaptive energy flow allocation instructions to each energy storage node and monitor the real-time operating status of each node after executing the adaptive energy flow allocation instructions. Based on the real-time operating status, the node aging differentiation parameters are updated to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

[0154] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0155] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring and managing the operation of an energy storage power station, characterized in that: The following steps are involved: Step S1: Obtain voltage data of each energy storage node in a static state, and perform periodic voltage sampling within a preset static time to obtain voltage rebound time series data; Perform temperature correction on the voltage rebound time series data to obtain standardized voltage rebound characteristic data; Step S2: Obtain the state of charge data of each energy storage node before and after operation; calculate the charge and discharge depth change value of each node based on the state of charge data; construct a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth change value to obtain the node aging differentiation parameter; Step S3: Determine the available capacity level of each node based on the node aging differentiation parameter; Calculate the optimal operating range of each node based on the available capacity level to obtain node operation capacity classification data; use the node operation capacity classification data to establish a node charging and discharging power allocation model; Step S4: Obtaining the overall power dispatch instruction of the energy storage power station; decomposing the overall power dispatch instruction according to the node charging and discharging power allocation model to obtain a node differentiated power allocation scheme; dynamically optimizing the node differentiated power allocation scheme using the minimum power perturbation method to obtain an adaptive energy flow allocation instruction; Step S5: Send adaptive energy flow allocation instructions to each energy storage node and monitor the real-time operating status of each node after executing the adaptive energy flow allocation instructions; update the node aging differentiation parameters based on the real-time operating status to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

2. The energy storage power station operation monitoring and management method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: determining a rest time parameter according to pre-acquired cell model characteristics of each energy storage node, thereby obtaining rest time configuration data; Step S12: Controlling the energy storage node to enter a rest mode according to the rest time configuration data, interrupting all charging and discharging operations, and obtaining a node rest state confirmation signal; Step S13: After receiving the node static state confirmation signal, start the periodic voltage sampling process to record the voltage changes of each energy storage node based on the preset sampling frequency to obtain the original voltage time series sampling data; Step S14: performing time series arrangement and preliminary screening on the original voltage time series sampling data, removing abnormal data points, and forming voltage rebound time series data; Step S15: performing temperature correction processing on the voltage rebound time series data to obtain standardized voltage rebound characteristic data.

3. The energy storage power station operation monitoring and management method according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: setting the state of charge detection time window parameters to be suitable for the state of charge acquisition frequency of each energy storage node type, and obtaining state of charge monitoring configuration data; Step S22: collecting terminal voltage, current, and temperature at specific moments before and after the node charge and discharge process according to the state of charge monitoring configuration data to obtain raw data on the node state before and after operation; Step S23: Preliminary filtering and calibration of the original data of the node state before and after operation to eliminate the influence of measurement interference and transient fluctuations, and obtain effective state of charge data; Step S24: Calculate the state of charge change of each energy storage node within a complete operation cycle based on the effective state of charge data to obtain a preliminary assessment value of the node's charge and discharge depth; Step S25: Correcting the preliminary evaluation value of the node charge and discharge depth based on the actual operation time of the node and the charge and discharge current, thereby obtaining a charge and discharge depth change value; Step S26: constructing a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth variation value to obtain node aging differentiation parameters.

4. The energy storage power station operation monitoring and management method according to claim 3, characterized in that: Step S26 includes the following steps: Step S261: performing data fusion matching based on the standardized voltage rebound characteristic data and the charge and discharge depth change value to construct a node operation behavior characteristic matrix; Step S262: Analyze the correlation between voltage rebound characteristics and charge / discharge depth based on the node operation behavior characteristic matrix, thereby establishing a preliminary node health assessment model; Step S263: Calibrate the parameter weights in the preliminary node health assessment model using pre-acquired historical operation data, optimize the model response characteristics, and thus obtain a node health status assessment model; Step S264: Quantitatively analyze the current status of each node using the node health status assessment model, and output comparable health status difference indicators, thereby obtaining node aging difference parameters.

5. The energy storage power station operation monitoring and management method according to claim 4, characterized in that: Determining the available capacity level of each node according to the node aging differentiation parameter in step S3 includes: The node aging differentiation parameters are normalized based on the 0-1 normalization method to eliminate the influence of different dimensions and obtain the standardized aging parameters; Based on the standardized aging parameters, the aging parameter threshold interval [0.15, 0.35, 0.55, 0.75] was set as the classification boundary point, and segmented mapping was performed to obtain the preliminary aging grade classification results; Based on the preliminary aging grade classification results and the pre-acquired node rated capacity values ​​of each energy storage node, the actual capacity loss rate is calculated based on the loss rate calculation formula, where the loss rate calculation formula is loss rate = basic loss rate + aging grade coefficient × attenuation acceleration factor; Dynamically correct the actual capacity loss rate. For nodes with an operating time of more than 1,000 hours, add a 0.8% correction value to the original loss rate for every additional 500 hours to obtain the corrected capacity loss rate. Calculate the actual available capacity percentage of the node based on the corrected capacity loss rate, where the actual available capacity percentage of the node = 100% - the corrected capacity loss rate; set capacity grading standards based on the actual available capacity percentage of the node to form a node capacity grading standard; Based on the node capacity grading standard, the actual available capacity percentage of each node is graded and divided to obtain the node available capacity grade data; The nodes with adjacent level boundary values ​​are extracted from the node available capacity level data, and a secondary correction is performed based on the stable voltage recovery rate in the voltage rebound feature data. When the recovery rate is lower than the threshold, the node level is lowered by one level to obtain the available capacity level.

6. The energy storage power station operation monitoring and management method according to claim 5, characterized in that: Step S3 includes the following steps: Establishing a mapping relationship between capacity level and state-of-charge operating range based on available capacity level to obtain preliminary state-of-charge operating range data; The voltage-state of charge curve of each node under standard charge and discharge conditions is collected, and the area where the voltage change rate is less than 0.05V / 1%SOC is selected as the voltage platform area to obtain the node voltage platform interval data; Based on the node voltage platform interval data and the preliminary state-of-charge operating range data, the operating range is optimized and adjusted to ensure that the operating range includes at least 75% of the voltage platform area, and the adjusted operating range data is obtained; Perform constant power charge and discharge tests on each node at a 0.5C rate, record the terminal voltage change rate at different states of charge, and obtain voltage response characteristic data; Based on the voltage response characteristic data, the internal resistance change trend of each node under different charge states is calculated. Taking the point where the internal resistance increases by 20% as the boundary, the working range boundary is further optimized to obtain the internal resistance optimized working range data; The intersection of the adjusted working range data and the internal resistance optimized working range data is calculated as the node's safe working range. The available range width is divided into the following categories: width greater than 70% is level 1, 50%-70% is level 2, 30%-50% is level 3, and less than 30% is level 4, thus obtaining the node working range grade data. A two-dimensional evaluation matrix is ​​established based on the node working range level data and available capacity level data to obtain the node's preliminary operating capability level; The power response capability test is performed on the node's preliminary operational capability level to obtain a power response capability rating. The power response capability test specifically applies a pulse power of 0.8C within the safe operating range for 30 seconds and records the voltage drop. A voltage drop of less than 0.15V is considered excellent, 0.15V-0.25V is considered good, 0.25V-0.35V is considered fair, and greater than 0.35V is considered poor. The node operation capability classification is determined based on the node's preliminary operation capability level and power response capability rating, forming node operation capability classification data including three-dimensional characteristics of capacity status, working range and power response.

7. The energy storage power station operation monitoring and management method according to claim 6, characterized in that: The establishment of a node charging and discharging power allocation model using the node operation capability classification data in step S3 includes: Based on the node operation capability classification data, a basic power weight coefficient is assigned to each node to obtain a node basic power weight coefficient table; Collect the charge and discharge efficiency data of each node at different states of charge, perform sampling tests at intervals of 10% state of charge, record the energy conversion efficiency of each sampling point, and obtain the node charge and discharge efficiency curve; Based on the node charge and discharge efficiency curve, the optimal charge and discharge efficiency range of each node is calculated, and the area with efficiency higher than 90% is defined as the optimal working point to obtain the node efficiency optimization range data; Combine the node efficiency optimization interval data and the node safe working interval to calculate the intersection area of ​​the two as the node priority scheduling interval, and obtain the node priority scheduling interval data; design the power allocation coefficient within the interval based on the node priority scheduling interval data; Monitor the current state of charge of the node in real time and calculate the distance ratio between the current state of charge and the boundary of the priority scheduling interval. When the distance ratio is less than 0.2, the basic power weight coefficient is linearly attenuated to obtain the boundary adjustment coefficient. Monitor the node temperature change status and set the normal operating temperature range to 15℃-35℃. When the temperature exceeds this range, the basic power weight coefficient is attenuated by 5% for every 5℃ increase or decrease to obtain the temperature correction coefficient. A node charging and discharging power allocation model is established based on the power allocation coefficient within the range, the boundary adjustment coefficient, and the temperature correction coefficient.

8. The energy storage power station operation monitoring and management method according to claim 7, characterized in that: Step S4 includes the following steps: Step S41: Obtain the overall power dispatch instruction of the energy storage power station, parse the instruction and extract the charging and discharging power demand value, duration parameter and response time requirement to obtain a power dispatch parameter set; Step S42: Calculate the preliminary power allocation coefficient of each energy storage node based on the power scheduling parameter set and the node charge and discharge power allocation model to obtain a preliminary power allocation plan; Step S43: Calculate the upper and lower limits of the loadable power of each node based on the preliminary power allocation plan and the node operation capability classification data of each energy storage node to obtain the node power constraint conditions; Step S44: Correcting the preliminary power allocation plan according to the node power constraint conditions to ensure that the power value allocated to each node does not exceed its safe operating range, thereby obtaining a safe corrected power allocation plan; Step S45: Calculate the deviation between the current state of charge of each node and its optimal working range, calculate the interval deviation adjustment coefficient, optimize the safety correction power allocation plan, and obtain a balanced optimized power allocation plan; Step S46: Monitor the real-time temperature change trend of each node. When the temperature change rate exceeds a preset threshold, calculate the temperature risk coefficient and dynamically adjust the balance optimization power allocation scheme to obtain a temperature adaptive power allocation scheme. Step S47: forming a node-differentiated power allocation scheme based on the temperature-adaptive power allocation scheme, including power allocation values ​​for each node and an execution order; Step S48: Dynamically optimize the node differentiated power allocation scheme using the minimum power perturbation method to obtain an adaptive energy flow allocation instruction.

9. The energy storage power station operation monitoring and management method according to claim 8, characterized in that: Step S5 includes the following steps: Step S51: Generate an operation control command for each energy storage node including a specific charge and discharge power setting value and a timing execution arrangement according to the adaptive energy flow distribution instruction, and send the operation control command to each energy storage node to trigger the node to perform the corresponding charge and discharge operation; Step S52: Start the energy storage node real-time operation status monitoring program, collect the voltage, current, temperature and charge state of each node, and form a node real-time operation status data stream; Step S53: Perform online analysis on the node real-time operation status data stream, calculate the power response delay time, voltage fluctuation amplitude and temperature change rate of each node, and generate a node operation characteristic evaluation report; Step S54: updating the node aging differentiation parameter using a sliding time window method according to the node operation characteristic evaluation report, dynamically evaluating the aging rate, and obtaining the node aging differentiation update parameter; Step S55: calibrate and optimize the node health status assessment model using node aging differentiation update parameters to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

10. An energy storage power station operation monitoring and management system, characterized in that: Used to execute the energy storage power station operation monitoring and management method according to claim 1, the energy storage power station operation monitoring and management system comprises: The voltage characteristic acquisition module is used to obtain the voltage data of each energy storage node in the static state and perform periodic voltage sampling during the preset static time to obtain voltage rebound time series data; the voltage rebound time series data is temperature corrected to obtain standardized voltage rebound characteristic data; The health status assessment module is used to obtain the state of charge data of each energy storage node before and after operation; calculate the charge and discharge depth change value of each node based on the state of charge data; construct a node health status assessment model based on the standardized voltage rebound characteristic data and the charge and discharge depth change value, and obtain the node aging differentiation parameters; The capacity grading and allocation module is used to determine the available capacity level of each node based on the node aging differentiation parameters; calculate the optimal working range of each node based on the available capacity level to obtain node operation capacity grading data; and use the node operation capacity grading data to establish a node charging and discharging power allocation model; The energy flow intelligent allocation module is used to obtain the overall power dispatch instructions of the energy storage power station; the overall power dispatch instructions are decomposed and processed according to the node charging and discharging power allocation model to obtain the node differentiated power allocation plan; the node differentiated power allocation plan is dynamically optimized using the minimum power perturbation method to obtain the adaptive energy flow allocation instructions; The closed-loop monitoring and optimization module is used to issue adaptive energy flow allocation instructions to each energy storage node and monitor the real-time operating status of each node after executing the adaptive energy flow allocation instructions. Based on the real-time operating status, the node aging differentiation parameters are updated to form a closed-loop optimized energy storage power station operation monitoring and management mechanism.

Images