A collaborative optimization method and system for trading and operation and maintenance based on the health status constraints of energy storage devices.

By constructing a collaborative optimization method for energy storage equipment health status constraints in trading and operation and maintenance, the problem of data disconnect between market-oriented profitability and safe operation and maintenance of energy storage power stations has been solved. This method enables dynamic adaptation of trading strategies and equipment health management, thereby improving the market participation capability and operational efficiency of energy storage power stations.

CN123117576APending Publication Date: 2026-11-17SHANGHAI BOYUE INTELLIGENT ELECTRIC ENERGY TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610981228.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-07-02
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Energy storage power stations face challenges in achieving market-driven profitability and safe operation and maintenance, including data fragmentation, crude decision-making, lagging risk control, and insufficient coordination between energy storage and trading. These issues hinder integrated management, resulting in underutilized revenue potential and low operational efficiency.

Method used

By constructing a health status constraint trading and operation and maintenance collaborative optimization method for energy storage equipment, multi-source heterogeneous data is acquired, a health status model of the equipment is established, a basic dataset for trading and operation and maintenance collaboration is generated, health assessment and optimization calculations are performed, a set of trading strategies is generated, and execution feedback is obtained in real time for dynamic adjustment, forming a closed-loop optimization mechanism.

Benefits of technology

It achieves a deep integration of transaction revenue optimization and equipment health management, improves the market transaction reliability and operational efficiency of energy storage power stations, reduces fault response time and maintenance costs, and ensures equipment safety and controllability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123117576A_ABST
    Figure CN123117576A_ABST
Patent Text Reader

Abstract

This invention relates to the field of power system technology and discloses a method and system for collaborative optimization of trading and operation and maintenance based on the health status constraints of energy storage equipment. First, market trading data, equipment operation data, environmental status data, and operation and maintenance management data are collected to construct a basic dataset for collaborative trading and operation and maintenance. Then, an equipment health status constraint model is established to comprehensively evaluate the available capacity, available power, lifespan loss level, and operational risk level of the energy storage equipment, generating a set of equipment health constraint parameters. Further, a collaborative optimization model for trading and operation and maintenance is constructed, achieving joint optimization of revenue and lifespan through an equipment health index model, a trading revenue model, and a lifespan loss model, generating charge / discharge power curves, SOC control curves, and market pricing strategies. Finally, dynamic corrections and anomaly investigations are performed based on execution feedback data to achieve closed-loop collaborative optimization of trading decisions, equipment operation, and operation and maintenance management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of power system technology, specifically to a method and system for collaborative optimization of operation and maintenance based on the health status constraints of energy storage devices. Background Technology

[0002] Against the backdrop of accelerated construction of new power systems and the deepening of power market reforms, energy storage power stations, as core new entities for regulating power supply and demand and participating in market profitability, face the dual core demands of "market-based profitability" and "safe operation and maintenance." On the one hand, with multiple markets such as medium- and long-term electricity trading, spot trading, and ancillary services operating in parallel, complex trading rules, volatile electricity prices, and fierce market competition, traditional manual trading models suffer from problems such as data fragmentation, crude decision-making, lagging risk control, and insufficient coordination between energy storage and trading, making it difficult to fully tap the market profitability potential of energy storage power stations. On the other hand, energy storage power stations are characterized by dense equipment and high operational complexity, generally suffering from pain points such as decentralized monitoring, untimely fault prediction, non-standardized operation and maintenance processes, weak battery life management, and low efficiency in multi-station operation and maintenance. High safety risks and operation and maintenance costs directly constrain the long-term operation of energy storage power stations. Furthermore, power trading and energy storage operation and maintenance are mostly independent systems, resulting in data incompatibility, business disconnect, and fragmented management, making it difficult to meet the integrated management needs of market participants for energy storage power stations that are "safe and controllable, with optimal returns and efficient operation." To address the industry challenges of fragmented business operations, data silos, and the difficulty in balancing profitability and security, and to establish a collaborative link between power trading and energy storage operation and maintenance, thereby achieving dual empowerment of improved profitability and safe operation and maintenance, it is urgent to build a smart management platform for energy storage power stations to provide one-stop support for the entire life cycle operation of energy storage power stations. Summary of the Invention

[0003] To achieve the above-mentioned objectives, this invention provides the following technical solution: a collaborative optimization method for operation and maintenance based on the health status constraints of energy storage devices, comprising the following steps: Step S1: Obtain market transaction data, equipment operation data, environmental status data, and operation and maintenance management data of energy storage power stations; perform multi-source heterogeneous fusion processing on the market transaction data, equipment operation data, environmental status data, and operation and maintenance management data to construct an energy storage power station operation status feature set and generate a transaction and operation and maintenance collaborative basic dataset. Step S2: Based on the transaction operation and maintenance collaboration basic dataset, perform a health assessment and analysis on the operating status of energy storage equipment, establish an equipment health status constraint model, comprehensively calculate the current available capacity, available power, life loss level and operating risk level of the energy storage equipment, and generate a set of equipment health constraint parameters. Step S3: Based on the set of equipment health constraint parameters and market transaction forecast results, construct a collaborative optimization model for transaction operation and maintenance under the constraints of the health status of energy storage equipment. Jointly evaluate the health status of energy storage equipment, market revenue level and equipment life loss, generate transaction revenue evaluation results and life loss evaluation results, and perform collaborative optimization calculations on the transaction strategies of energy storage power stations participating in the electricity spot market, medium and long-term trading market and ancillary service market based on the transaction revenue evaluation results and life loss evaluation results, generate a set of transaction execution strategies including charge and discharge power curves, SOC control curves, market pricing strategies and revenue forecast results; Step S4: Control the energy storage power station to execute charging and discharging trading tasks according to the transaction execution strategy set, and obtain execution feedback data in real time. Perform dynamic analysis on execution deviation, abnormal equipment status and operation and maintenance handling results. Iteratively update the equipment health constraint parameter set and transaction execution strategy set according to the analysis results to form a closed-loop optimization mechanism for transaction decision-making, equipment operation and operation and maintenance management.

[0004] Preferably, step S1 specifically includes: Real-time electricity price data, day-ahead electricity price data, medium- and long-term transaction price data, ancillary service market price data, and market transaction data for the target trading period are obtained through the electricity market interface. Ambient temperature data, ambient humidity data, solar radiation data, wind speed data, and weather forecast data are obtained through a meteorological data acquisition platform. The energy storage power station monitoring system acquires battery cluster operation data, PCS operation data, BMS operation data, EMS operation data, and historical operation data. The operation and maintenance management platform is used to obtain equipment inspection record data, maintenance plan data, fault work order data, spare parts management data, and equipment history data. Establish a mapping relationship between market information, equipment operation, environmental impact and operation and maintenance management dimensions, and perform time synchronization, anomaly removal, missing data compensation and standardization on the collected data. Based on the processed data, construct a market revenue feature matrix, an equipment status feature matrix, an environmental impact feature matrix, and an operation and maintenance status feature matrix. Further, an analysis model for the coupling relationship between trading and operation and maintenance is established. Correlation feature extraction and dynamic weight fusion processing are performed on each feature matrix to generate a basic dataset for trading and operation and maintenance collaboration. The basic dataset for trading and operation and maintenance collaboration includes market return representation information, equipment operation representation information, lifespan loss representation information, risk status representation information, and operation and maintenance resource representation information.

[0005] Preferably, step S2 specifically includes: Based on the aforementioned transaction operation and maintenance collaborative basic dataset, battery state of charge information, battery health status information, battery temperature distribution information, battery consistency information, battery cycle count information, and fault alarm information are extracted. A health status assessment model is constructed to predict and analyze the trends of battery capacity decay, battery internal resistance change, thermal runaway risk, and equipment failure probability. Based on the prediction and analysis results, an equipment health evaluation index system is calculated, which includes capacity health index, power health index, safety health index, lifespan health index, and operation and maintenance support index. Based on the equipment health evaluation index system, an equipment health status constraint model is established to dynamically calculate the maximum available capacity, maximum charging power, maximum discharging power, and allowable operating range of energy storage equipment within the target trading cycle. Further, the life loss cost corresponding to the unit revenue is calculated by combining the equipment life value assessment model, and a health constraint boundary is established based on the life loss cost. A set of equipment health constraint parameters is generated based on the equipment health status constraint model. The set of equipment health constraint parameters includes equipment available capacity constraint parameters, equipment available power constraint parameters, equipment lifetime loss constraint parameters, equipment safe operation constraint parameters, and equipment operation and maintenance support constraint parameters.

[0006] Preferably, step S3 specifically includes: A collaborative optimization model for transaction operation and maintenance is established based on historical market transaction data, real-time market transaction data, power grid load forecast data, and the set of equipment health constraint parameters generated in step S2. First, extract the device health status parameters, including battery health status. Temperature Anomaly Index and battery consistency index And construct an equipment health index model. : ; in: ; , as well as These represent the weights for health status, temperature status, and consistency status, respectively. According to equipment health index Calculate the available capacity boundary, available power boundary, and safe operating boundary of the equipment, and formulate equipment health constraints; A power price forecast series for the next 96 time periods was established based on current market price data, real-time market price data, and load forecast results. ; Based on the predicted electricity price sequence and the energy storage device charging and discharging power sequence Calculate the expected return over the trading cycle : ; in: Indicates the first Charge and discharge power over time period; Indicates the first Forecasted electricity prices for different time periods; Based on charge / discharge depth Number of loops and equipment health status Establish a lifetime attrition model and calculate lifetime attrition costs: ; Further establish a synergistic optimization objective function for transaction revenue and equipment lifespan: ; in: To comprehensively optimize the target value; To predict transaction profits; Costs related to lifespan depletion; This refers to the lifetime constraint weighting coefficient. According to the objective function The optimal charging and discharging strategy for the target trading period is obtained by jointly optimizing spot market transactions, medium- and long-term transactions, and ancillary service market transactions. Based on the optimal charging and discharging strategy, a 96-period charging and discharging power curve, a SOC control curve, a market pricing strategy, and profit forecast results are generated, forming a set of trading execution strategies.

[0007] Preferably, step S4 specifically includes: The transaction execution strategy set is distributed to the energy storage power station EMS system for execution, and charging and discharging power data, SOC change data, equipment operating status data and market execution result data are collected in real time during the execution process; An execution deviation analysis model is established to monitor in real time the deviations between planned power and actual power, planned SOC and actual SOC, and planned revenue and actual revenue. When the execution deviation exceeds the preset threshold, a dynamic correction mechanism is activated to re-optimize the trading strategy for the remaining trading cycle. When equipment failure, equipment performance degradation, abnormal equipment temperature, or sudden changes in the market environment are detected, an anomaly investigation task is automatically generated and pushed to the operation and maintenance management platform. The equipment health status constraint model is updated based on the operation and maintenance handling results. Recalculate the equipment health constraint parameter set based on the updated equipment health status constraint model; The transaction execution strategy set is revised based on the regenerated set of device health constraint parameters; By continuously looping through the processes of equipment status feedback, strategy correction, anomaly handling, and parameter updates, a closed-loop collaborative optimization operation is achieved between the transaction decision system, the operation and maintenance management system, and the EMS execution system.

[0008] This invention also provides a collaborative optimization system for operation and maintenance based on the health status constraints of energy storage devices, comprising the following modules: The data collaboration and analysis module is used to acquire market transaction data, equipment operation data, environmental status data, and operation and maintenance management data, and to build a basic dataset for transaction and operation and maintenance collaboration. The health constraint decision module is used to establish a device health status constraint model based on the transaction operation and maintenance collaboration basic dataset, and generate a set of device health constraint parameters and a set of transaction execution strategies. The execution feedback optimization module is used to execute transaction execution strategies, perform feedback analysis on equipment operating status and execution results, and complete collaborative handling of anomalies and dynamic optimization control.

[0009] The data collaborative analysis module includes: The data acquisition unit is used to collect real-time electricity price data, day-ahead electricity price data, medium- and long-term transaction data, ancillary service market data, and historical transaction data through the electricity market interface; to collect battery cluster operation data, PCS operation data, BMS operation data, EMS operation data, and fault alarm data through the energy storage power station monitoring network; to collect ambient temperature data, ambient humidity data, wind speed data, light intensity data, and weather forecast data through the meteorological service platform; and to collect inspection record data, maintenance plan data, work order processing data, and equipment history data through the operation and maintenance management platform. The data fusion unit is used to perform unified timestamp processing, outlier identification processing, missing data compensation processing, and standardization processing on the collected data, establish the correlation mapping relationship between market data, equipment data, environmental data, and operation and maintenance data, and form multi-source heterogeneous data fusion results according to unified data coding rules. The feature construction unit is used to construct market revenue feature sets, equipment operation feature sets, environmental impact feature sets, and operation and maintenance status feature sets based on the data fusion results. It performs correlation analysis and dynamic weight fusion on features of different dimensions to generate a basic dataset for transaction operation and maintenance collaboration.

[0010] The health constraint decision module includes: The health assessment unit is used to receive the basic dataset for transaction operation and maintenance collaboration, extract battery state of charge information, battery health status information, battery temperature distribution information, battery consistency information, battery cycle life information, and fault alarm information, establish an equipment health assessment model, analyze and calculate the degree of equipment capacity decay, internal resistance growth trend, thermal runaway risk level, and fault occurrence probability, and generate equipment health evaluation results. The constraint generation unit is used to establish a constraint model for the health status of the equipment based on the equipment health assessment results. It calculates the current available capacity, available charging power, available discharging power, safe operating range, and life loss boundary of the energy storage equipment, forms a set of equipment health constraint parameters, and dynamically adjusts the constraint boundary according to the equipment operation risk level. The collaborative optimization unit receives the set of equipment health constraint parameters and market forecast results, establishes a multi-objective collaborative optimization model among market revenue objectives, equipment life objectives, and operational safety objectives, and performs joint optimization calculations on spot transactions, medium- and long-term transactions, and ancillary service transactions based on power plant capacity constraints, SOC operation constraints, market transaction rules, and equipment health constraints. It generates a set of transaction execution strategies consisting of a charge / discharge plan, an SOC control plan, a transaction pricing plan, and a risk warning plan, and performs revenue and risk assessments on the set of transaction execution strategies.

[0011] The execution feedback optimization module includes: The execution control unit is used to receive the transaction execution strategy set generated by the health constraint decision module, and convert the transaction execution strategy set into control instructions that can be executed by the EMS system, and control the energy storage device to execute the corresponding transaction tasks according to the preset charging and discharging plan, SOC control plan and auxiliary service plan; The status feedback unit is used to collect real-time data on actual charging and discharging power of energy storage devices, SOC change data, battery temperature data, equipment alarm data, market transaction results data, and revenue settlement data. It monitors and analyzes the deviation between the planned execution results and the actual execution results, and generates an execution feedback dataset. The closed-loop optimization unit is used to establish an execution deviation analysis model based on the execution feedback dataset, and to comprehensively evaluate power deviation, SOC deviation, revenue deviation and equipment status deviation. When equipment failure, power abnormality, SOC abnormality, market environment change or revenue deviation exceeds the limit is detected, the dynamic correction mechanism is automatically triggered to recalculate the trading strategy for the remaining trading cycle. The closed-loop optimization unit is also used to generate anomaly investigation work orders and push them to the corresponding operation and maintenance personnel's terminals. It receives fault diagnosis results, on-site handling results, and operation and maintenance feedback results. Based on the feedback results, it updates the equipment health status parameters, life loss parameters, and risk assessment parameters, and feeds the updated parameters back to the health constraint decision module. This enables data closed-loop collaborative optimization operation between the transaction auxiliary decision system, the intelligent operation and maintenance system, and the energy storage power station EMS execution system.

[0012] Compared with existing technologies, the transaction operation and maintenance collaborative optimization method and system based on the health status constraints of energy storage equipment proposed in this invention achieves a deep integration of transaction revenue optimization and equipment health management by constructing a closed-loop linkage mechanism of transaction decision-making, equipment health assessment, operation and maintenance collaboration, and execution feedback, and has the following beneficial effects: First, this invention overcomes the limitations of traditional energy storage trading systems that solely rely on market prices and returns for strategy formulation. It incorporates factors such as the operating status, health condition, and failure risks of energy storage equipment into the trading decision-making process, establishing a collaborative optimization model between trading returns and equipment lifespan. When generating charging and discharging strategies, it considers not only electricity price forecasts and market trading rules but also key parameters such as battery SOC, SOH, temperature distribution, voltage consistency, and cycle life. This avoids the problem of accelerated battery degradation due to excessive pursuit of short-term gains, thereby maximizing the returns of energy storage assets throughout their entire lifecycle.

[0013] Secondly, this invention achieves data integration and business collaboration between the transaction support decision-making system and the intelligent operation and maintenance system. By acquiring the real-time operating status, fault information, and maintenance plans of energy storage equipment, the trading strategy can dynamically adapt to the actual operating capacity of the equipment. When equipment experiences performance degradation, capacity limitations, or increased fault risk, the system can automatically adjust charging and discharging strategies and pricing strategies, preventing transaction execution failures and deviation assessment problems caused by insufficient equipment capacity from the source, thereby improving the reliability and success rate of energy storage power stations participating in electricity market transactions.

[0014] Furthermore, this invention establishes a closed-loop optimization mechanism based on EMS execution feedback. After the charging and discharging strategy is issued, the system can continuously receive information such as actual power, actual SOC, equipment status, and execution deviation from the EMS, and perform real-time comparison and analysis with the trading plan. When the execution deviation exceeds a preset threshold, the system automatically triggers a strategy re-optimization mechanism to dynamically correct subsequent charging and discharging plans, enabling the trading strategy to continuously adapt to changes in the power grid operating environment and equipment operating status, thereby improving the execution accuracy and market responsiveness of the trading strategy.

[0015] Fourth, this invention innovatively constructs an automatic linkage mechanism for anomaly investigation. When the system identifies equipment anomalies, power deviation anomalies, SOC deviation anomalies, or transaction execution anomalies, it can automatically generate an anomaly investigation work order and push it to the intelligent operation and maintenance system, realizing automatic collaboration between the transaction system and the operation and maintenance system. Compared with existing technologies that rely on telephone, instant messaging tools, or manual communication, this invention can significantly shorten the anomaly response time, improve the efficiency of fault location and handling, and reduce the impact of anomalies on transaction revenue and equipment safety.

[0016] Fifth, this invention achieves unified optimization of revenue, safety, and lifespan objectives by establishing equipment health evaluation models, fault risk evaluation models, and a joint revenue and loss evaluation model. The system not only outputs the optimal charging and discharging strategy but also simultaneously assesses the impact of this strategy on battery lifespan, providing operators with a more scientific and reasonable basis for decision-making, thereby effectively reducing battery replacement costs. Attached Figure Description

[0017] Figure 1 A flowchart illustrating the method steps provided in this application; Figure 2 A schematic diagram of the system modules provided in this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] refer to Figure 1 This invention provides a method for collaborative optimization of trading and operation and maintenance based on the health status constraints of energy storage devices, including the following steps: Step S1: Obtain market transaction data, equipment operation data, environmental status data, and operation and maintenance management data of energy storage power stations; perform multi-source heterogeneous fusion processing on the market transaction data, equipment operation data, environmental status data, and operation and maintenance management data to construct an energy storage power station operation status feature set and generate a transaction and operation and maintenance collaborative basic dataset. Step S2: Based on the transaction operation and maintenance collaboration basic dataset, perform a health assessment and analysis on the operating status of energy storage equipment, establish an equipment health status constraint model, comprehensively calculate the current available capacity, available power, life loss level and operating risk level of the energy storage equipment, and generate a set of equipment health constraint parameters. Step S3: Based on the set of equipment health constraint parameters and market transaction forecast results, construct a collaborative optimization model for transaction operation and maintenance under the constraints of the health status of energy storage equipment. Jointly evaluate the health status of energy storage equipment, market revenue level and equipment life loss, generate transaction revenue evaluation results and life loss evaluation results, and perform collaborative optimization calculations on the transaction strategies of energy storage power stations participating in the electricity spot market, medium and long-term trading market and ancillary service market based on the transaction revenue evaluation results and life loss evaluation results, generate a set of transaction execution strategies including charge and discharge power curves, SOC control curves, market pricing strategies and revenue forecast results; Step S4: Control the energy storage power station to execute charging and discharging trading tasks according to the transaction execution strategy set, and obtain execution feedback data in real time. Perform dynamic analysis on execution deviation, abnormal equipment status and operation and maintenance handling results. Iteratively update the equipment health constraint parameter set and transaction execution strategy set according to the analysis results to form a closed-loop optimization mechanism for transaction decision-making, equipment operation and operation and maintenance management.

[0020] First, the system acquires real-time electricity price data, day-ahead electricity price data, medium- and long-term transaction price data, ancillary service market price data, and market transaction data within the target trading period through the electricity market interface; it acquires battery cluster operation data, PCS operation data, BMS operation data, EMS operation data, and historical operation data through the energy storage power station monitoring system; it acquires environmental status data and weather forecast data through the meteorological acquisition platform; and it acquires equipment inspection record data, maintenance plan data, fault work order data, and equipment history data through the operation and maintenance management platform. The system performs time synchronization processing, anomaly removal processing, missing data compensation processing, and standardization processing on the above data, establishes the correlation mapping relationship between market information dimension, equipment operation dimension, environmental impact dimension, and operation and maintenance management dimension, and constructs market revenue feature matrix, equipment status feature matrix, environmental impact feature matrix, and operation and maintenance status feature matrix. Subsequently, the system uses the transaction operation and maintenance coupling relationship analysis model to extract correlation features and perform dynamic weight fusion processing on each feature matrix to generate a transaction operation and maintenance collaborative basic dataset. The transaction operation and maintenance collaborative basic dataset includes market return representation information, equipment operation representation information, lifespan loss representation information, risk status representation information, and operation and maintenance resource representation information, and serves as the data basis for subsequent equipment health status assessment.

[0021] Subsequently, the system extracts battery state of charge information, battery health status information, battery temperature distribution information, battery consistency information, battery cycle count information, and fault alarm information based on the transaction operation and maintenance collaboration basic dataset. It then constructs an equipment health status assessment model, predictively analyzing battery capacity decay trends, battery internal resistance change trends, thermal runaway risk trends, and equipment failure probability trends. This forms an equipment health evaluation index system composed of capacity health indicators, power health indicators, safety health indicators, lifespan health indicators, and operation and maintenance support indicators. Based on this, an equipment health status constraint model is established to dynamically calculate the available capacity range, charge / discharge capacity range, and safe operating range of the energy storage equipment within the target transaction cycle. Simultaneously, combined with an equipment lifespan value assessment model, the system evaluates the potential lifespan loss costs of the equipment under different operating conditions. Based on the lifespan loss assessment results, health constraint boundaries are established, ultimately generating an equipment health constraint parameter set. This set includes equipment available capacity constraint parameters, equipment available power constraint parameters, equipment lifespan loss constraint parameters, equipment safe operation constraint parameters, and equipment operation and maintenance support constraint parameters, which serve as input conditions for the transaction collaboration optimization stage.

[0022] Next, the system establishes a collaborative optimization model for transaction operation and maintenance based on historical market transaction data, real-time market transaction data, power grid load forecast data, and the set of equipment health constraint parameters generated in step S2. First, extract the device health status parameters, including battery health status. Temperature Anomaly Index and battery consistency index And construct an equipment health index model. : ; in: ; , as well as These represent the weights for health status, temperature status, and consistency status, respectively. The system is based on the equipment health index Calculate the current available capacity boundary, available power boundary, and safe operation boundary of the energy storage device, and formulate equipment health constraints, including the equipment health index. A higher health index indicates a better overall operating condition of the equipment and a stronger ability to participate in market transactions. When the load is reduced, the system automatically tightens the charging and discharging capacity constraints and the SOC operating constraints to reduce the risk of equipment lifespan loss.

[0023] Subsequently, the system establishes a future electricity price forecast sequence based on day-ahead market price data, real-time market price data, and load forecasting results. And combined with the charging and discharging power sequence of energy storage devices Calculate the expected return over the trading cycle : ; in: Indicates the first Charge and discharge power over time period; Indicates the first Forecasted electricity prices for different time periods; Based on charge / discharge depth Number of loops and equipment health status Establish a lifetime attrition model and calculate lifetime attrition costs. : ; Further establish a synergistic optimization objective function for transaction revenue and equipment lifespan: ; in: To comprehensively optimize the target value; To predict transaction profits; Costs related to lifespan depletion; This refers to the lifetime constraint weighting coefficient. The system uses the objective function With maximizing as the optimization objective, under constraints of equipment health, market trading rules, and SOC operation, a joint optimization solution is performed on spot market transactions, medium- and long-term transactions, and ancillary service market transactions to obtain the optimal charging and discharging strategy within the target trading period.

[0024] Based on the optimization results, charge / discharge power curves, SOC control curves, market pricing strategies, and profit forecasts are generated, and a set of transaction execution strategies is formed and sent to the EMS system for execution.

[0025] Finally, the system distributes the transaction execution strategy set to the EMS system and acquires real-time data on charging and discharging power, SOC changes, equipment operating status, and market execution results. The system continuously monitors the difference between planned and actual execution results using an execution deviation analysis model, analyzing power deviation, SOC deviation, and revenue deviation. When an execution deviation exceeds a preset threshold, a dynamic correction mechanism is automatically activated to recalculate the transaction strategy for the remaining trading cycle. When equipment failure, performance degradation, abnormal equipment temperature, or sudden market changes are detected, an anomaly investigation task is automatically generated and pushed to the operation and maintenance management platform. After completing on-site inspections, fault diagnosis, and problem handling based on the investigation task, operation and maintenance personnel feed back the results to the system. The system updates the equipment health status constraint model and equipment health constraint parameter set based on the feedback results and re-corrects the transaction execution strategy set. By continuously looping through equipment status feedback, strategy correction, anomaly handling, and parameter updates, data collaboration and closed-loop optimized operation are achieved between the transaction auxiliary decision-making system, the intelligent operation and maintenance system, and the energy storage power station EMS system, thereby improving the transaction revenue level, equipment reliability, and overall operation and management efficiency of the energy storage power station.

[0026] refer to Figure 2 This invention provides a collaborative optimization system for trading and maintenance based on the health status constraints of energy storage devices, comprising the following modules: The data collaboration and analysis module is used to acquire market transaction data, equipment operation data, environmental status data, and operation and maintenance management data, and to build a basic dataset for transaction and operation and maintenance collaboration. The health constraint decision module is used to establish a device health status constraint model based on the transaction operation and maintenance collaboration basic dataset, and generate a set of device health constraint parameters and a set of transaction execution strategies. The execution feedback optimization module is used to execute transaction execution strategies, perform feedback analysis on equipment operating status and execution results, and complete collaborative handling of anomalies and dynamic optimization control.

[0027] The data collaborative analysis module includes: The data acquisition unit is used to collect real-time electricity price data, day-ahead electricity price data, medium- and long-term transaction data, ancillary service market data, and historical transaction data through the electricity market interface; to collect battery cluster operation data, PCS operation data, BMS operation data, EMS operation data, and fault alarm data through the energy storage power station monitoring network; to collect ambient temperature data, ambient humidity data, wind speed data, light intensity data, and weather forecast data through the meteorological service platform; and to collect inspection record data, maintenance plan data, work order processing data, and equipment history data through the operation and maintenance management platform. The data fusion unit is used to perform unified timestamp processing, outlier identification processing, missing data compensation processing, and standardization processing on the collected data, establish the correlation mapping relationship between market data, equipment data, environmental data, and operation and maintenance data, and form multi-source heterogeneous data fusion results according to unified data coding rules. The feature construction unit is used to construct market revenue feature sets, equipment operation feature sets, environmental impact feature sets, and operation and maintenance status feature sets based on the data fusion results. It performs correlation analysis and dynamic weight fusion on features of different dimensions to generate a basic dataset for transaction operation and maintenance collaboration.

[0028] The health constraint decision module includes: The health assessment unit is used to receive the basic dataset for transaction operation and maintenance collaboration, extract battery state of charge information, battery health status information, battery temperature distribution information, battery consistency information, battery cycle life information, and fault alarm information, establish an equipment health assessment model, analyze and calculate the degree of equipment capacity decay, internal resistance growth trend, thermal runaway risk level, and fault occurrence probability, and generate equipment health evaluation results. The constraint generation unit is used to establish a constraint model for the health status of the equipment based on the equipment health assessment results. It calculates the current available capacity, available charging power, available discharging power, safe operating range, and life loss boundary of the energy storage equipment, forms a set of equipment health constraint parameters, and dynamically adjusts the constraint boundary according to the equipment operation risk level. The collaborative optimization unit receives the set of equipment health constraint parameters and market forecast results, establishes a multi-objective collaborative optimization model among market revenue objectives, equipment life objectives, and operational safety objectives, and performs joint optimization calculations on spot transactions, medium- and long-term transactions, and ancillary service transactions based on power plant capacity constraints, SOC operation constraints, market transaction rules, and equipment health constraints. It generates a set of transaction execution strategies consisting of a charge / discharge plan, an SOC control plan, a transaction pricing plan, and a risk warning plan, and performs revenue and risk assessments on the set of transaction execution strategies.

[0029] The execution feedback optimization module includes: The execution control unit is used to receive the transaction execution strategy set generated by the health constraint decision module, and convert the transaction execution strategy set into control instructions that can be executed by the EMS system, and control the energy storage device to execute the corresponding transaction tasks according to the preset charging and discharging plan, SOC control plan and auxiliary service plan; The status feedback unit is used to collect real-time data on actual charging and discharging power of energy storage devices, SOC change data, battery temperature data, equipment alarm data, market transaction results data, and revenue settlement data. It monitors and analyzes the deviation between the planned execution results and the actual execution results, and generates an execution feedback dataset. The closed-loop optimization unit is used to establish an execution deviation analysis model based on the execution feedback dataset, and to comprehensively evaluate power deviation, SOC deviation, revenue deviation and equipment status deviation. When equipment failure, power abnormality, SOC abnormality, market environment change or revenue deviation exceeds the limit is detected, the dynamic correction mechanism is automatically triggered to recalculate the trading strategy for the remaining trading cycle. The closed-loop optimization unit is also used to generate anomaly investigation work orders and push them to the corresponding operation and maintenance personnel's terminals. It receives fault diagnosis results, on-site handling results, and operation and maintenance feedback results. Based on the feedback results, it updates the equipment health status parameters, life loss parameters, and risk assessment parameters, and feeds the updated parameters back to the health constraint decision module. This enables data closed-loop collaborative optimization operation between the transaction auxiliary decision system, the intelligent operation and maintenance system, and the energy storage power station EMS execution system.

[0030] It should be noted that, unless otherwise specified, the embodiments and features and technical solutions in the present invention can be combined with each other.

[0031] Obviously, the embodiments described above are merely some embodiments of the present invention, not all embodiments. The accompanying drawings show preferred embodiments of the present invention, but do not limit the patent scope of the present invention. The present invention can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure of the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the patent protection scope of this invention.

Claims

1. A collaborative optimization method for operation and maintenance based on health status constraints of energy storage devices, characterized in that, Includes the following steps: Step S1: Obtain market transaction data, equipment operation data, environmental status data, and operation and maintenance management data of energy storage power stations; perform multi-source heterogeneous fusion processing on the market transaction data, equipment operation data, environmental status data, and operation and maintenance management data to construct an energy storage power station operation status feature set and generate a transaction and operation and maintenance collaborative basic dataset. Step S2: Based on the transaction operation and maintenance collaboration basic dataset, perform a health assessment and analysis on the operating status of energy storage equipment, establish an equipment health status constraint model, comprehensively calculate the current available capacity, available power, life loss level and operating risk level of the energy storage equipment, and generate a set of equipment health constraint parameters. Step S3: Based on the set of equipment health constraint parameters and market transaction forecast results, construct a collaborative optimization model for transaction operation and maintenance under the constraints of the health status of energy storage equipment. Jointly evaluate the health status of energy storage equipment, market revenue level and equipment life loss, generate transaction revenue evaluation results and life loss evaluation results, and perform collaborative optimization calculations on the transaction strategies of energy storage power stations participating in the electricity spot market, medium and long-term trading market and ancillary service market based on the transaction revenue evaluation results and life loss evaluation results, generate a set of transaction execution strategies including charge and discharge power curves, SOC control curves, market pricing strategies and revenue forecast results; Step S4: Control the energy storage power station to execute charging and discharging trading tasks according to the transaction execution strategy set, and obtain execution feedback data in real time. Perform dynamic analysis on execution deviation, abnormal equipment status and operation and maintenance handling results. Iteratively update the equipment health constraint parameter set and transaction execution strategy set according to the analysis results to form a closed-loop optimization mechanism for transaction decision-making, equipment operation and operation and maintenance management.

2. The method for collaborative optimization of operation and maintenance based on health status constraints of energy storage devices according to claim 1, characterized in that, Step S1 specifically includes: Real-time electricity price data, day-ahead electricity price data, medium- and long-term transaction price data, ancillary service market price data, and market transaction data for the target trading period are obtained through the electricity market interface. Ambient temperature data, ambient humidity data, solar radiation data, wind speed data, and weather forecast data are obtained through a meteorological data acquisition platform. The energy storage power station monitoring system acquires battery cluster operation data, PCS operation data, BMS operation data, EMS operation data, and historical operation data. The operation and maintenance management platform is used to obtain equipment inspection record data, maintenance plan data, fault work order data, spare parts management data, and equipment history data. Establish a mapping relationship between market information, equipment operation, environmental impact and operation and maintenance management dimensions, and perform time synchronization, anomaly removal, missing data compensation and standardization on the collected data. Based on the processed data, construct a market revenue feature matrix, an equipment status feature matrix, an environmental impact feature matrix, and an operation and maintenance status feature matrix. Further, an analysis model for the coupling relationship between trading and operation and maintenance is established. Correlation feature extraction and dynamic weight fusion processing are performed on each feature matrix to generate a basic dataset for trading and operation and maintenance collaboration. The basic dataset for trading and operation and maintenance collaboration includes market return representation information, equipment operation representation information, lifespan loss representation information, risk status representation information, and operation and maintenance resource representation information.

3. The method for collaborative optimization of operation and maintenance based on health status constraints of energy storage devices according to claim 1, characterized in that, Step S2 specifically includes: Based on the aforementioned transaction operation and maintenance collaborative basic dataset, battery state of charge information, battery health status information, battery temperature distribution information, battery consistency information, battery cycle count information, and fault alarm information are extracted. A health status assessment model is constructed to predict and analyze the trends of battery capacity decay, battery internal resistance change, thermal runaway risk, and equipment failure probability. Based on the prediction and analysis results, an equipment health evaluation index system is calculated, which includes capacity health index, power health index, safety health index, lifespan health index, and operation and maintenance support index. Based on the equipment health evaluation index system, an equipment health status constraint model is established to dynamically calculate the maximum available capacity, maximum charging power, maximum discharging power, and allowable operating range of energy storage equipment within the target trading cycle. Further, the life loss cost corresponding to the unit revenue is calculated by combining the equipment life value assessment model, and a health constraint boundary is established based on the life loss cost. A set of equipment health constraint parameters is generated based on the equipment health status constraint model. The set of equipment health constraint parameters includes equipment available capacity constraint parameters, equipment available power constraint parameters, equipment lifetime loss constraint parameters, equipment safe operation constraint parameters, and equipment operation and maintenance support constraint parameters.

4. The method for collaborative optimization of operation and maintenance based on health status constraints of energy storage devices according to claim 1, characterized in that, Step S3 specifically includes: A collaborative optimization model for transaction operation and maintenance is established based on historical market transaction data, real-time market transaction data, power grid load forecast data, and the set of equipment health constraint parameters generated in step S2. First, extract the device health status parameters, including battery health status. Temperature Anomaly Index and battery consistency index And construct an equipment health index model. : ; in: ; , as well as These represent the weights for health status, temperature status, and consistency status, respectively. According to equipment health index Calculate the available capacity boundary, available power boundary, and safe operating boundary of the equipment, and formulate equipment health constraints; A power price forecast series for the next 96 time periods was established based on current market price data, real-time market price data, and load forecast results. ; Based on the predicted electricity price sequence and the energy storage device charging and discharging power sequence Calculate the expected return over the trading cycle : ; in: Indicates the first Charge and discharge power over time period; Indicates the first Forecasted electricity prices for different time periods; Based on charge / discharge depth Number of loops and equipment health status Establish a lifetime attrition model and calculate lifetime attrition costs. : ; Further establish a synergistic optimization objective function for transaction revenue and equipment lifespan: ; in: To comprehensively optimize the target value; To predict transaction profits; Costs related to lifespan depletion; This refers to the lifetime constraint weighting coefficient. According to the objective function The optimal charging and discharging strategy for the target trading period is obtained by jointly optimizing spot market transactions, medium- and long-term transactions, and ancillary service market transactions. Based on the optimal charging and discharging strategy, a 96-period charging and discharging power curve, a SOC control curve, a market pricing strategy, and profit forecast results are generated, forming a set of trading execution strategies.

5. The method for collaborative optimization of operation and maintenance based on health status constraints of energy storage devices according to claim 1, characterized in that, Step S4 specifically includes: The transaction execution strategy set is distributed to the energy storage power station EMS system for execution, and charging and discharging power data, SOC change data, equipment operating status data and market execution result data are collected in real time during the execution process; An execution deviation analysis model is established to monitor in real time the deviations between planned power and actual power, planned SOC and actual SOC, and planned revenue and actual revenue. When the execution deviation exceeds the preset threshold, a dynamic correction mechanism is activated to re-optimize the trading strategy for the remaining trading cycle. When equipment failure, equipment performance degradation, abnormal equipment temperature, or sudden changes in the market environment are detected, an anomaly investigation task is automatically generated and pushed to the operation and maintenance management platform. The equipment health status constraint model is updated based on the operation and maintenance handling results. Recalculate the equipment health constraint parameter set based on the updated equipment health status constraint model; The transaction execution strategy set is revised based on the regenerated set of device health constraint parameters; By continuously looping through the processes of equipment status feedback, strategy correction, anomaly handling, and parameter updates, a closed-loop collaborative optimization operation is achieved between the transaction decision system, the operation and maintenance management system, and the EMS execution system.

6. A collaborative optimization system for operation and maintenance based on health status constraints of energy storage devices, applied to the collaborative optimization method for operation and maintenance based on health status constraints of energy storage devices as described in any one of claims 1-5, characterized in that, Includes the following modules: The data collaboration and analysis module is used to acquire market transaction data, equipment operation data, environmental status data, and operation and maintenance management data, and to build a basic dataset for transaction and operation and maintenance collaboration. The health constraint decision module is used to establish a device health status constraint model based on the transaction operation and maintenance collaboration basic dataset, and generate a set of device health constraint parameters and a set of transaction execution strategies. The execution feedback optimization module is used to execute transaction execution strategies, perform feedback analysis on equipment operating status and execution results, and complete collaborative handling of anomalies and dynamic optimization control.

7. The energy storage device health status constraint trading operation and maintenance collaborative optimization system according to claim 6, characterized in that, The data collaborative analysis module includes: The data acquisition unit is used to collect real-time electricity price data, day-ahead electricity price data, medium- and long-term transaction data, ancillary service market data, and historical transaction data through the electricity market interface; to collect battery cluster operation data, PCS operation data, BMS operation data, EMS operation data, and fault alarm data through the energy storage power station monitoring network; to collect ambient temperature data, ambient humidity data, wind speed data, light intensity data, and weather forecast data through the meteorological service platform; and to collect inspection record data, maintenance plan data, work order processing data, and equipment history data through the operation and maintenance management platform. The data fusion unit is used to perform unified timestamp processing, outlier identification processing, missing data compensation processing, and standardization processing on the collected data, establish the correlation mapping relationship between market data, equipment data, environmental data, and operation and maintenance data, and form multi-source heterogeneous data fusion results according to unified data coding rules. The feature construction unit is used to construct market revenue feature sets, equipment operation feature sets, environmental impact feature sets, and operation and maintenance status feature sets based on the data fusion results. It performs correlation analysis and dynamic weight fusion on features of different dimensions to generate a basic dataset for transaction operation and maintenance collaboration.

8. The energy storage device health status constraint trading and operation and maintenance collaborative optimization system according to claim 6, characterized in that, The health constraint decision module includes: The health assessment unit is used to receive the basic dataset for transaction operation and maintenance collaboration, extract battery state of charge information, battery health status information, battery temperature distribution information, battery consistency information, battery cycle life information, and fault alarm information, establish an equipment health assessment model, analyze and calculate the degree of equipment capacity decay, internal resistance growth trend, thermal runaway risk level, and fault occurrence probability, and generate equipment health evaluation results. The constraint generation unit is used to establish a constraint model for the health status of the equipment based on the equipment health assessment results. It calculates the current available capacity, available charging power, available discharging power, safe operating range, and life loss boundary of the energy storage equipment, forms a set of equipment health constraint parameters, and dynamically adjusts the constraint boundary according to the equipment operation risk level. The collaborative optimization unit receives the set of equipment health constraint parameters and market forecast results, establishes a multi-objective collaborative optimization model among market revenue objectives, equipment life objectives, and operational safety objectives, and performs joint optimization calculations on spot transactions, medium- and long-term transactions, and ancillary service transactions based on power plant capacity constraints, SOC operation constraints, market transaction rules, and equipment health constraints. It generates a set of transaction execution strategies consisting of a charge / discharge plan, an SOC control plan, a transaction pricing plan, and a risk warning plan, and performs revenue and risk assessments on the set of transaction execution strategies.

9. A collaborative optimization system for operation and maintenance based on health status constraints of energy storage devices, as described in claim 6, is characterized in that... The execution feedback optimization module includes: The execution control unit is used to receive the transaction execution strategy set generated by the health constraint decision module, and convert the transaction execution strategy set into control instructions that can be executed by the EMS system, and control the energy storage device to execute the corresponding transaction tasks according to the preset charging and discharging plan, SOC control plan and auxiliary service plan; The status feedback unit is used to collect real-time data on actual charging and discharging power of energy storage devices, SOC change data, battery temperature data, equipment alarm data, market transaction results data, and revenue settlement data. It monitors and analyzes the deviation between the planned execution results and the actual execution results, and generates an execution feedback dataset. The closed-loop optimization unit is used to establish an execution deviation analysis model based on the execution feedback dataset, and to comprehensively evaluate power deviation, SOC deviation, revenue deviation and equipment status deviation. When equipment failure, power abnormality, SOC abnormality, market environment change or revenue deviation exceeds the limit is detected, the dynamic correction mechanism is automatically triggered to recalculate the trading strategy for the remaining trading cycle. The closed-loop optimization unit is also used to generate anomaly investigation work orders and push them to the corresponding operation and maintenance personnel's terminals. It receives fault diagnosis results, on-site handling results, and operation and maintenance feedback results. Based on the feedback results, it updates the equipment health status parameters, life loss parameters, and risk assessment parameters, and feeds the updated parameters back to the health constraint decision module. This enables data closed-loop collaborative optimization operation between the transaction auxiliary decision system, the intelligent operation and maintenance system, and the energy storage power station EMS execution system.