Energy storage cluster dynamic optimization control system based on edge computing

Abstract

The invention discloses an energy storage cluster dynamic optimization control system based on edge computing, which relates to the technical field of micro-grid management, and comprises a data acquisition module, a voltage and current sensor, a power sensor, a temperature sensor, an illumination intensity sensor and the like are utilized for real-time monitoring and transmission optimization of the data acquisition module; power load related data, energy storage state related data and environment variable related data in the micro-grid are collected in real time; the edge calculation processing module performs local processing and dimensionless analysis on the data, and extracts a load change rate, an energy storage state index and an operation environment index; decision suggestions are generated through normalization processing and sorting evaluation of the decision support module in combination with a dynamic load prediction model, and the data processing speed and the decision accuracy are effectively improved. The comprehensive performance evaluation index is calculated and evaluated, self-adaptive adjustment is carried out, it is ensured that the energy storage system quickly responds to sudden changes in a complex environment, and stability and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of microgrid management technology, and specifically to a dynamic optimization control system for energy storage clusters based on edge computing. Background Art

[0002] The development of dynamic optimization control systems for energy storage clusters stems from the demand for renewable energy development, particularly the volatility and instability faced by traditional power systems with the widespread adoption of wind and solar power. With advances in battery technology, energy storage systems have become a key tool for balancing supply and demand and improving power system reliability. In recent years, the development of big data and artificial intelligence technologies has enabled dynamic optimization control systems to achieve more efficient energy storage management, improving energy efficiency and economic efficiency.

[0003] However, with the development of power systems, energy storage clusters often face the following technical problems when applied to microgrid management: During real-time monitoring and control, delays in data collection and transmission may lead to decision lags, affecting the energy storage system's ability to respond to instantaneous load changes.

[0004] Faced with the data generated by a large amount of sensors and devices, existing processing algorithms may not be able to analyze and extract useful information in a timely and effective manner, resulting in decisions being based on outdated or incomplete data.

[0005] In complex environments, the decision-making system of the energy storage cluster may lack sufficient intelligence and be unable to quickly adapt to dynamic changes, resulting in untimely responses to emergencies and affecting the stability and efficiency of the overall system. Summary of the Invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is: solving the technical problems of data delay, insufficient data processing capability and lack of intelligent decision support in the background technology.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a dynamic optimization control system for energy storage clusters based on edge computing, comprising: Data acquisition module, edge computing processing module, decision support module, load forecasting module and optimization control module; The data acquisition module is used to monitor microgrid-related data in the microgrid in real time, wherein the microgrid-related data includes power load-related data, energy storage status-related data, and environmental variable-related data, and construct a first data group, while integrating and transmitting multiple sensor data to the edge computing module; The edge computing processing module is used to receive the first data group generated by the data acquisition module, perform local data analysis and processing, and construct a second data group by extracting key characteristic parameters and performing calculations. The second data group includes a load change rate, an energy storage state index, and an operating environment index; The decision support module is used to normalize the values ​​of the second data group, perform a ranking evaluation, and generate and execute decision suggestions based on the evaluation content of the second data group in combination with the dynamic load forecasting model; The load forecasting module is used to predict the power load within a fixed period after executing the decision recommendation; by collecting and extracting real-time weather-related data and historical weather-related data, it generates and evaluates the load forecast index to guide the charging and discharging scheduling of the energy storage system; The optimization control module is used to monitor the overall operating status of the energy storage system in real time and collect data related to the performance of the energy storage system in real time; after fitting the data related to the performance of the energy storage system, a comprehensive performance evaluation index is generated and evaluated, and the energy storage system is adaptively adjusted. The adaptive adjustment includes the charge and discharge rate, operating cycle and battery health status.

[0009] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, the power load related data includes harmonic distortion rate, instantaneous power, short-circuit capacity and reactive power; The energy storage status related data includes the discharge depth value, battery internal resistance value and charge and discharge cycle number; The environmental variable related data include wet-bulb humidity, dew point humidity, solar irradiance and ultraviolet index.

[0010] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, wherein: the edge computing processing module includes a load calculation unit, an energy storage calculation unit and an environment calculation unit; The load calculation unit extracts the power load related data from the first data group and performs dimensionless processing to calculate the load change rate, which is expressed as: , in, Indicates the change in harmonic distortion rate between the current moment and the previous moment. Indicates the instantaneous power change value between the current moment and the previous moment, Indicates the change in short-circuit capacity between the current moment and the previous moment. Indicates the reactive power change between the current moment and the previous moment.

[0011] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, the energy storage calculation unit extracts the energy storage state related data in the first data group and performs dimensionless processing to calculate the energy storage state index, which is expressed as: ,

[0012] in, Indicates the depth of discharge value, Indicates the internal resistance of the battery. Indicates the number of charge and discharge cycles.

[0013] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, the environmental calculation unit extracts the environmental variable related data in the first data group and performs dimensionless processing to calculate the operating environment index, which is expressed as: , in, represents the wet-bulb humidity, Indicates the dew point humidity, represents the solar irradiance, Indicates the UV index.

[0014] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, wherein: the decision support module includes a data normalization unit and a ranking evaluation and decision generation unit; The data normalization unit is used to convert the load change rate, energy storage state index and operating environment index into a unified standardized numerical range, and normalize them to the interval of [0,1]; The ranking evaluation and decision generation unit is used to perform ranking evaluation on the load change rate, energy storage state index and operating environment index; Prioritize based on the values ​​of load change rate, energy storage status index, and operating environment index; Combined with the dynamic load forecasting model, decision recommendations are generated preferentially for parameters whose values ​​are greater than a preset threshold; the decision recommendations include adjusting the energy storage charging and discharging strategy and adjusting the operating time period.

[0015] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, wherein: the load forecasting module includes a forecasting calculation unit and a forecasting evaluation unit; The prediction calculation unit collects weather-related data in real time; collects historical data in real time by reading the historical meteorological record database and the power management database; and calculates and obtains the load prediction index, which is expressed as: ,

[0016] Among them, Cvr represents the cloud cover rate in the real-time weather related data, Apr represents the atmospheric pressure change rate in the real-time weather related data, Rsr represents the surface radiation in the real-time weather related data; Hhv represents the historical humidity fluctuation data in the historical related data, and Hlp represents the historical power grid load peak time distribution in the historical related data.

[0017] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, wherein: the prediction and evaluation unit compares and evaluates the load prediction index by presetting a first load prediction threshold Q1 and a second load prediction threshold Q2, and the first load prediction threshold Q1>the second load prediction threshold Q2, and guides the charging and discharging scheduling of the energy storage system; If the load forecast index exceeds the first load forecast threshold Q1, it indicates that the future power load is abnormal, the system load is approaching the limit, or there is a risk of peak power demand. In this case, the charging operation of the energy storage equipment is stopped first, the discharge function of the energy storage system is activated, and the operation of non-critical equipment is restricted. If the first load prediction threshold Q1 ≥ load prediction index > second load prediction threshold Q2, it means that the future power load is normal, the microgrid load is stable, and the energy storage system does not need to be adjusted; If the second load forecast threshold Q2 ≥ the load forecast index, it indicates that the future power load is normal and below the threshold, indicating that the grid has surplus power. At this time, the energy storage system is started to charge and non-critical load equipment is operated, including system maintenance and equipment calibration.

[0018] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, wherein: the optimization control module includes a system performance quantification unit and a system performance evaluation unit; The energy storage system performance related data collected by the system performance quantification unit includes energy storage utilization rate, system charging and discharging efficiency, operation stability and energy loss rate; After dimensionless processing of the energy storage system performance data, the comprehensive performance evaluation index is calculated using the following formula, expressed as: , in, Indicates energy utilization rate, Indicates the system charge and discharge efficiency, Indicates operational stability. Indicates the energy loss rate.

[0019] As a preferred solution of the energy storage cluster dynamic optimization control system based on edge computing described in the present invention, wherein: the system performance evaluation unit compares and evaluates the preset performance threshold W with the comprehensive performance evaluation index, and adaptively adjusts the energy storage system; If the performance threshold W ≥ the comprehensive performance evaluation index, it indicates that the overall operating performance of the energy storage system is abnormal, and there are problems with the health and energy efficiency of the energy storage system. In this case, the discharge rate is reduced by 10% from the original level, the operating cycle is adjusted, and the battery health maintenance program is initiated. The performance threshold W< is based on the comprehensive performance evaluation index, indicating that the overall operating performance of the energy storage system is normal, maintaining the current charge and discharge rate and operating cycle, and performing regular preventive maintenance on equipment and batteries.

[0020] Beneficial effects of the present invention: The energy storage cluster dynamic optimization control system based on edge computing provided by the present invention, through real-time monitoring and transmission optimization of the data acquisition module, uses a variety of sensor devices such as voltage and current sensors, power sensors, temperature sensors, power sensors and light intensity sensors to collect power load-related data, energy storage status-related data and environmental variable-related data in the microgrid in real time; the above data are locally processed and analyzed by the edge computing processing module, which reduces the delay problem of data transmission, realizes faster decision generation, and solves the decision lag problem caused by data delay in the real-time monitoring and control process, thereby improving the energy storage system's response capability to instantaneous load changes.

[0021] This energy storage cluster dynamic optimization control system based on edge computing performs dimensionless processing on the first data group through the load calculation unit, energy storage calculation unit and environment calculation unit of the edge computing processing module, and extracts key parameters such as the load change rate Hhz, energy storage state index Szc and operating environment index Ecp; then, the data normalization unit in the decision support module standardizes these parameters and normalizes them to the range of [0,1]; and through the ranking evaluation and decision generation unit combined with the dynamic load forecasting model, generates decision recommendations for the load change rate Hhz, energy storage state index Szc and operating environment index Ecp. This process greatly improves the processing capability of complex data, avoids the problem of data obsolescence caused by insufficient algorithm analysis speed, and ensures that data decisions are based on the latest valid information.

[0022] This energy storage cluster dynamic optimization control system based on edge computing uses an optimization control module to generate a comprehensive performance evaluation index Zhpj by real-time monitoring and dimensionless processing of the energy storage utilization rate Snly, system charge and discharge efficiency Cpsx, operational stability Zwdx, and energy loss rate Nshl. By comparing and evaluating this index with a preset performance threshold W, the system can adaptively adjust the operating status of the energy storage system, including adjusting the charge and discharge rates, optimizing the operating cycle, and maintaining the battery health status. This dynamic decision-making process combines the load forecasting index Pljx generated by the cloud cover rate Cvr, atmospheric pressure change rate Apr, surface radiation Rsr, historical humidity fluctuation data Hhv, and historical grid load peak time distribution Hlp in the load forecasting module to ensure that the system can respond quickly to emergencies in complex environments, avoiding untimely responses due to a lack of intelligent decision-making support, thereby improving the stability and operational efficiency of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 This is a diagram showing the overall structure of an energy storage cluster dynamic optimization control system based on edge computing, provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0027] Example 1 Reference Figure 1 , which is an embodiment of the present invention, provides a dynamic optimization control system for energy storage clusters based on edge computing, including: Data acquisition module, edge computing processing module, decision support module, load forecasting module and optimization control module; The data acquisition module is used to monitor microgrid-related data in the microgrid in real time, including power load-related data, energy storage status-related data, and environmental variable-related data, and to construct a first data group, while integrating and transmitting multiple sensor data to the edge computing module; The edge computing processing module is used to perform local data analysis and processing based on the first data set generated by the data acquisition module, and construct a second data set by extracting key characteristic parameters and performing calculations, including the load change rate Hhz, the energy storage state index Szc, and the operating environment index Ecp; The decision support module is used to normalize the values ​​of the second data group, perform a ranking evaluation, and generate and execute decision suggestions based on the evaluation content of the second data group in combination with the dynamic load forecasting model; The load forecasting module is used to predict the power load within a fixed period after executing the decision recommendation; by collecting and extracting real-time weather-related data and historical weather-related data, it generates and evaluates the load forecast index Pljx, which is used to guide the charging and discharging scheduling of the energy storage system; The optimization control module is used to monitor the overall operating status of the energy storage system in real time and collect data related to the energy storage system performance in real time. Then, after fitting the data related to the energy storage system performance, a comprehensive performance evaluation index Zhpj is generated and evaluated. Then, the energy storage system is adaptively adjusted based on the evaluation content of the comprehensive performance evaluation index Zhpj, including the charge and discharge rate, operating cycle and battery health status.

[0028] In this embodiment, the data acquisition module ensures accurate microgrid operating status information by real-time monitoring of power load-related data, energy storage status-related data, and environmental variable-related data, effectively improving data integrity. The edge computing processing module extracts the load change rate Hhz, energy storage status index Szc, and operating environment index Ecp through local analysis and processing of the first data group, reducing data transmission delay and improving computing efficiency. The decision support module generates dynamic load forecasting model decisions through normalization processing and high-low ranking evaluation to ensure the accuracy and timeliness of decisions. The load forecasting module accurately predicts the power load in a fixed period in the future through the load forecast index Pljx of real-time weather-related data and historical-related data, thereby optimizing the energy storage system scheduling. The optimization control module generates a comprehensive performance evaluation index Zhpj by monitoring the energy storage utilization rate Snly, system charge and discharge efficiency Cpsx, operating stability Zwdx, and energy loss rate Nshl, and performs adaptive adjustment to improve system stability, response speed, and battery life.

[0029] The data acquisition module first collects microgrid-related data in real time within the microgrid through multiple sensors, including voltage and current sensors, power sensors, temperature sensors, power sensors, and light intensity sensors; then formats the collected microgrid-related data and packages it into a first data group through a data integration mechanism; finally, the integrated first data group is sent to the edge computing module through a data transmission link for further analysis and processing; Among them, power load related data include harmonic distortion rate Thd, instantaneous power Pin, short-circuit capacity Scc and reactive power Wgl; Energy storage status related data include discharge depth value Fsd, battery internal resistance value Dnz and charge and discharge cycle number Xcf; Environmental variable related data include wet-bulb humidity Ssd, dew point humidity Sld, solar irradiance Sfz and ultraviolet index Swx.

[0030] In this embodiment, multiple sensors of the data acquisition module collect power load related data, energy storage status related data and environmental variable related data in the microgrid in real time, and integrate them into a first data group and send them to the edge computing module for analysis and processing. This process can significantly improve the data acquisition efficiency and accuracy of the system; the harmonic distortion rate Thd in the power load related data can effectively monitor the changes in power quality, the instantaneous power Pin is used to reflect the fluctuation of the system load in real time, the short-circuit capacity Scc evaluates the carrying capacity of the system in the event of a fault, and the reactive power Wgl is used to evaluate the power factor and power transmission efficiency of the system; the energy storage status related data The depth of discharge value Fsd can help monitor the battery discharge condition, the battery internal resistance value Dnz reflects the battery health and resistance change, and the number of charge and discharge cycles Xcf helps to determine the battery service life and current cycle status; the wet-bulb humidity Ssd and dew-point humidity Sld in the environmental variable-related data are used to evaluate the impact of ambient humidity on equipment operation, the solar irradiance Sfz is used to predict the potential of photovoltaic power generation, and the ultraviolet index Swx can evaluate the potential impact of ultraviolet rays on the aging of equipment casing materials; by collecting and processing these key data, the operating status of the microgrid can be comprehensively optimized, and the operating efficiency and overall stability of the energy storage system can be improved.

[0031] The edge computing processing module includes a load calculation unit, an energy storage calculation unit and an environment calculation unit; The load calculation unit extracts the power load related data from the first data group and performs dimensionless processing to calculate the load change rate Hhz. The specific formula is as follows: , Where, Indicates the change in harmonic distortion rate between the current moment and the previous moment. Indicates the instantaneous power change value between the current moment and the previous moment, Indicates the change in short-circuit capacity between the current moment and the previous moment. Indicates the reactive power change between the current moment and the previous moment.

[0032] The energy storage calculation unit extracts the energy storage state related data from the first data group and performs dimensionless processing to calculate the energy storage state index Szc. The specific formula is as follows: , The environment calculation unit calculates and obtains the operating environment index Ecp by extracting the environmental variable related data from the first data group and performing dimensionless processing. The specific formula is as follows: , The decision support module includes a data normalization unit and a ranking evaluation and decision generation unit; The data normalization unit is used to convert the load change rate Hhz, the energy storage state index Szc and the operating environment index Ecp into a unified standardized value range, specifically normalizing them to the interval [0,1]; The ranking evaluation and decision generation unit is used to evaluate the load change rate Hhz, energy storage state index Szc and operating environment index Ecp in a ranking order; prioritize the load change rate Hhz, energy storage state index Szc and operating environment index Ecp according to their numerical values, with the largest value having the greatest impact on system operation; then, combined with the dynamic load forecasting model, generate corresponding decision recommendations for the parameters with the largest values, including adjusting the energy storage charging and discharging strategy and adjusting the operating time period.

[0033] In this embodiment, the load change rate Hhz, energy storage state index Szc, and operating environment index Ecp are converted into a unified standardized numerical range through a data normalization unit, ensuring that data of different magnitudes can be consistently compared and processed, eliminating interference caused by differences in data dimensions. These parameters are then ranked and evaluated through a ranking evaluation and decision generation unit, prioritizing parameters with the greatest impact on the system to ensure that the system can effectively focus on the most critical operating factors. Combined with a dynamic load forecasting model, this module can generate targeted decision recommendations based on the current load change rate Hhz, energy storage state index Szc, and operating environment index Ecp, optimizing the charging and discharging strategies and operating time periods of the energy storage system, improving the system's response speed and operating efficiency, enabling the system to more intelligently adapt to changes in load and environment, and ensuring the efficient and stable operation of the energy storage system.

[0034] The load forecasting module includes a forecast calculation unit and a forecast evaluation unit; The prediction calculation unit collects real-time weather-related data through cloud detection sensors, air pressure sensors, and deployed radiation measurement sensors; it also collects historical related data in real time by reading historical meteorological record databases and power management databases; and then calculates the load prediction index Pljx using the following formula: , Where Cvr represents the cloud cover rate in the real-time weather data, Apr represents the atmospheric pressure change rate in the real-time weather data, Rsr represents the surface radiation in the real-time weather data, Hhv represents the historical humidity fluctuation data in the historical data, and Hlp represents the historical power grid load peak time distribution in the historical data.

[0035] The prediction and evaluation unit compares and evaluates the load prediction index Pljx by presetting a first load prediction threshold Q1 and a second load prediction threshold Q2, and the first load prediction threshold Q1> the second load prediction threshold Q2, and guides the charge and discharge scheduling of the energy storage system. The specific contents are as follows: If the load forecast index Pljx is greater than the first load forecast threshold Q1, it indicates that the future power load is abnormal, the system load is approaching the limit, or there is a risk of peak power demand. In this case, the charging operation of the energy storage device should be stopped first, the discharge function of the energy storage system should be activated, and the operation of non-critical equipment should be restricted. If the first load prediction threshold Q1 ≥ load prediction index Pljx > second load prediction threshold Q2, it means that the future power load is normal, the microgrid load is stable, and the energy storage system does not need to be adjusted; If the second load forecast threshold Q2 ≥ the load forecast index Pljx, it indicates that the future power load is normal and below the threshold, indicating that the grid has surplus power. At this time, the energy storage system is started to charge and non-critical load equipment is operated, including system maintenance and equipment calibration.

[0036] In this embodiment, the prediction calculation unit uses cloud detection sensors, air pressure sensors and deployed radiation measurement sensors to collect real-time weather-related data such as cloud coverage rate Cvr, atmospheric pressure change rate Apr and surface radiation Rsr; at the same time, historical related data such as historical humidity fluctuation data Hhv and historical power grid load peak time distribution Hlp are collected from the historical meteorological record database and the power management database; these data are calculated to generate the load prediction index Pljx, which helps to accurately predict the power load situation in a fixed period in the future; among them, the cloud coverage rate Cvr reflects the potential of solar power generation, the atmospheric pressure change rate Apr affects the fluctuation of wind power generation, the surface radiation Rsr measures the output capacity of photovoltaic power generation, and the historical humidity fluctuation data Hhv and the historical power grid load peak time distribution Hlp are used to evaluate the load variation in the power grid operation history. The prediction and evaluation unit compares and evaluates the load prediction index Pljx with the preset first load prediction threshold Q1 and second load prediction threshold Q2, effectively predicting the future power load state and guiding the charging and discharging scheduling of the energy storage system. When the load prediction index Pljx exceeds the first load prediction threshold Q1, the system can start discharging and restrict the operation of non-critical equipment to ensure stable power supply during peak load periods. When the load prediction index Pljx is between the first load prediction threshold Q1 and the second load prediction threshold Q2, the system maintains normal operation without adjustment. When the load prediction index Pljx is lower than the second load prediction threshold Q2, the system can start charging and perform equipment maintenance to fully utilize surplus power resources. Through this process, the energy storage system can achieve efficient scheduling under different load conditions, ensuring stable operation and effective energy utilization.

[0037] The optimization control module includes a system performance quantification unit and a system performance evaluation unit; The energy storage system performance data collected by the system performance quantification unit include energy storage utilization rate Snly, system charge and discharge efficiency Cpsx, operation stability Zwdx, and energy loss rate Nshl. After dimensionless processing of the energy storage system performance data, the comprehensive performance evaluation index Zhpj is calculated using the following formula: , The system performance evaluation unit compares and evaluates the preset performance threshold W with the comprehensive performance evaluation index Zhpj and performs adaptive adjustment on the energy storage system. The specific contents are as follows: If the performance threshold W ≥ the comprehensive performance evaluation index Zhpj, it indicates that the overall operating performance of the energy storage system is abnormal, and there are problems with the health and energy efficiency of the energy storage system. In this case, the discharge rate is reduced by 10% from the original level, the operating cycle is adjusted, and the battery health maintenance program is initiated. The performance threshold W < based on the comprehensive performance evaluation index Zhpj indicates that the overall operating performance of the energy storage system is normal, maintaining the current charge and discharge rate and operating cycle, and performing regular preventive maintenance on equipment and batteries.

[0038] In this embodiment, the system performance quantification unit collects data related to the performance of the energy storage system, including the energy storage utilization rate Snly, the system charge and discharge efficiency Cpsx, the operation stability Zwdx, and the energy loss rate Nshl. After dimensionless processing of these data, the comprehensive performance evaluation index Zhpj is calculated, which helps to monitor the overall operation status of the energy storage system in real time. The energy storage utilization rate Snly reflects the utilization rate of the system's effective energy storage, the system charge and discharge efficiency Cpsx measures the effectiveness of energy conversion, the operation stability Zwdx evaluates the degree of fluctuation of the system under different loads, and the energy loss rate Nshl represents the energy loss of the system during operation. ; Through the calculated comprehensive performance evaluation index Zhpj, the system performance evaluation unit can compare and evaluate it with the preset performance threshold W, timely discover potential system problems and make adaptive adjustments; when the performance evaluation index Zhpj is lower than the threshold W, it indicates that the system performance has declined, and the system will automatically reduce the discharge rate, adjust the operating cycle and start the battery health maintenance program to improve operating efficiency and extend battery life; when the performance evaluation index Zhpj is higher than the threshold W, the system performance is in normal state, maintain the current operating strategy and perform preventive maintenance regularly; this process ensures the efficiency, stability and reliability of the energy storage system under various operating conditions.

[0039] Example 2 One embodiment of the present invention provides a dynamic optimization control system for an energy storage cluster based on edge computing. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0040] The preparation for the experiment includes: Software functional unit design: Select typical application scenarios in multiple power monitoring systems, including functional modules such as data acquisition, processing and analysis, and early warning response. Data acquisition: Collect experimental data through computer networks to form standardized input and output data sets to support system function verification. Specification formulation: Develop relevant functional specifications and performance evaluation standards based on existing computer software engineering standards and actual industry needs. Software implementation and optimization: Use software programming languages ​​to develop various functional modules and optimize performance bottlenecks to ensure stable operation of each module. Software verification: By setting up multiple test environments and running different workloads, comprehensively verify the software's response speed, accuracy, and stability, and optimize the software code. Early warning system design: By writing early warning algorithms that adapt to different work scenarios, ensure that the software can respond quickly and trigger warnings when anomalies occur. Data statistics and analysis: Collect various performance indicators of the software system during actual operation and form a system operation report.

[0041] Experimental data recording form: , Analysis of the tabular data reveals a generally high recognition accuracy across all modules, exceeding 95%, demonstrating that the implemented software system possesses strong recognition capabilities across diverse functional scenarios. Warning response times are generally under 2 seconds, demonstrating the system's rapid response capabilities and ensuring safe monitoring of power facilities. System stability exceeds 99%, fully demonstrating the system's reliability in long-term operation. Functional implementation coverage approaches 100%, indicating that the system is fully functional and can meet practical operational requirements. Low system resource consumption demonstrates the software solution's efficient resource utilization. Furthermore, work efficiency improvement data reveals that the system significantly improves work efficiency, with an overall improvement of between 10% and 20%, further demonstrating the effectiveness of this technical solution in enhancing the efficiency and safety of power operations.

[0042] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The energy storage cluster dynamic optimization control system based on edge computing is characterized by: include: Data acquisition module, edge computing processing module, decision support module, load forecasting module and optimization control module; The data acquisition module is used to monitor microgrid-related data in the microgrid in real time, wherein the microgrid-related data includes power load-related data, energy storage status-related data, and environmental variable-related data, and construct a first data group, while integrating and transmitting multiple sensor data to the edge computing module; The edge computing processing module is used to receive the first data group generated by the data acquisition module, perform local data analysis and processing, and construct a second data group by extracting key characteristic parameters and calculations, wherein the second data group includes a load change rate, an energy storage state index, and an operating environment index; The decision support module is used to normalize the values ​​of the second data group, perform high and low ranking evaluation, and generate and execute decision suggestions based on the evaluation content of the second data group combined with the dynamic load forecasting model; The load forecasting module is used to forecast the power load within a fixed period after executing the decision suggestion; by collecting and extracting real-time weather-related data and historical weather-related data, a load forecasting index is generated and evaluated to guide the charging and discharging scheduling of the energy storage system; The optimization control module is used to monitor the overall operating status of the energy storage system in real time and collect performance-related data of the energy storage system in real time; After fitting the performance-related data of the energy storage system, a comprehensive performance evaluation index is generated and evaluated, and the energy storage system is adaptively adjusted, including the charge and discharge rate, operation cycle and battery health status.

2. The energy storage cluster dynamic optimization control system based on edge computing according to claim 1, characterized in that: The power load related data include harmonic distortion rate, instantaneous power, short-circuit capacity and reactive power; The energy storage state related data include discharge depth value, battery internal resistance value and charge and discharge cycle number; The environmental variable related data include wet bulb humidity, dew point humidity, solar irradiance and ultraviolet index.

3. The energy storage cluster dynamic optimization control system based on edge computing as claimed in claim 2, characterized in that: The edge computing processing module includes a load computing unit, an energy storage computing unit and an environment computing unit; The load calculation unit extracts the power load related data in the first data group and performs dimensionless processing to calculate the load change rate, which is expressed as: ， in, Indicates the change in harmonic distortion rate between the current moment and the previous moment. Indicates the instantaneous power change value between the current moment and the previous moment, Indicates the change in short-circuit capacity between the current moment and the previous moment. Indicates the reactive power change between the current moment and the previous moment.

4. The energy storage cluster dynamic optimization control system based on edge computing as claimed in claim 3, characterized in that: The energy storage calculation unit extracts the energy storage state related data in the first data group and performs dimensionless processing to calculate and obtain the energy storage state index, which is expressed as: ， in, Indicates the discharge depth value, Indicates the internal resistance of the battery. Indicates the number of charge and discharge cycles.

5. The energy storage cluster dynamic optimization control system based on edge computing as claimed in claim 4, characterized in that: The environment calculation unit calculates and obtains the operating environment index by extracting the environment variable related data in the first data group and performing dimensionless processing, which is expressed as: ， in, represents the wet bulb humidity, Indicates the dew point humidity, is the solar irradiance, Indicates the UV index.

6. The energy storage cluster dynamic optimization control system based on edge computing as claimed in claim 5, characterized in that: The decision support module includes a data normalization unit and a ranking evaluation and decision generation unit; The data normalization unit is used to convert the load change rate, the energy storage state index and the operating environment index into a unified standardized value range, and normalize them to the interval of [0,1]; The ranking evaluation and decision making unit is used to evaluate the load change rate, energy storage state index and operating environment index in a high-low ranking manner; Prioritize according to the values ​​of load change rate, energy storage status index and operating environment index; Combined with the dynamic load forecasting model, decision suggestions are generated preferentially for parameters whose values ​​are greater than preset thresholds; the decision suggestions include adjusting the energy storage charging and discharging strategy and adjusting the operating time period.

7. The energy storage cluster dynamic optimization control system based on edge computing according to claim 6, characterized in that: The load forecasting module includes a forecasting calculation unit and a forecasting evaluation unit; The prediction calculation unit collects weather-related data in real time; collects historical data in real time by reading the historical meteorological record database and the power management database; and calculates and obtains the load prediction index, which is expressed as: ， Among them, Cvr represents the cloud coverage rate in the real-time weather related data, Apr represents the atmospheric pressure change rate in the real-time weather related data, Rsr represents the surface radiation in the real-time weather related data; Hhv represents the historical humidity fluctuation data in the historical related data, and Hlp represents the historical power grid load peak time distribution in the historical related data.

8. The energy storage cluster dynamic optimization control system based on edge computing according to claim 7, characterized in that: The prediction and evaluation unit compares and evaluates the load prediction index by presetting a first load prediction threshold Q1 and a second load prediction threshold Q2, and the first load prediction threshold Q1>the second load prediction threshold Q2, and guides the charging and discharging scheduling of the energy storage system; If the load forecast index is greater than the first load forecast threshold Q1, it indicates that the future power load is abnormal, the system load is close to the limit or there is a risk of peak power consumption; at this time, the charging operation of the energy storage equipment is stopped first, the discharge function of the energy storage system is started, and the operation of non-critical equipment is restricted; If the first load prediction threshold Q1 ≥ load prediction index > second load prediction threshold Q2, it means that the future power load is normal, the microgrid load is stable, and the energy storage system does not need to be adjusted; If the second load prediction threshold Q2 ≥ load prediction index, it means that the future power load is normal and the future load is lower than the threshold, and there is surplus power in the power grid; at this time, the energy storage system is started to charge and non-critical load equipment is operated, including system maintenance and equipment calibration.

9. The energy storage cluster dynamic optimization control system based on edge computing according to claim 8, characterized in that: The optimization control module includes a system performance quantification unit and a system performance evaluation unit; The energy storage system performance related data collected by the system performance quantification unit include energy storage utilization rate, system charging and discharging efficiency, operation stability and energy loss rate; After dimensionless processing of the performance data of the energy storage system, the comprehensive performance evaluation index is calculated by the following formula, expressed as: ， in, Indicates the utilization rate. Indicates the system charging and discharging efficiency, Indicates operational stability. Represents the energy loss rate.

10. The energy storage cluster dynamic optimization control system based on edge computing according to claim 9, characterized in that: The system performance evaluation unit compares and evaluates the preset performance threshold W with the comprehensive performance evaluation index, and adaptively adjusts the energy storage system; If the performance threshold W ≥ the comprehensive performance evaluation index, it means that the overall operating performance of the energy storage system is abnormal, and there are problems with the health and energy efficiency of the energy storage system. At this time, the discharge rate is reduced by 10% on the original basis, the operation cycle is adjusted, and the battery health maintenance program is started; The performance threshold W<based on the comprehensive performance evaluation index indicates that the overall operating performance of the energy storage system is normal, maintaining the current charge and discharge rate and operating cycle, and performing regular preventive maintenance on equipment and batteries.

Images