Self-adaptive power execution device and distribution method for energy storage system

By designing an adaptive power actuator in the energy storage system, real-time data acquisition and intelligent control are achieved, the shortcomings of traditional energy storage systems in load tracking and balancing are solved, and the stability and reliability of power supply are improved.

CN119010109AActive Publication Date: 2024-11-22HEFEI HUAZHI ENERGY TECH CO LTD

Patent Information

Application Number
CN202411081806.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-22
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

Traditional energy storage systems have shortcomings in adaptive load tracking and balancing, lack high-precision real-time data acquisition and preprocessing mechanism, fixed control strategies, and cannot effectively respond to the load demand in complex and changeable power systems, affecting the stability of power supply. and reliability.

Method used

Design an adaptive power execution device for energy storage systems, including load monitoring module, prediction and analysis module, strategy formulation module, power execution and control module, feedback and optimization module, and safety protection and fault monitoring module, through real-time data acquisition, high Accuracy prediction and intelligent control strategy optimization realize dynamic power adjustment and closed-loop feedback, and improve load tracking and balance capabilities.

Benefits of technology

It significantly improves the load tracking and balancing capabilities of energy storage systems in complex power systems, ensures efficient and stable operation, enhances the reliability and safety of the system, can flexibly respond to load fluctuations, and improves the stability and safety of power supply. sex.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119010109A_ABST
    Figure CN119010109A_ABST
Patent Text Reader

Abstract

The invention discloses a self-adaptive power execution device and distribution method for an energy storage system, and relates to the field of energy storage systems, and the device comprises a load monitoring module which collects key parameters of current and voltage of a power grid and a load in real time through a high-precision sensor, carries out the preprocessing and storage through a processing unit, and transmits the key parameters to a power supply module; according to the invention, through real-time acquisition and preprocessing of key data of a power system load, a generator and a transformer, in combination with time sequence analysis and a linear regression advanced prediction algorithm, accurate prediction of future load change is realized, and based on the prediction results, the device can automatically formulate and optimize a power distribution strategy of an energy storage system, and the power distribution efficiency is improved. According to the self-adaptive power supply method, rapid response can be ensured during load fluctuation, dynamic adjustment of the output power of the energy storage system is realized, the self-adaptive capability not only effectively relieves the contradiction between supply and demand in a power system, but also remarkably improves the stability and reliability of power supply, and provides powerful guarantee for safe operation of the power system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage systems, and in particular to an energy storage system adaptive power execution device and distribution method. Background Art

[0002] With the growing demand for electricity and the increasing complexity of the power system, ensuring the stability and reliability of power supply has become a key issue that the power industry needs to solve urgently. As an important component of the power system, the energy storage system plays an irreplaceable role in load regulation, peak-valley balance, and responding to sudden load changes. Traditional energy storage system control methods often rely on fixed control strategies and parameter settings, which make it difficult to adapt to the complex and changeable load demands in the power system in real time.

[0003] Traditional energy storage systems have obvious deficiencies in adaptive load tracking and balancing. On the one hand, due to the lack of high-precision real-time data acquisition and preprocessing mechanisms, traditional systems find it difficult to accurately obtain key load data in the power system, resulting in limited prediction accuracy and an inability to effectively respond to rapidly changing load demands. On the other hand, traditional control strategies are often based on static and fixed model parameters and lack dynamic adjustment and optimization capabilities, making it difficult to achieve accurate load tracking and balancing in complex and changeable power systems. Traditional systems also lack effective feedback and adjustment mechanisms and are unable to detect and correct deviations in a timely manner during operation, resulting in a decline in system performance and affecting the stability and reliability of power supply.

[0004] Therefore, an adaptive power execution device and distribution method for an energy storage system is invented, aiming to solve the shortcomings of traditional energy storage systems in adaptive load tracking and balancing through technological innovation, and to provide strong support for the safe and efficient operation of the power system. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide an adaptive power execution device and distribution method for an energy storage system, which can significantly improve the load tracking and balancing capabilities of the energy storage system in the power system through real-time data acquisition, high-precision prediction, intelligent control strategy optimization and closed-loop feedback adjustment. It not only solves the problems of low prediction accuracy, fixed control strategy and lack of feedback mechanism in traditional technologies, but also ensures that the energy storage system can respond flexibly in complex and changeable power systems to achieve efficient and stable operation. At the same time, the highly integrated safety protection and fault monitoring functions further enhance the reliability and safety of the system.

[0006] 2. In order to solve the above technical problems, the present invention provides the following technical solutions: On the one hand, an adaptive power execution device for an energy storage system, characterized in that the device comprises:

[0007] Load monitoring module: collects key parameters of current and voltage of the power grid and load in real time through high-precision sensors, and uses processing units for preprocessing and storage;

[0008] Forecasting and analysis module: Based on the data provided by the load monitoring module, combined with historical load data, external factors and advanced forecasting algorithms, load forecasting and analysis are carried out to predict the load change trend in the future;

[0009] Strategy formulation module: formulates an adaptive power adjustment strategy based on the output results of the prediction and analysis module and the current state of the energy storage system;

[0010] Power execution and control module: Through power electronic converters and controllers, according to the instructions of the strategy formulation module, the charging and discharging process of the energy storage system is accurately controlled to achieve automatic power adjustment;

[0011] Feedback and optimization module: collects the adjusted system operation status data, including actual load changes and energy storage system charging and discharging status, compares and analyzes them with the prediction results, evaluates the effect of the power adjustment strategy, and continuously optimizes and improves the strategy based on the evaluation results;

[0012] Safety protection and fault monitoring module: monitors the operating status of the energy storage system in real time. Once an abnormal situation is found, protective measures are taken immediately to prevent system damage and safety accidents. It also has fault recording and alarm functions to facilitate fault troubleshooting and subsequent maintenance.

[0013] Communication and interface module: realize data exchange and command transmission between the device and other systems.

[0014] Furthermore, the working principle of the system is as follows: the load monitoring module collects the key parameters of the current and voltage of the power grid and the load in real time through high-precision sensors and data processing units, and after preprocessing and storage, provides an accurate data basis for the prediction and analysis module. The prediction and analysis module uses these data, combined with historical load data, external factors and advanced prediction algorithms, to predict the load change trend in the future. The strategy formulation module formulates an adaptive power adjustment strategy for balancing the charging and discharging process of the energy storage system based on the prediction results and the current state of the energy storage system. After receiving the strategy instructions, the power execution and control module accurately controls the charging and discharging of the energy storage system through power electronic converters and controllers to achieve automatic power adjustment. In this process, the feedback and optimization module collects system operation status data, compares and analyzes it with the prediction results, evaluates the effect of the power adjustment strategy, and continuously optimizes the strategy. At the same time, the safety protection and fault monitoring module always monitors the system operation and takes protection measures immediately when abnormalities are found. The communication and interface module ensures data exchange and collaborative control between the device and other systems to achieve collaborative work of each module.

[0015] On the other hand, an adaptive power allocation method for an energy storage system is provided, wherein the specific steps of the allocation method are as follows:

[0016] S100, real-time data collection and preprocessing: collecting real-time load data of the power system, generator output value and transformer ratio value data, preprocessing and storing the collected data;

[0017] S200, load forecasting: Based on the preprocessed data, the time series model ARIMA is used to capture the time dependence and periodicity characteristics of the load data, and the linear regression model is used to make accurate forecasts by learning the relationship between historical data and future loads;

[0018] S300, formulation of optimization control strategy: determining the objective function based on the load forecast results and real-time system parameters, and establishing a control model, using the optimization algorithm to search and optimize the parameters in the control model, and providing an optimization control strategy for the energy storage system;

[0019] S400, adaptive power allocation: According to the optimization control strategy, the power output of the energy storage system is dynamically adjusted. When it is predicted that the load will increase significantly, the discharge power of the energy storage system is increased in advance. When it is predicted that the load will decrease, the discharge power is appropriately reduced and the charging mode is switched;

[0020] S500, feedback and adjustment: During the actual operation process, the operating status and load changes are continuously monitored. By comparing the difference between the actual load and the predicted load, the effectiveness of the optimized control strategy is evaluated. Once a large deviation and system performance degradation are found, the feedback mechanism will be immediately triggered to adjust and optimize the control strategy in real time.

[0021] Furthermore, the S100 includes:

[0022] S101, install sensors and data collection equipment at key nodes of the power system, and establish transmission channels with the data processing center through a stable communication network;

[0023] S102, start the collection equipment to collect the power system load, generator and transformer data in real time;

[0024] S103, the data processing center receives the real-time data and performs integrity check;

[0025] S104, cleaning the received data, detecting and removing outliers, and normalizing the data;

[0026] S105, securely storing the preprocessed data in a database.

[0027] Furthermore, the S200 includes:

[0028] S201, extracting load forecast related data from the preprocessed data set, and further screening and sorting the extracted data;

[0029] S202, applying the ARIMA model to perform time series analysis to capture the time dependence and periodicity characteristics in the load data;

[0030] S203, constructing a linear regression model to learn the relationship between historical data and future loads and accurately predict future loads;

[0031] S204, integrating the ARIMA model with the time series prediction results and the linear regression model prediction results to improve the prediction accuracy;

[0032] S205, evaluate the prediction results, compare with the actual data to analyze the cause of the error, and optimize the model.

[0033] Furthermore, the S202 applies the ARIMA model to perform time series analysis to capture the time dependence and periodicity characteristics in the load data, and performs a stationarity test on the collected original load data. If the data is not stationary, differential processing is performed until the data meets the stationarity requirement. The general form of the ARIMA model is: Among them, Y t is the load value at the current moment, φ i and θ j are the autoregressive and moving average parameters, p is the autoregressive order, q is the moving average order, ∈ t It is a white noise sequence. When determining the model parameters p, d and q, the information criterion AIC is used to evaluate the advantages and disadvantages of different models. The formula is: AIC = -2ln(L) + 2k, where L is the likelihood function, k is the number of model parameters, and n is the number of samples. The combination of p and q with the smallest AIC value is selected as the optimal model parameter. After determining the parameters, the root mean square error is calculated using real-time data to evaluate the fitting effect. The root mean square error formula is: in, Based on these evaluation indicators on the test set, the model with the best fitting effect and prediction accuracy is selected to analyze the data.

[0034] Furthermore, the S203 constructs a linear regression model to learn the relationship between historical data and future load, so as to achieve accurate prediction of future load. The basic form of the linear regression model is: Y = β0 + β1X1 + β2X2 + ... + β n X n +∈, where Y represents the future load, X1,X2,…,X n are historical loads, timestamps, and weather conditions, β0 is the intercept term, β1, β2, …, βn is the regression coefficient of the characteristic, ∈ is the error term, collects historical load data and related characteristic data, and randomly initializes the regression coefficients β0, β1, β2, …, β n , define the square error function as the loss function, and the mean square error formula is: Where m is the number of samples, y i is the actual load value, The load value predicted by the model is minimized using the gradient descent algorithm to update the regression coefficient. The trained model is evaluated by calculating the mean absolute error using the test data. The mean absolute error formula is: The model is optimized based on the evaluation results so that it can effectively learn the relationship between historical data and future loads, thereby achieving accurate prediction of future loads.

[0035] Furthermore, the S300 includes:

[0036] S301, constructing a control model based on the characteristics of the energy storage system, taking the load forecast results and real-time system parameters as input to simulate the behavior under different operating conditions;

[0037] S302, defining the operating cost as the optimization target to construct an objective function, determining various constraints during the operation of the energy storage system and embedding them into the model;

[0038] S303, selecting a genetic algorithm as the optimization algorithm, initializing the algorithm state, performing an iterative search within the control model, and gradually optimizing the objective function value by continuously adjusting the control parameters;

[0039] S304, evaluate the optimization results to formulate a control strategy, and apply it in actual operation, and perform feedback adjustment and optimization on the control strategy based on data monitoring and analysis.

[0040] Furthermore, the S400 includes:

[0041] S401, collect the energy storage system operation status data in real time and perform load forecasting, evaluate the impact according to the optimization control strategy, and determine the power adjustment range and target;

[0042] S402, when it is predicted that the load will increase significantly, the discharge power will be increased in advance and the power will be monitored; when it is predicted that the load will decrease, the discharge power will be appropriately reduced and the charging mode will be switched to reduce the cost;

[0043] S403, continuously monitoring the operating status and load changes during power adjustment, and fine-tuning the power allocation strategy according to the feedback to achieve a high degree of matching with the load demand;

[0044] S404: Ensure the safe operation of the energy storage system during power adjustment, monitor key indicators, and activate emergency plans in extreme situations to ensure the stability and reliability of the power system.

[0045] Furthermore, the S500 includes:

[0046] S501, the system collects and saves the operating status data of the energy storage system in real time, and compares the real-time and predicted load data to calculate the difference and analyze the cause;

[0047] S502, evaluating the effectiveness of the optimization control strategy based on the load difference, setting a deviation threshold, and triggering a feedback mechanism when a large deviation and system performance degradation are detected;

[0048] S503, after the feedback mechanism is triggered, the control strategy is automatically adjusted according to the deviation analysis and effectiveness evaluation, and the effect is continuously monitored and verified after the adjustment;

[0049] S504: During the entire process, the energy storage system is always guaranteed to operate safely and stably, key indicators are monitored to prevent failures, strategies are continuously optimized, and experience is accumulated to improve the level of intelligence.

[0050] Compared with the prior art, the energy storage system adaptive power execution device and distribution method have the following beneficial effects:

[0051] 1. The present invention realizes accurate prediction of future load changes by real-time collection and preprocessing of key data of power system loads, generators and transformers, combined with time series analysis and linear regression advanced prediction algorithms. Based on these prediction results, the device can automatically formulate and optimize the power allocation strategy of the energy storage system to ensure rapid response when load fluctuates and realize dynamic adjustment of the output power of the energy storage system. This adaptive capability not only effectively alleviates the contradiction between supply and demand in the power system, but also significantly improves the stability and reliability of power supply, providing a strong guarantee for the safe operation of the power system.

[0052] 2. The present invention monitors the operating status and load changes of the energy storage system in real time, evaluates the actual effect of the optimized control strategy, and immediately triggers the feedback mechanism when large deviations and system performance degradation are found, and adjusts the control strategy in real time. This closed-loop control strategy ensures that the energy storage system always remains in the best working state, maximizes the regulation ability and economic benefits of the energy storage system, and at the same time, the device also has a high degree of safety protection and fault monitoring functions to ensure that the emergency plan can be quickly activated in extreme situations to ensure the stable and reliable operation of the power system.

[0053] Other advantages, objectives and features of the present invention will be set forth in part in the following description and in part will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 It is a structural schematic diagram of an adaptive power execution device of an energy storage system;

[0056] Figure 2 The present invention is a flow chart of an adaptive power allocation method for an energy storage system. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] A method for adaptive power distribution of an energy storage system comprises the following steps: real-time data acquisition and preprocessing, load forecasting, formulation of an optimization control strategy, adaptive power distribution, feedback and adjustment.

[0060] First, enter the real-time data collection and preprocessing stage (S100), install high-precision sensors and data acquisition equipment at key nodes of the power system, these devices include but are not limited to load monitoring sensors, generator operation status monitoring sensors, transformer temperature and current and voltage sensors, ensure that all devices establish efficient transmission channels with the data processing center through a stable and reliable communication network to ensure the real-time and accuracy of the data, start the data acquisition equipment installed on the key nodes, collect the power system load, load power of generators and transformers, generator output power, transformer load rate, voltage and current values ​​every 5 minutes, after receiving the real-time data, the data processing center performs data integrity check to check whether the data packet is complete, whether the timestamp is continuous, and whether the data field is complete, and further processes the data that passes the integrity check, including data cleaning, abnormal value detection and removal, data normalization, and safely stores the preprocessed data in the database.

[0061] Next, the load forecasting stage (S200) is entered. Data directly related to load forecasting are extracted from the preprocessed data set. These data usually include historical load values, weather conditions, holiday information, and special event markers. The extracted data are further screened and sorted to remove noise data, fill in missing values, and ensure the time series and consistency of the data. The ARIMA model is applied to perform time series analysis on the screened load data. The ARIMA model predicts future load trends by identifying time dependence and periodicity characteristics in the data. A linear regression model is constructed to learn the potential relationship between historical data and future loads. Weather conditions and holiday factors are included as independent variables in the model. The model parameters are estimated by the least squares method, and the model's fit and prediction ability are evaluated. The time series prediction results of the ARIMA model are fused with the prediction results of the linear regression model by weighted averaging. The fused prediction results will serve as an important basis for the power allocation strategy of the energy storage system. The prediction results are evaluated, and the predicted values ​​are compared with the actual load data. The error index is calculated to quantify the accuracy of the prediction, and the causes of the errors are analyzed. Based on the evaluation results, the ARIMA model and the linear regression model are optimized and adjusted to improve the prediction performance of the model.

[0062] Subsequently, the optimization control strategy formulation phase (S300) is entered. A control model is constructed according to the physical characteristics and technical specifications of the energy storage system to simulate the behavior of the energy storage system under different operating conditions. The load forecast results and real-time system parameters are input into the control model as input data. These input data will be used to simulate the operation of the energy storage system at different time points to evaluate its impact on the stability and economy of the power grid, clarify the optimization goal of the energy storage system operation, and minimize the operating cost. Based on this goal, an objective function is constructed, which will include the various operating costs of the energy storage system, determine the various constraints during the operation of the energy storage system, and embed these constraints into the control model. In the model, the genetic algorithm is selected as the optimization algorithm to solve the optimal solution of the objective function. The results of the genetic algorithm optimization are used to formulate the control strategies of the energy storage system. These control strategies will guide the charging and discharging behaviors of the energy storage system at different time points to achieve the predetermined optimization goals. The control strategies are applied to actual operations, and the operating status and grid parameters of the energy storage system are monitored in real time through the data monitoring system. The control strategies are feedback adjusted and optimized based on the monitoring data to cope with various situations that may arise in actual operation, ensure that the energy storage system can operate stably and efficiently, regularly evaluate the effectiveness of the control strategies, and make necessary adjustments and improvements to the control model, objective function and optimization algorithm based on the evaluation results.

[0063] Then, enter the adaptive power allocation stage (S400), collect the energy storage system operation status data in real time and perform load forecasting, evaluate the impact according to the optimization control strategy, evaluate the impact on electricity cost, system stability and battery life based on the operation conditions under different control strategies, determine the optimal power adjustment range and target, increase the discharge power in advance and monitor the power when the load is predicted to increase significantly, and the load warning mechanism is automatically triggered when the load is predicted to increase significantly, adjust the discharge power in advance to meet the peak demand and monitor the remaining power, continuously monitor the operation status and load changes during power adjustment, use the monitoring system to track the operation status and load changes in real time, dynamically adjust the power allocation strategy according to the monitoring data to ensure matching and reduce energy loss, optimize the power allocation algorithm by collecting feedback and operation data to improve the adaptive ability and response speed, ensure the safe operation of the energy storage system during power adjustment, formulate emergency plans to deal with extreme weather and equipment failures to ensure the stability and reliability of the power system, and regularly perform maintenance and inspections on the energy storage system, including battery pack performance testing and cooling system cleaning to prevent hidden dangers and extend service life.

[0064] Finally, the feedback and adjustment stage (S500) is entered to ensure that the system can collect and save various operating status data of the energy storage system in real time, receive the predicted load data from the load prediction module in real time, and compare it with the current actual load data. By calculating the difference between the real-time load and the predicted load and analyzing the causes of these differences, the effectiveness of the current control strategy is evaluated based on the load difference, and a series of deviation thresholds are set. When the system detects that the difference between the real-time load and the predicted load exceeds the set deviation threshold and is accompanied by signs of system performance degradation, the feedback mechanism will be automatically triggered. After the feedback mechanism is triggered, the system will first automatically adjust the control strategy based on the deviation analysis and the effectiveness evaluation results of the control strategy. The adjustment may involve changing the charging and discharging strategy, adjusting the SOC target range, and optimizing the charging and discharging power distribution. The adjusted control strategy will be immediately applied to the actual operation of the energy storage system, and its effect will be verified through continuous data monitoring. By real-time monitoring of key indicators, potential faults can be prevented, and corresponding measures will be taken in time when abnormal conditions are found. The system continuously optimizes the control strategy and accumulates experience to improve its intelligence level. Through continuous monitoring, evaluation and optimization, the energy storage system can maintain an efficient, stable and safe operating state under various complex and changeable operating conditions.

[0065] Example 2

[0066] An adaptive power execution device and distribution method for an energy storage system particularly emphasizes the functions of tracking load changes and automatically balancing power.

[0067] Data directly related to load forecasting are extracted from the preprocessed data set, including but not limited to historical load values, timestamps, weather conditions, and other external factors that may affect the load. The extracted data are further screened and sorted to remove noise data and fill in missing values.

[0068] Entering the time series analysis stage, the collected original load data is tested for stationarity. If the data is not stationary, differential processing is performed until the data meets the stationarity requirements. Based on the stationary data, an ARIMA model is constructed to capture the time dependence and periodicity characteristics of the load data. The general form of the ARIMA model is: The information criterion AIC is used to evaluate the pros and cons of different models. The formula is: AIC = -2ln(L) + 2k, where L is the likelihood function, k is the number of model parameters, and n is the number of samples. The combination of p and q with the smallest AIC value is selected as the optimal model parameter. After the parameters are determined, the root mean square error is calculated using real-time data to evaluate the fitting effect. The root mean square error formula is: in, is the predicted value, Y iis the actual value. By comparing these evaluation indicators of different models on the test set, the model with the best fitting effect and prediction accuracy is selected to analyze the data.

[0069] A linear regression model is constructed to learn the relationship between historical data and future load, so as to achieve accurate prediction of future load. The basic form of the linear regression model is: Y = β0 + β1X1 + β2X2 + … + β n X n +∈, extract the historical load data and related feature data from the feature data, and randomly initialize the regression coefficients β0,β1,β2,…,β n , define the square error function as the loss function, and the mean square error formula is: Where m is the number of samples, y i is the actual load value, The load value predicted by the model is minimized using the gradient descent algorithm to update the regression coefficient. The trained model is evaluated by calculating the mean absolute error using the test data. The mean absolute error formula is: The model is optimized based on the evaluation results so that it can effectively learn the relationship between historical data and future loads, thereby achieving accurate prediction of future loads.

[0070] After obtaining the prediction results of the ARIMA model and the linear regression model, the two are fused through weighted averaging. The fused prediction results combine the advantages of the two models, compare the predicted values ​​with the actual load data, calculate the error index and analyze the causes of the errors. According to the evaluation results, the model is further optimized and adjusted to improve the efficiency and accuracy of the adaptive power allocation of the energy storage system.

[0071] A control model is constructed based on the physical characteristics and operating requirements of the energy storage system to reflect the key factors of the charging and discharging capacity of the energy storage equipment. The load forecast results and real-time system parameters are used as input to simulate its behavior under different conditions. Minimizing the operating cost is clearly defined as the goal of the optimization control strategy. An objective function is constructed to quantify the evaluation effect. Various constraints are determined and embedded in the model as mathematical expressions. A genetic algorithm is selected as the optimization algorithm. The algorithm parameters are set and the state is initialized. The control parameters are iteratively searched and adjusted within the control model to optimize the objective function. The output results of the optimization algorithm are evaluated, the constraints and the objective function effects are checked, and the optimization control strategy is formulated and simulated for verification. The strategy is applied to actual operation and dynamically adjusted according to real-time parameters and forecast results. The operating status and performance indicators are monitored, and data is collected and analyzed to provide feedback to adjust the optimization strategy to improve the overall operating efficiency and economy of the energy storage system.

[0072] Collect the operating status data of the energy storage system in real time, use advanced load forecasting technology, combine historical data and current system status, accurately predict the load changes in the future, and in the application of optimization control strategy, evaluate the impact of the current load forecast results on the energy storage system according to the pre-established strategy, determine the reasonable power adjustment range and target, increase the discharge power in advance and monitor the remaining power when a significant increase in load is predicted, appropriately reduce the discharge power when the load is predicted to decrease, and switch to charging mode when conditions permit and it is economically reasonable to reduce costs. During the power adjustment process, continuously monitor the operating status and load changes, fine-tune the power allocation strategy according to real-time feedback data to ensure that the output is highly matched with the load demand, always ensure safe operation when making power adjustments, avoid overcharging and over-discharging, monitor key indicators to ensure operation within a safe range, and quickly launch emergency plans in extreme cases to ensure the stability and reliability of the power system.

[0073] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An adaptive power execution device for an energy storage system, characterized in that: The device includes: Load monitoring module: collects key parameters of current and voltage of the power grid and load in real time through high-precision sensors, and uses processing units for preprocessing and storage; Forecasting and analysis module: Based on the data provided by the load monitoring module, combined with historical load data, external factors and advanced forecasting algorithms, load forecasting and analysis are carried out to predict the load change trend in the future; Strategy formulation module: formulates an adaptive power adjustment strategy based on the output results of the prediction and analysis module and the current state of the energy storage system; Power execution and control module: Through power electronic converters and controllers, according to the instructions of the strategy formulation module, the charging and discharging process of the energy storage system is accurately controlled to achieve automatic power adjustment; Feedback and optimization module: collects the adjusted system operation status data, including actual load changes and energy storage system charging and discharging status, compares and analyzes them with the prediction results, evaluates the effect of the power adjustment strategy, and continuously optimizes and improves the strategy based on the evaluation results; Safety protection and fault monitoring module: monitors the operating status of the energy storage system in real time. Once an abnormal situation is found, protective measures are taken immediately to prevent system damage and safety accidents. It also has fault recording and alarm functions to facilitate fault troubleshooting and subsequent maintenance. Communication and interface module: realize data exchange and command transmission between the device and other systems.

2. According to claim 1, an energy storage system adaptive power execution device is characterized in that: The working principle of the system is as follows: the load monitoring module collects the key parameters of the current and voltage of the power grid and the load in real time through high-precision sensors and data processing units, and provides an accurate data basis for the prediction and analysis module after preprocessing and storage. The prediction and analysis module uses these data, combined with historical load data, external factors and advanced prediction algorithms, to predict the load change trend in the future. The strategy formulation module formulates an adaptive power adjustment strategy for balancing the charging and discharging process of the energy storage system based on the prediction results and the current state of the energy storage system. After receiving the strategy instructions, the power execution and control module accurately controls the charging and discharging of the energy storage system through power electronic converters and controllers to achieve automatic power adjustment. In this process, the feedback and optimization module collects system operation status data, compares and analyzes it with the prediction results, evaluates the effect of the power adjustment strategy, and continuously optimizes the strategy. At the same time, the safety protection and fault monitoring module always monitors the system operation and takes protection measures immediately when abnormalities are found. The communication and interface module ensures data exchange and collaborative control between the device and other systems to achieve collaborative work of each module.

3. An adaptive power allocation method for an energy storage system, characterized in that: The specific steps of this allocation method are: S100, real-time data collection and preprocessing: collecting real-time load data of the power system, generator output value and transformer ratio value data, preprocessing and storing the collected data; S200, load forecasting: Based on the preprocessed data, the time series model ARIMA is used to capture the time dependence and periodicity characteristics of the load data, and the linear regression model is used to make accurate forecasts by learning the relationship between historical data and future loads; S300, formulation of optimization control strategy: determining the objective function based on the load forecast results and real-time system parameters, and establishing a control model, using the optimization algorithm to search and optimize the parameters in the control model, and providing an optimization control strategy for the energy storage system; S400, adaptive power allocation: According to the optimization control strategy, the power output of the energy storage system is dynamically adjusted. When it is predicted that the load will increase significantly, the discharge power of the energy storage system is increased in advance. When it is predicted that the load will decrease, the discharge power is appropriately reduced and the charging mode is switched; S500, feedback and adjustment: During the actual operation process, the operating status and load changes are continuously monitored. By comparing the difference between the actual load and the predicted load, the effectiveness of the optimized control strategy is evaluated. Once a large deviation and system performance degradation are found, the feedback mechanism will be immediately triggered to adjust and optimize the control strategy in real time.

4. The method for adaptive power allocation of an energy storage system according to claim 3, characterized in that: The S100 includes: S101, install sensors and data collection equipment at key nodes of the power system, and establish transmission channels with the data processing center through a stable communication network; S102, start the collection equipment to collect the power system load, generator and transformer data in real time; S103, the data processing center receives the real-time data and performs integrity check; S104, cleaning the received data, detecting and removing outliers, and normalizing the data; S105, securely storing the preprocessed data in a database.

5. The method for adaptive power allocation of an energy storage system according to claim 3, characterized in that: The S200 includes: S201, extracting load forecast related data from the preprocessed data set, and further screening and sorting the extracted data; S202, applying the ARIMA model to perform time series analysis to capture the time dependence and periodicity characteristics in the load data; S203, constructing a linear regression model to learn the relationship between historical data and future loads and accurately predict future loads; S204, integrating the ARIMA model with the time series prediction results and the linear regression model prediction results to improve the prediction accuracy; S205, evaluate the prediction results, compare with the actual data to analyze the cause of the error, and optimize the model.

6. The method for adaptive power allocation of an energy storage system according to claim 5, characterized in that: The S202 applies the ARIMA model to perform time series analysis to capture the time dependence and periodicity characteristics in the load data, and performs a stationarity test on the collected original load data. If the data is not stationary, differential processing is performed until the data meets the stationarity requirement. The general form of the ARIMA model is: Among them, Y t is the load value at the current moment, φ i and θ j are the autoregressive and moving average parameters, p is the autoregressive order, q is the moving average order, ∈ t It is a white noise sequence. When determining the model parameters p, d and q, the information criterion AIC is used to evaluate the advantages and disadvantages of different models. The formula is: AIC = -2ln(L) + 2k, where L is the likelihood function, k is the number of model parameters, and n is the number of samples. The combination of p and q with the smallest AIC value is selected as the optimal model parameter. After determining the parameters, the root mean square error is calculated using real-time data to evaluate the fitting effect. The root mean square error formula is: in, is the predicted value, Y i is the actual value. By comparing these evaluation indicators of different models on the test set, the model with the best fitting effect and prediction accuracy is selected to analyze the data.

7. The method for adaptive power allocation of an energy storage system according to claim 5, characterized in that: S203 constructs a linear regression model to learn the relationship between historical data and future load, so as to achieve accurate prediction of future load. The basic form of the linear regression model is: Y = β0 + β1X1 + β2X2 + ... + β n X n +∈, where Y represents the future load, X1,X2,(,X n is the historical load, timestamp, and weather condition, β0 is the intercept term, β1,β2,(,β n is the regression coefficient of the characteristic, ∈ is the error term, collects historical load data and related characteristic data, and randomly initializes the regression coefficients β0, β1, β2, …, β n , define the square error function as the loss function, and the mean square error formula is: Where m is the number of samples, y i is the actual load value, The load value predicted by the model is minimized using the gradient descent algorithm to update the regression coefficient. The trained model is evaluated by calculating the mean absolute error using the test data. The mean absolute error formula is: The model is optimized based on the evaluation results so that it can effectively learn the relationship between historical data and future loads, thereby achieving accurate prediction of future loads.

8. The method for adaptive power allocation of an energy storage system according to claim 3, characterized in that: The S300 includes: S301, constructing a control model based on the characteristics of the energy storage system, taking the load forecast results and real-time system parameters as input to simulate the behavior under different operating conditions; S302, defining the operating cost as the optimization target to construct an objective function, determining various constraints during the operation of the energy storage system and embedding them into the model; S303, selecting a genetic algorithm as the optimization algorithm, initializing the algorithm state, performing an iterative search within the control model, and gradually optimizing the objective function value by continuously adjusting the control parameters; S304, evaluate the optimization results to formulate a control strategy, and apply it in actual operation, and perform feedback adjustment and optimization on the control strategy based on data monitoring and analysis.

9. The method for adaptive power allocation of an energy storage system according to claim 3, characterized in that: The S400 includes: S401, collect the energy storage system operation status data in real time and perform load forecasting, evaluate the impact according to the optimization control strategy, and determine the power adjustment range and target; S402, when it is predicted that the load will increase significantly, the discharge power will be increased in advance and the power will be monitored; when it is predicted that the load will decrease, the discharge power will be appropriately reduced and the charging mode will be switched to reduce the cost; S403, continuously monitoring the operating status and load changes during power adjustment, and fine-tuning the power allocation strategy according to the feedback to achieve a high degree of matching with the load demand; S404: Ensure the safe operation of the energy storage system during power adjustment, monitor key indicators, and activate emergency plans in extreme situations to ensure the stability and reliability of the power system.

10. The method for adaptive power allocation of an energy storage system according to claim 3, characterized in that: The S500 includes: S501, the system collects and saves the operating status data of the energy storage system in real time, and compares the real-time and predicted load data to calculate the difference and analyze the cause; S502, evaluating the effectiveness of the optimization control strategy based on the load difference, setting a deviation threshold, and triggering a feedback mechanism when a large deviation and system performance degradation are detected; S503, after the feedback mechanism is triggered, the control strategy is automatically adjusted according to the deviation analysis and effectiveness evaluation, and the effect is continuously monitored and verified after the adjustment; S504: During the entire process, the energy storage system is always guaranteed to operate safely and stably, key indicators are monitored to prevent failures, strategies are continuously optimized, and experience is accumulated to improve the level of intelligence.

Citation Information

Patent Citations

  • Energy management and control device and method for multi-energy ship

    CN112510701A

  • Power load scheduling method and system based on big data

    CN116646933A

  • Intelligent energy storage charging system

    CN117411039A

Cited By

  • Electric vehicle charging method and system with optimized power grid load

    CN119209528A

  • Independent electrochemical energy storage integrated management system

    CN119315611A

  • An independent electrochemical energy storage integrated management system

    CN119315611B

  • Self-adaptive power balance control method of wind-solar hybrid power generation system

    CN119482745A

  • Microgrid electrochemical energy storage management method and system, terminal and storage medium

    CN119582300A