Energy distribution optimization adjustment method for energy storage system

Abstract

The invention provides an energy distribution optimization adjustment method for an energy storage system, and belongs to the technical field of energy storage management, and the method comprises the steps: obtaining a basic structure of the energy storage system, carrying out the structural decomposition of the basic structure, and deploying a sensor according to a structural decomposition result. Obtaining internal system data and external environment data of the energy storage system based on a deployment result, determining an energy optimization target, carrying out data fusion on the internal system data and the external environment data according to the energy optimization target, extracting influence distribution characteristics from the fused data, and establishing a prediction model; key factors and distribution trends of each energy optimization target are identified according to the prediction model, an energy distribution strategy is determined, energy storage system configuration is optimized according to the energy distribution strategy, a configuration result is fed back to the prediction model, dynamic optimization and intelligent management are achieved, power demand changes are responded in real time, the energy distribution strategy is optimized, and energy storage system configuration is optimized. And the overall efficiency of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage management, and in particular to an energy distribution optimization and regulation method for an energy storage system. Background Art

[0002] With the rapid development of renewable energy, especially the widespread application of solar and wind energy, the power system is facing increasing energy management challenges. As an important link between renewable energy and the power grid, the energy storage system can effectively balance supply and demand and improve the stability and reliability of the power system. However, traditional energy storage management methods often fail to fully utilize the potential of energy storage equipment, have poor flexibility, and limit the comprehensive understanding of energy demand.

[0003] Therefore, the present invention provides an energy distribution optimization and regulation method for an energy storage system. Summary of the invention

[0004] The present invention provides an energy distribution optimization and adjustment method for an energy storage system. The basic structure of the energy storage system is obtained through structural decomposition and sensor deployment, and internal and external data are collected in real time for fusion to clarify the energy optimization target. By extracting features to establish a prediction model, identifying key factors and distribution trends, formulating an energy distribution strategy, and finally adjusting the energy storage system configuration and feeding back to the model, dynamic optimization and intelligent management are achieved, and changes in power demand are responded to in real time, and energy distribution strategies are optimized, thereby improving the overall efficiency of the system.

[0005] The present invention provides an energy distribution optimization and regulation method for an energy storage system, comprising: Step 1: Obtain the basic structure of the energy storage system, decompose the basic structure, and deploy sensors based on the decomposition results; Step 2: Based on the deployment results, the internal system data and external environment data of the energy storage system are obtained, the energy optimization target is clarified, and the internal system data and the external environment data are integrated according to the energy optimization target; Step 3: Extract the features that affect allocation from the fused data to establish a prediction model, identify the key factors and allocation trends of each energy optimization target based on the prediction model, and determine the energy allocation strategy; Step 4: Optimize the energy storage system configuration according to the energy allocation strategy, and feed the configuration results back to the prediction model.

[0006] The present invention provides an energy distribution optimization and regulation method for an energy storage system, which obtains the basic structure of the energy storage system, decomposes the basic structure, and deploys sensors according to the decomposition result, including: Acquire a system type and an application scenario of the energy storage system, and determine a basic structure of the energy storage system based on the system type and the application scenario; The basic structure is first decomposed according to different functions of the energy storage system, and secondly decomposed according to the physical components of the energy storage system. The parameters to be detected are determined by combining the first decomposition result and the second decomposition result, and the internal detection points corresponding to each parameter to be detected and the external detection points related to the application scenario are selected according to the application scenario, and then the detection scheme is set, and the sensors are deployed according to the detection scheme.

[0007] The present invention provides an energy distribution optimization and regulation method for an energy storage system, which obtains internal system data and external environment data of the energy storage system based on a deployment result, clarifies an energy optimization target, and performs data fusion on the internal system data and the external environment data according to the energy optimization target, including: Determine the specific links that require energy prediction based on the energy optimization goal; Obtain historical load data of the supply side related to the energy storage system, draw a load line graph based on the historical load data, identify load trends and load periodic changes from the load line graph, perform seasonal analysis on the load line graph, determine load seasonal changes, and derive energy demand points based on the load trends, load periodic changes, and load seasonal changes; According to the energy demand points combined with specific links, a set of key decision points is obtained, and a comprehensive score is performed based on the key decision point set and the energy optimization target. Based on the comprehensive score, the data fusion strategy corresponding to the key decision point is determined, and the internal system data and the external environment data are fused according to the data fusion strategy.

[0008] The present invention provides an energy distribution optimization and regulation method for an energy storage system, which obtains a key decision point set according to energy demand points combined with specific links, performs comprehensive scoring according to the key decision point set and energy optimization goals, and determines a data fusion strategy corresponding to the key decision point based on the comprehensive scoring, including: According to the energy demand point combined with the specific links, a first dynamic threshold, a second dynamic threshold and a third dynamic threshold are set, a charging decision point is determined according to the first dynamic threshold, a discharging decision point is determined according to the second dynamic threshold, and an emergency decision point is determined according to the third dynamic threshold, and the charging decision point, the discharging decision point and the emergency decision point are combined to form a key decision point set; Determine external influencing factors based on external environment data corresponding to key decision points, score the key decision point set based on the external influencing factors, and obtain a comprehensive score for each key decision point; Match the data fusion strategy of the key decision point corresponding to each comprehensive score from the score-strategy table.

[0009] The present invention provides an energy distribution optimization and regulation method for an energy storage system, which determines external influencing factors according to external environmental data corresponding to key decision points, scores a set of key decision points according to the external influencing factors, and obtains a comprehensive score for each key decision point, including: ,in, represents the comprehensive score between the i-th key decision point and the energy optimization target; The weight coefficient of the i-th key decision point; represents the i-th key decision point in the key decision point set; represents the weight coefficient of the i-th key decision point for the energy optimization target at time t; represents the energy optimization objective at time t; represents the weight coefficient of the jth external influencing factor; represents the jth external influencing factor; represents the interaction coefficient between the i-th key decision point and the j-th external influencing factor; represents the error term of the i-th key decision point; i and k represent the indexes of the key decision points in the key decision point set; j and l represent the indexes of the external influencing factors; n represents the total number of key decision points in the key decision set; m represents the total number of external influencing factors.

[0010] The present invention provides an energy distribution optimization and regulation method for an energy storage system, extracts the influencing distribution features from the fusion data to establish a prediction model, identifies the key factors and distribution trends of each energy optimization target according to the prediction model, and determines the energy distribution strategy, including: Based on the energy optimization goal, the key features in the fusion data are identified, and the principal component analysis is performed on the key features according to the energy optimization goal. The influence distribution features that have an impact on the energy optimization goal are screened out according to the principal component analysis results; Matching the initial model from the target-model library according to the energy optimization goal, and deriving the prediction model in combination with the impact distribution characteristics; Forecast energy demand based on the output of the forecast model, analyze the forecasted energy demand, identify the distribution trend and key factors of energy demand, and determine the energy allocation strategy.

[0011] The present invention provides an energy distribution optimization and regulation method for an energy storage system, which outputs a predicted energy demand according to a prediction model, analyzes the predicted energy demand, identifies the distribution trend and key factors of the energy demand, and determines an energy distribution strategy, including: For a set of key decision points, scenario analysis is performed to evaluate the predicted energy demand under different scenarios and the impact of changes in predicted energy demand on the allocation of energy demand; The distribution trend and key factors of energy demand are determined based on the evaluation results, and then the energy allocation strategy for each key decision point is determined in combination with the key decision point set.

[0012] The present invention provides an energy distribution optimization and regulation method for an energy storage system, which optimizes the energy storage system configuration according to the energy distribution strategy and feeds back the configuration result to a prediction model, including: Determine the response requirements of the energy storage system in different time periods according to the energy allocation strategy, evaluate the system configuration of the current energy storage system, and determine whether the existing configuration meets the energy allocation strategy; Optimizing the energy allocation strategy according to the satisfaction, and formulating an adjustment plan for the energy storage system configuration based on the optimization result; Compare the configuration results with the output of the prediction model and make feedback adjustments to the prediction model.

[0013] Compared with the prior art, the beneficial effects of this application are as follows: the basic structure of the energy storage system is obtained through structural decomposition and sensor deployment, internal and external data are collected in real time for fusion, and the energy optimization goal is clarified. By extracting features to establish a prediction model, identify key factors and distribution trends, formulate an energy distribution strategy, and finally adjust the energy storage system configuration and feed it back to the model, dynamic optimization and intelligent management are achieved, real-time response to changes in power demand, and energy distribution strategies are optimized, thereby improving the overall efficiency of the system.

[0014] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of an energy distribution optimization and regulation method for an energy storage system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] Embodiment 1: The embodiment of the present invention provides an energy distribution optimization adjustment method for an energy storage system, such as Figure 1 As shown, including: Step 1: Obtain the basic structure of the energy storage system, decompose the basic structure, and deploy sensors based on the decomposition results; Step 2: Based on the deployment results, the internal system data and external environment data of the energy storage system are obtained, the energy optimization target is clarified, and the internal system data and the external environment data are integrated according to the energy optimization target; Step 3: Extract the features that affect allocation from the fused data to establish a prediction model, identify the key factors and allocation trends of each energy optimization target based on the prediction model, and determine the energy allocation strategy; Step 4: Optimize the energy storage system configuration according to the energy allocation strategy, and feed the configuration results back to the prediction model.

[0019] In this embodiment, the basic structure is the core component of the energy storage system, for example, energy storage elements: such as lithium-ion batteries, pumped storage tanks, compressed air containers, energy converters: such as inverters (converting direct current to alternating current), transformers, control systems: such as battery management systems, monitoring software.

[0020] In this embodiment, the structural decomposition is a dual decomposition of the basic structure in terms of function and physical composition, and the structural decomposition result includes a first decomposition result and a second decomposition result.

[0021] In this embodiment, deploying sensors is to install sensors at determined detection points according to the detection scheme, for example, installing voltage sensors and temperature sensors in the battery pack, installing power sensors at the input and output ends of the inverter, and installing a data acquisition module in the control system.

[0022] In this embodiment, the basic structure of the energy storage system is determined by obtaining the type and application scenario of the energy storage system, and the basic structure is decomposed into functional and physical components, the parameters to be detected are identified, and detection points are selected according to the application scenario, a detection plan is formulated, and sensors are deployed.

[0023] In this embodiment, the deployment results include internal system data and external system data. The internal system data is data generated inside the energy storage system, which is usually related to the operating status and performance of the system, such as the battery state of charge (SOC), the battery discharge power and current, the system's temperature, pressure and other environmental parameters, the inverter's operating efficiency and output power; the external environment data is data related to the external environment of the energy storage system, which usually includes market, weather, load forecast and other information, such as meteorological data (such as temperature, humidity, wind speed).

[0024] In this embodiment, the energy optimization target is a specific goal that is desired to be achieved in the energy storage system, which is usually related to energy utilization efficiency, cost-effectiveness or environmental impact, such as maximizing the utilization rate of renewable energy and improving the response speed and stability of the system.

[0025] In this embodiment, data fusion is the integration of data from different sources to form a more comprehensive and consistent data set, for example, combining real-time load data from internal systems with external weather forecast data to generate a more accurate load forecast.

[0026] In this embodiment, by clarifying the energy optimization goal, identifying the links in the energy storage system that require energy prediction, obtaining historical load data and drawing a load line chart, analyzing load trends and seasonal changes, determining energy demand points, combining key decision point sets with energy optimization goals for scoring, formulating data fusion strategies, and finally integrating internal system data with external environmental data.

[0027] In this embodiment, fusion data refers to the integration of data from different sources or different types for comprehensive analysis and decision-making. For example, power market data, meteorological data, user power consumption data and energy storage system operation data can be combined together, such as weather forecasts (temperature, wind speed), electricity price history data, user power consumption patterns and renewable energy generation data to better predict future energy demand.

[0028] In this embodiment, the input of the prediction model is the characteristics that affect allocation, and the output is the prediction of future energy demand. For example, the input characteristics include temperature, wind speed, historical electricity consumption and electricity price, and the output is the electricity demand forecast for the next week.

[0029] In this embodiment, the distribution trend refers to the changing pattern and direction of energy demand under different time periods or conditions. For example, the analysis results may show that during the high temperature period in summer, the electricity demand increases significantly, forming a clear upward trend.

[0030] In this embodiment, the key factor energy refers to the factor that plays a major role in affecting energy demand, which is usually identified through analysis. For example, temperature changes are identified as a key factor affecting electricity demand because air conditioning usage increases when the temperature is high.

[0031] In this embodiment, the energy allocation strategy refers to an energy allocation and use plan developed based on prediction results and analysis, which aims to optimize resource utilization and meet demand. For example, when it is predicted that electricity demand will increase in summer, a strategy is developed to give priority to discharging the energy storage system during peak hours to reduce grid pressure and save costs.

[0032] In this embodiment, the system configuration is a standard for evaluating the efficiency and effectiveness of the energy storage system, including energy efficiency, response time, charge and discharge capability, cycle life, etc. For example, energy efficiency: the energy loss of the energy storage system during charging and discharging, usually expressed as a percentage, for example, the system energy efficiency is 90%, response time: the time required for the energy storage system to start discharging after receiving a command, such as 5 minutes.

[0033] In this embodiment, the optimization process refers to adjusting the energy allocation strategy based on the performance evaluation results of the current energy storage system to ensure that the energy storage system can better meet the demand, evaluating the system configuration of the existing energy storage system, determining the gap between the existing configuration and the corresponding requirements, and adjusting the energy allocation strategy based on the gap to improve system efficiency and responsiveness. For example, if it is found that the energy storage system cannot meet the demand during peak hours, the strategy can be adjusted to increase the charging time of the energy storage system.

[0034] In this embodiment, feedback adjustment refers to adjusting the prediction model based on the comparison results to improve its accuracy and reliability. This process is a cycle that aims to continuously optimize system performance. For example, if it is found that the prediction model underestimates the electricity demand during peak periods, the model parameters can be adjusted to increase sensitivity to changes in temperature and electricity consumption patterns, thereby improving prediction accuracy.

[0035] The working principle and beneficial effects of the above technical solution are: obtain the basic structure of the energy storage system through structural decomposition and sensor deployment, collect internal and external data in real time for fusion, and clarify the energy optimization goal. Establish a prediction model by extracting features, identify key factors and distribution trends, formulate energy distribution strategies, and finally adjust the energy storage system configuration and feedback to the model to achieve dynamic optimization and intelligent management, respond to changes in power demand in real time, optimize energy distribution strategies, and thus improve the overall efficiency of the system.

[0036] Embodiment 2: The embodiment of the present invention provides an energy distribution optimization and adjustment method for an energy storage system, which obtains the basic structure of the energy storage system, decomposes the basic structure, and deploys sensors according to the decomposition result, including: Acquire a system type and an application scenario of the energy storage system, and determine a basic structure of the energy storage system based on the system type and the application scenario; The basic structure is first decomposed according to different functions of the energy storage system, and secondly decomposed according to the physical components of the energy storage system. The parameters to be detected are determined by combining the first decomposition result and the second decomposition result, and the internal detection points corresponding to each parameter to be detected and the external detection points related to the application scenario are selected according to the application scenario, and then the detection scheme is set, and the sensors are deployed according to the detection scheme.

[0037] In this embodiment, the system type is different technologies and methods of energy storage systems, such as lithium-ion batteries: used in electric vehicles and portable electronic devices, pumped storage: used for grid peak regulation, using water level difference to store energy, compressed air energy storage: suitable for large-scale energy storage, using compressed air to store energy.

[0038] In this embodiment, the application scenario is the specific environment or purpose in which the energy storage system is used, such as grid peak shaving: releasing stored energy during peak electricity consumption hours to balance grid load, and renewable energy integration: storing solar or wind energy for use when demand is high.

[0039] In this embodiment, different functions are the main functions of the energy storage system, such as energy storage: converting electrical energy into chemical energy (such as battery charging), energy release: converting stored energy into electrical energy to supply the load (such as battery discharging), and energy conversion: converting electrical energy into other forms (such as converting electrical energy into mechanical energy).

[0040] In this embodiment, the first decomposition is the decomposition of the basic structure according to the function, for example, the energy storage subsystem: including battery cells, water reservoirs, etc., the energy conversion subsystem: including inverters, transformers, etc., the control subsystem: including battery management system (BMS), monitoring system.

[0041] In this embodiment, the second decomposition is a more detailed decomposition of the first decomposition result based on physical components, for example, the battery cell: including positive electrode, negative electrode, electrolyte, diaphragm, etc., the battery management system: including voltage detection module, temperature sensor, balancing circuit, etc., the inverter: including power circuit, control circuit, cooling system, etc.

[0042] In this embodiment, the parameters to be detected are determined based on the first decomposition and the second decomposition to determine the parameters to be detected, such as battery voltage, battery temperature, charge and discharge power, energy flow, etc.

[0043] In this embodiment, the detection point is selected by selecting the specific detection position of each parameter to be detected according to the application scenario, for example, a voltage sensor is set on the battery cell, a temperature sensor is set in the battery pack, and a power sensor is set at the input and output ends of the inverter.

[0044] In this embodiment, setting the detection plan is to formulate a detection and data collection plan based on the detection points, for example, regularly collecting battery voltage and temperature data, real-time detection of charging and discharging power, setting alarm thresholds, and regularly checking the working status of the control system.

[0045] In this embodiment, the physical components are the specific physical structures of the components in the energy storage system, for example, lithium-ion batteries: positive electrode (such as lithium cobalt oxide), negative electrode (such as graphite), electrolyte, and diaphragm.

[0046] In this embodiment, the first decomposition result is to decompose the basic structure of the energy storage system according to different functions. For example, the energy storage subsystem includes lithium-ion battery cells and pumped storage tanks, and the energy conversion subsystem includes an inverter (converting DC power into AC power) and a transformer (regulating voltage).

[0047] In this embodiment, the second decomposition result is a more detailed decomposition of the first decomposition result based on physical components. For example, the energy storage subsystem includes lithium-ion battery cells, positive electrode materials (such as lithium cobalt oxide), negative electrode materials (such as graphite), electrolytes, and diaphragms.

[0048] In this embodiment, the parameters to be detected are key parameters that need to be detected, such as battery voltage: the voltage of each battery cell, battery temperature, battery operating temperature, charge and discharge power, battery charge and discharge power, energy flow, input and output energy (such as current and voltage).

[0049] In this embodiment, the external detection point refers to a monitoring location located outside the energy storage system, which is used to collect data related to the environment, market or external conditions of the system. For example, a meteorological monitoring station monitors meteorological data such as temperature, humidity, wind speed, precipitation, etc. These data can affect the charging and discharging strategy of the energy storage system, especially in the application scenarios of renewable energy (such as solar energy and wind energy). The grid interface monitors the voltage, current, frequency and other parameters of the grid to evaluate the interaction between the energy storage system and the grid and ensure the stability and safety of the system.

[0050] In this embodiment, the internal detection point refers to a monitoring location located inside the energy storage system, which is used to collect data related to the system operating status, performance and safety, such as the battery management system: monitoring the battery's state of charge (SOC), temperature, voltage and current and other parameters to ensure that the battery operates within a safe range and optimize its service life, the inverter monitoring point: monitoring the inverter's output power, efficiency and fault status to ensure the effectiveness and stability of power conversion, the thermal management system monitoring point: monitoring the temperature of the battery and other components to prevent overheating or low temperature from affecting system performance, and the energy flow monitoring point: monitoring the flow of energy between the various parts of the energy storage system, including energy loss during charging, discharging and storage.

[0051] In this embodiment, the detection point is a specific location where the parameter to be detected is detected, for example, battery voltage: a voltage sensor is set on each battery cell, and battery temperature: a temperature sensor is set in the battery pack, usually placed on the top or side of the battery.

[0052] In this embodiment, the detection scheme is a detection and data collection scheme formulated according to the detection points, for example, battery voltage detection: regularly collect voltage data of each battery cell (such as once a minute) and record it in the database, battery temperature detection: real-time detection of battery temperature, setting threshold alarm (such as alarm when exceeding 60°C), charge and discharge power detection: real-time detection of charging and discharging power, recording power changes in each cycle, energy flow detection: regular generation of energy flow reports, and analysis of input and output energy.

[0053] The working principle and beneficial effects of the above technical solution are: by obtaining the type and application scenario of the energy storage system, determining its basic structure, decomposing the basic structure into both functional and physical components, identifying the parameters to be detected, selecting detection points according to the application scenario, formulating detection plans and deploying sensors, achieving comprehensive detection and data collection of the energy storage system, providing a basis for subsequent optimization and management, and enhancing the system's adaptability.

[0054] Embodiment 3: The embodiment of the present invention provides an energy distribution optimization and adjustment method for an energy storage system, which obtains internal system data and external environment data of the energy storage system based on the deployment result, clarifies the energy optimization target, and performs data fusion on the internal system data and the external environment data according to the energy optimization target, including: Determine the specific links that require energy prediction based on the energy optimization goal; Obtain historical load data of the supply side related to the energy storage system, draw a load line graph based on the historical load data, identify load trends and load periodic changes from the load line graph, perform seasonal analysis on the load line graph, determine load seasonal changes, and derive energy demand points based on the load trends, load periodic changes, and load seasonal changes; According to the energy demand points combined with specific links, a set of key decision points is obtained, and a comprehensive score is performed based on the key decision point set and the energy optimization target. Based on the comprehensive score, the data fusion strategy corresponding to the key decision point is determined, and the internal system data and the external environment data are fused according to the data fusion strategy.

[0055] In this embodiment, the specific links are specific steps or stages that need to be performed in the energy optimization process, such as the load forecasting stage, the energy scheduling stage, and the system monitoring and adjustment stage.

[0056] In this embodiment, the historical load data of the relevant supply side is the load usage of the relevant supply side of the energy storage system (such as the power grid, power plant, etc.) in the past period of time, for example, the power load data (hours, days, weeks, etc.) of a certain area in the past year, and the record of changes in power demand in different time periods.

[0057] In this embodiment, the load line graph is a graph that plots load data with time as the horizontal axis and load value as the vertical axis, which is used to intuitively display the load change trend. For example, a line graph of load changes in a power grid within a week shows peak and trough periods, and a line graph of seasonal load changes shows the load difference between summer and winter.

[0058] In this embodiment, the energy demand point is the energy demand at a specific time point determined based on historical load data and prediction results, such as the electricity demand forecast for a specific date and time (such as the morning peak electricity demand on a certain weekday) and the load demand under specific weather conditions (such as heating demand in cold weather).

[0059] In this embodiment, the load trend is the overall change direction and pattern of the load data over a period of time, for example, the trend of increasing electricity demand in a city year by year, and the rising trend of load in a certain period of time (such as summer).

[0060] In this embodiment, the load periodic variation is a pattern in which load data recurs within a periodic time period (such as a day, week, or month), for example, a peak load from 8 to 9 a.m. every day and an increase in power demand every Friday night.

[0061] In this embodiment, the seasonal variation of load is the variation pattern of load between different seasons, for example, the increase of power demand due to the use of air conditioning in summer and the increase of power demand due to heating demand in winter.

[0062] In this embodiment, the key decision point set is the specific moments or conditions where key decisions need to be made in the energy optimization process, such as deciding whether to charge when the electricity price is lower than a certain threshold, and deciding whether to start the backup power supply when the predicted load exceeds the historical maximum value.

[0063] In this embodiment, the data fusion strategy is a strategy for integrating and processing data from different sources to improve the availability and accuracy of data, for example, combining meteorological data and historical load data to predict future load demand.

[0064] The working principle and beneficial effects of the above technical solution are: by clarifying the energy optimization goals, identifying the links in the energy storage system that require energy prediction, obtaining historical load data and drawing load line charts, analyzing load trends and seasonal changes, determining energy demand points, combining key decision point sets with energy optimization goals for scoring, formulating data fusion strategies, and finally integrating internal system data with external environmental data to provide an accurate basis for energy management, improve the accuracy of energy demand prediction, and improve the overall stability and reliability of the power system.

[0065] Embodiment 4: The embodiment of the present invention provides an energy distribution optimization and regulation method for an energy storage system, which obtains a key decision point set according to energy demand points combined with specific links, performs comprehensive scoring according to the key decision point set and energy optimization goals, and determines a data fusion strategy corresponding to the key decision point based on the comprehensive scoring, including: According to the energy demand point combined with the specific links, a first dynamic threshold, a second dynamic threshold and a third dynamic threshold are set, a charging decision point is determined according to the first dynamic threshold, a discharging decision point is determined according to the second dynamic threshold, and an emergency decision point is determined according to the third dynamic threshold, and the charging decision point, the discharging decision point and the emergency decision point are combined to form a key decision point set; Determine external influencing factors based on external environment data corresponding to key decision points, score the key decision point set based on the external influencing factors, and obtain a comprehensive score for each key decision point; Match the data fusion strategy of the key decision point corresponding to each comprehensive score from the score-strategy table.

[0066] In this embodiment, the first dynamic threshold is a threshold used to determine the charging decision, which generally refers to the condition under which the system starts charging when the battery status or market conditions reach a certain level. For example, when the battery status power is lower than 40%, the system starts charging; or, when the electricity price is lower than a set value (such as 0.1 yuan / kWh), charging is triggered.

[0067] In this embodiment, the second dynamic threshold is a threshold used to determine the discharge decision, which refers to the condition under which the system starts discharging when the battery status or market conditions reach a certain level. For example, when the SOC of the battery is higher than 80%, the system starts discharging; or, when the electricity price is higher than a set value (such as 0.5 yuan / kWh), discharge is triggered.

[0068] In this embodiment, the third dynamic threshold is a threshold used to determine emergency decisions, which generally refers to the conditions for taking emergency measures when the system is abnormal or the battery is in poor condition. For example, when the battery temperature exceeds 75°C, emergency protection measures are triggered; or when the grid frequency deviates from the normal range (such as higher than 60.5Hz or lower than 59.5Hz), emergency discharge is initiated.

[0069] In this embodiment, the charging decision point is the moment when the system decides to start charging when the first dynamic threshold is reached, for example, when the electricity price is lower than 0.1 yuan / kWh, the system starts charging; the discharging decision point is the moment when the system decides to start discharging when the second dynamic threshold is reached, for example, when the electricity price is higher than 0.5 yuan / kWh, the system starts discharging; the emergency decision point is the moment when the system takes emergency measures when the third dynamic threshold is reached, for example, when the battery temperature exceeds 75°C, the system stops charging and starts the cooling system.

[0070] In this embodiment, the key decision point set is a set consisting of charging decision points, discharging decision points and emergency decision points, forming key decision nodes of the energy storage system. For example, the key decision point set includes charging decision points (such as electricity prices lower than 0.1 yuan / kWh), discharging decision points (such as electricity prices higher than 0.5 yuan / kWh) and emergency decision points (such as battery temperature exceeding 75°C).

[0071] In this embodiment, the score-strategy table is a table that lists the comprehensive score and corresponding strategy of each key decision point. The score is used to evaluate the influence of external factors on the decision and formulate corresponding response strategies. For example, the comprehensive score of the emergency decision point is 70, and the corresponding data fusion strategy is to start the cooling system to reduce the temperature.

[0072] The working principle and beneficial effects of the above technical solution are: by setting dynamic thresholds to determine the charging, discharging and emergency decision points, a set of key decision points is formed, and these decision points are scored in combination with external influencing factors. After obtaining a comprehensive score, the corresponding data fusion strategy is matched from the score-strategy table to achieve effective fusion of internal system data and external environment data, so as to optimize energy management, ensure the rationality and efficiency of resource allocation, and improve the scientific nature of management decisions.

[0073] Embodiment 5: The embodiment of the present invention provides an energy distribution optimization and regulation method for an energy storage system, which determines external influencing factors according to external environmental data corresponding to key decision points, scores a set of key decision points according to the external influencing factors, and obtains a comprehensive score for each key decision point, including: ,in, represents the comprehensive score between the i-th key decision point and the energy optimization target; The weight coefficient of the i-th key decision point; represents the i-th key decision point in the key decision point set; represents the weight coefficient of the i-th key decision point for the energy optimization target at time t; represents the energy optimization objective at time t; represents the weight coefficient of the jth external influencing factor; represents the jth external influencing factor; represents the interaction coefficient between the i-th key decision point and the j-th external influencing factor; represents the error term of the i-th key decision point; i and k represent the indexes of the key decision points in the key decision point set; j and l represent the indexes of the external influencing factors; n represents the total number of key decision points in the key decision set; m represents the total number of external influencing factors.

[0074] In this embodiment, external influencing factors refer to external conditions or variables that affect the operation and decision-making of the energy storage system, including: renewable energy power generation, electricity price fluctuations, grid demand, etc.

[0075] In this embodiment, the interaction is that external influencing factors (such as electricity price fluctuations, renewable energy power generation, etc.) may change the triggering conditions of a key decision point. For example, when the electricity price rises suddenly, it may cause the triggering conditions of the discharge decision point to be met in advance, thereby affecting the discharge strategy. The response of the key decision point may also in turn affect the external influencing factors. For example, when the energy storage system discharges a large amount to cope with high electricity prices, it may affect the load demand of the power grid, thereby affecting the trend of electricity prices.

[0076] The working principle and beneficial effects of the above technical solution are: by calculating the comprehensive score between each key decision point and the energy optimization target, considering the weight coefficient of the decision point, external influencing factors and their interactions, the comprehensive score reflects the contribution of the decision point to the energy optimization target at a specific time, and combining the error term to ensure the accuracy of the score, thereby providing a scientific basis for optimizing energy management, achieving efficient allocation of energy storage resources, and enhancing the flexibility of the energy storage system to cope with various energy needs.

[0077] Embodiment 6: The embodiment of the present invention provides an energy distribution optimization and adjustment method for an energy storage system, extracts the characteristics affecting distribution from the fusion data to establish a prediction model, identifies the key factors and distribution trends of each energy optimization target according to the prediction model, and determines the energy distribution strategy, including: Based on the energy optimization goal, the key features in the fusion data are identified, and the principal component analysis is performed on the key features according to the energy optimization goal. The influence distribution features that have an impact on the energy optimization goal are screened out according to the principal component analysis results; Matching the initial model from the target-model library according to the energy optimization goal, and deriving the prediction model in combination with the impact distribution characteristics; Forecast energy demand based on the output of the forecast model, analyze the forecasted energy demand, identify the distribution trend and key factors of energy demand, and determine the energy allocation strategy.

[0078] In this embodiment, key features refer to variables or attributes in the data set that have a significant impact on the energy optimization goal. These features can help identify and explain changes in energy demand. For example, when predicting electricity demand, key features may include temperature, humidity, historical electricity consumption, holiday information, etc.

[0079] In this embodiment, principal component analysis is a statistical technique used to reduce the dimensionality of high-dimensional data by identifying the main components (principal components) in the data and retaining as much variance information as possible. This helps to simplify data analysis and visualization. For example, in a data set containing multiple features (such as temperature, humidity, wind speed, etc.), PCA can be used to convert these features into several main components for subsequent analysis.

[0080] In this embodiment, the influencing allocation feature refers to the feature that has a significant impact on the energy optimization target selected by principal component analysis. These features are used for prediction in the model. For example, if PCA finds that temperature and electricity consumption history are the main components that affect electricity demand, then these two features are the influencing allocation features.

[0081] In this embodiment, the target-model library is a collection of multiple models, which are optimized for different energy optimization goals. According to the specific energy demand target, a suitable model is selected from the library for analysis. For example, a target-model library may contain prediction models optimized for different power demand scenarios (such as peak period, off-peak period, holidays, etc.).

[0082] In this embodiment, the input of the initial model is usually the characteristics that affect allocation, and the output is the prediction result of the energy optimization target. For example, the input can be air temperature, humidity and historical electricity consumption, and the output is the predicted value of electricity demand for a certain period of time in the future.

[0083] In this embodiment, the predicted energy demand refers to an estimate of the energy demand in a certain future time period output by the model. For example, the result obtained by the prediction model shows that the electricity demand in the next week is 1000 MWh.

[0084] The working principle and beneficial effects of the above technical solution are: by extracting the features that affect distribution from the fused data, using principal component analysis to identify the key features related to the energy optimization goal, based on these features, matching the initial model and building a prediction model, outputting the predicted energy demand, and by analyzing the prediction results, identifying the distribution trend and key factors of energy demand, so as to formulate corresponding energy distribution strategies, achieve optimization management, and enhance the stability and reliability of the power system.

[0085] Embodiment 7: The embodiment of the present invention provides an energy distribution optimization and regulation method for an energy storage system, which outputs a predicted energy demand according to a prediction model, analyzes the predicted energy demand, identifies the distribution trend and key factors of the energy demand, and determines an energy distribution strategy, including: For a set of key decision points, scenario analysis is performed to evaluate the predicted energy demand under different scenarios and the impact of changes in predicted energy demand on the allocation of energy demand; The distribution trend and key factors of energy demand are determined based on the evaluation results, and then the energy allocation strategy for each key decision point is determined in combination with the key decision point set.

[0086] In this embodiment, scenario analysis is a decision support tool that simulates different hypothetical scenarios to assess their potential impact on the system or decision. This approach can help identify risks and opportunities and provide a basis for key decision points. For example, in power demand forecasting, the corresponding scenarios include: high demand scenario: assuming that the temperature is abnormally high in the next few days, resulting in increased use of air conditioners, low demand scenario: assuming normal temperatures and large-scale renewable energy generation, medium demand scenario: moderate temperatures and power demand remains at historical average levels.

[0087] In this embodiment, the evaluation process refers to analyzing the changes in predicted energy demand under different scenarios to understand the impact of these changes on energy distribution, collecting historical data and related variables (such as temperature, electricity consumption patterns, etc.), using the prediction model to run under different scenarios, deriving predicted energy demand, analyzing the prediction results under different scenarios, identifying patterns of demand changes, evaluating the impact of these changes on energy distribution, and identifying potential risks and opportunities. For example, in a high demand scenario, the prediction model may show a 20% increase in electricity demand in the next few days. The evaluation results may indicate that in this case, the power supply may be insufficient, and it is recommended to increase the discharge capacity of the energy storage system.

[0088] In this embodiment, the predicted energy demand change refers to the change in energy demand output by the prediction model under different scenarios. This change can be an absolute value (such as an increase or decrease in kilowatt-hours of demand) or a relative value (such as a percentage change). For example, in a high demand scenario, the prediction model may show that the demand increases from 1000 MWh to 1200 MWh, a change of 20%. In a low demand scenario, the demand may decrease to 800 MWh, a change of -20%.

[0089] The working principle and beneficial effects of the above technical solution are: by conducting scenario analysis on the energy demand output by the prediction model, evaluating the predicted energy demand under different situations and the impact of its changes on energy allocation, identifying the distribution trend and key factors of energy demand based on the evaluation results, and combining the key decision point set to formulate an energy allocation strategy for each key decision point, thereby realizing dynamic optimization management, dynamically adjusting the energy allocation strategy, and achieving more efficient energy management.

[0090] Embodiment 8: An embodiment of the present invention provides an energy distribution optimization and adjustment method for an energy storage system, which optimizes the energy storage system configuration according to the energy distribution strategy and feeds back the configuration result to a prediction model, including: Determine the response requirements of the energy storage system in different time periods according to the energy allocation strategy, evaluate the system configuration of the current energy storage system, and determine whether the existing configuration meets the energy allocation strategy; Optimizing the energy allocation strategy according to the satisfaction, and formulating an adjustment plan for the energy storage system configuration based on the optimization result; Compare the configuration results with the output of the prediction model and make feedback adjustments to the prediction model.

[0091] In this embodiment, the corresponding requirements refer to the energy output and response speed that the energy storage system needs to meet within a specific time period. These requirements are usually based on energy allocation strategies and power demand forecast results. For example, during peak power consumption periods, the energy storage system may need to provide 500 kWh of electricity within 30 minutes to cope with sudden increases in demand.

[0092] In this embodiment, the satisfaction refers to whether the performance of the current energy storage system can meet the predetermined energy allocation strategy and corresponding requirements. Evaluating the satisfaction can help identify the deficiencies of the system. For example, if the response requirement of the energy storage system is an output of 500 kWh, and the current system can only provide 400 kWh, the satisfaction is "not met".

[0093] In this embodiment, the optimization result refers to the improvement effect of the system configuration and energy allocation strategy of the energy storage system after the optimization process. For example, after optimization, the energy output capacity of the energy storage system is increased to 600 kWh, the response time is shortened to 3 minutes, and the energy efficiency is increased to 92%.

[0094] In this embodiment, the adjustment plan refers to specific measures and steps formulated based on the optimization results to improve the configuration and performance of the energy storage system. For example, the adjustment plan may include increasing the number of energy storage units, upgrading the control system software, optimizing the charging and discharging scheduling strategy, etc.

[0095] In this embodiment, the comparison process is to compare the optimized energy storage system configuration results with the output of the prediction model to verify the optimization effect and prediction accuracy, collect the optimized energy storage system performance data and the prediction model output, analyze the differences between the two, and evaluate the optimization effect. For example, by comparing the actual output of the optimized energy storage system during peak hours (600 kWh) with the prediction model output (500 kWh), it is found that the actual output is higher.

[0096] The working principle and beneficial effects of the above technical solution are: by determining the response requirements of the energy storage system in different time periods according to the energy allocation strategy, evaluating the system configuration of the current energy storage system, judging its satisfaction, optimizing the energy allocation strategy based on this situation, and formulating an energy storage system configuration adjustment plan, comparing the adjustment results with the output of the prediction model, and adjusting the prediction model through feedback to achieve continuous optimization.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing energy distribution in an energy storage system, characterized in that: include: Step 1: Obtain the basic structure of the energy storage system, decompose the basic structure, and deploy sensors based on the decomposition results; Step 2: Based on the deployment results, the internal system data and external environment data of the energy storage system are obtained, the energy optimization target is clarified, and the internal system data and the external environment data are integrated according to the energy optimization target; Step 3: Extract the features that affect allocation from the fused data to establish a prediction model, identify the key factors and allocation trends of each energy optimization target based on the prediction model, and determine the energy allocation strategy; Step 4: Optimize the energy storage system configuration according to the energy allocation strategy, and feed the configuration results back to the prediction model.

2. The energy distribution optimization and adjustment method for an energy storage system according to claim 1, characterized in that: Obtain the basic structure of the energy storage system, decompose the basic structure, and deploy sensors based on the decomposition results, including: Acquire a system type and an application scenario of the energy storage system, and determine a basic structure of the energy storage system based on the system type and the application scenario; The basic structure is first decomposed according to different functions of the energy storage system, and secondly decomposed according to the physical components of the energy storage system. The parameters to be detected are determined by combining the first decomposition result and the second decomposition result, and the internal detection points corresponding to each parameter to be detected and the external detection points related to the application scenario are selected according to the application scenario, and then the detection scheme is set, and the sensors are deployed according to the detection scheme.

3. The energy distribution optimization and adjustment method for an energy storage system according to claim 1, characterized in that: Based on the deployment results, the internal system data and external environment data of the energy storage system are obtained, the energy optimization target is clarified, and the internal system data and the external environment data are integrated according to the energy optimization target, including: Determine the specific links that require energy prediction based on the energy optimization goal; Obtain historical load data of the supply side related to the energy storage system, draw a load line graph based on the historical load data, identify load trends and load periodic changes from the load line graph, perform seasonal analysis on the load line graph, determine load seasonal changes, and derive energy demand points based on the load trends, load periodic changes, and load seasonal changes; According to the energy demand points combined with specific links, a set of key decision points is obtained, and a comprehensive score is performed based on the key decision point set and the energy optimization target. Based on the comprehensive score, the data fusion strategy corresponding to the key decision point is determined, and the internal system data and the external environment data are fused according to the data fusion strategy.

4. The energy distribution optimization and adjustment method for an energy storage system according to claim 3, characterized in that: According to the energy demand points combined with specific links, a set of key decision points is obtained, and a comprehensive score is performed according to the key decision point set and the energy optimization target. Based on the comprehensive score, a data fusion strategy corresponding to the key decision point is determined, including: According to the energy demand point combined with the specific links, a first dynamic threshold, a second dynamic threshold and a third dynamic threshold are set, a charging decision point is determined according to the first dynamic threshold, a discharging decision point is determined according to the second dynamic threshold, and an emergency decision point is determined according to the third dynamic threshold, and the charging decision point, the discharging decision point and the emergency decision point are combined to form a key decision point set; Determine external influencing factors based on external environment data corresponding to key decision points, score the key decision point set based on the external influencing factors, and obtain a comprehensive score for each key decision point; Match the data fusion strategy of the key decision point corresponding to each comprehensive score from the score-strategy table.

5. The energy distribution optimization and regulation method for an energy storage system according to claim 4, characterized in that: Determine external influencing factors based on external environmental data corresponding to key decision points, score the key decision point set based on the external influencing factors, and obtain a comprehensive score for each key decision point, including: ,in, represents the comprehensive score between the i-th key decision point and the energy optimization target; The weight coefficient of the i-th key decision point; represents the i-th key decision point in the key decision point set; represents the weight coefficient of the i-th key decision point for the energy optimization target at time t; represents the energy optimization objective at time t; represents the weight coefficient of the jth external influencing factor; represents the jth external influencing factor; represents the interaction coefficient between the i-th key decision point and the j-th external influencing factor; represents the error term of the i-th key decision point; i and k represent the indexes of the key decision points in the key decision point set; j and l represent the indexes of the external influencing factors; n represents the total number of key decision points in the key decision set; m represents the total number of external influencing factors.

6. The energy distribution optimization and regulation method for an energy storage system according to claim 1, characterized in that: Extract the features that affect allocation from the fused data to establish a prediction model. According to the prediction model, identify the key factors and allocation trends of each energy optimization target and determine the energy allocation strategy, including: Based on the energy optimization goal, the key features in the fusion data are identified, and the principal component analysis is performed on the key features according to the energy optimization goal. The influence distribution features that have an impact on the energy optimization goal are screened out according to the principal component analysis results; Matching the initial model from the target-model library according to the energy optimization goal, and deriving the prediction model in combination with the impact distribution characteristics; Forecast energy demand based on the output of the forecast model, analyze the forecasted energy demand, identify the distribution trend and key factors of energy demand, and determine the energy allocation strategy.

7. The energy distribution optimization and regulation method for an energy storage system according to claim 3, characterized in that: Forecast energy demand based on the output of the forecast model, analyze the forecasted energy demand, identify the distribution trend and key factors of energy demand, and determine the energy allocation strategy, including: For a set of key decision points, scenario analysis is performed to evaluate the predicted energy demand under different scenarios and the impact of changes in predicted energy demand on the allocation of energy demand; The distribution trend and key factors of energy demand are determined based on the evaluation results, and then the energy allocation strategy for each key decision point is determined in combination with the key decision point set.

8. The energy distribution optimization and regulation method for an energy storage system according to claim 1, characterized in that: The energy storage system configuration is optimized according to the energy allocation strategy, and the configuration results are fed back to the prediction model, including: Determine the response requirements of the energy storage system in different time periods according to the energy allocation strategy, evaluate the system configuration of the current energy storage system, and determine whether the existing configuration meets the energy allocation strategy; Optimizing the energy allocation strategy according to the satisfaction, and formulating an adjustment plan for the energy storage system configuration based on the optimization result; Compare the configuration results with the output of the prediction model and make feedback adjustments to the prediction model.

Images