A distributed new energy storage optimization configuration method and system for distribution network

Abstract

A distributed renewable energy storage optimization configuration method and system for a distribution network, comprising the following steps: constructing a load forecasting model using a probability discretization method based on historical electricity consumption data and real-time weather data; constructing a multi-objective optimization model based on load demand data output by the load forecasting model, with maximizing the utilization rate of distributed renewable energy power generation, minimizing the energy loss of distributed renewable energy storage, and minimizing the operating cost of energy storage and scheduling as optimization goals; adjusting the weight distribution of three optimization goals based on the multi-objective optimization model, gradually optimizing the power distribution between renewable energy power generation and energy storage, and generating an optimal renewable energy complementary strategy; adjusting charging and discharging based on the optimal renewable energy complementary strategy, collecting the health status of energy storage equipment, battery temperature, number of charge and discharge cycles, ambient temperature, and load demand changes in real time, and optimizing renewable energy power generation and energy storage configuration by dynamically comparing multiple indicators under different energy storage configurations in combination with power grid frequency fluctuations.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage optimization configuration, and more specifically, relates to a distributed new energy storage optimization configuration method and system for a distribution network. Background Art

[0002] In the current context of global energy shortage and increasingly prominent environmental problems, the development and utilization of renewable energy has become an important way for countries to promote energy transformation and achieve sustainable development. Distributed new energy systems, such as solar energy and wind energy, have been widely used due to their clean, renewable, and widely distributed advantages. However, due to the intermittent and volatile nature of solar and wind power generation, how to efficiently utilize these new energy sources and ensure the stable operation of the power system has become an urgent problem to be solved.

[0003] Traditional power systems usually rely on centralized power generation and dispatching methods, and lack effective management methods for the access and dispatch of distributed renewable energy. This leads to challenges to the stability and reliability of the power grid when a high proportion of renewable energy is connected. To address this problem, energy storage technology has been proposed as an important solution. Energy storage devices can store energy when there is excess power generation and release energy when there is insufficient power generation, thereby balancing the difference between power generation and load.

[0004] However, most existing energy storage systems and scheduling methods rely on fixed strategies or simple empirical rules, which cannot fully utilize real-time data and complex system dynamics, resulting in low utilization of energy storage equipment and the need to improve the overall efficiency of the system. For example, energy is stored when there is excess solar power generation, and discharged when load demand is higher than power generation. This type of method lacks flexibility and cannot make optimization judgments based on real-time data, making it difficult to generate scientific and accurate dynamic adjustment strategies, resulting in low overall system efficiency, which needs to be improved. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] Therefore, in order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A first aspect of the present invention provides a distributed renewable energy storage optimization configuration method for a distribution network, comprising the following steps:

[0008] Based on historical electricity consumption data and real-time weather data, a load forecasting model is constructed using the probability discretization method;

[0009] According to the load demand data output by the load forecasting model, a multi-objective optimization model is constructed with the optimization goals of maximizing the utilization rate of distributed renewable energy power generation, minimizing the energy loss of distributed renewable energy storage, and minimizing the operating costs of energy storage and scheduling;

[0010] According to the multi-objective optimization model, the weight distribution of the three optimization objectives is adjusted, the power distribution between renewable energy generation and energy storage is gradually optimized, and the optimal renewable energy complementary strategy is generated;

[0011] Adjust charging and discharging according to the optimal new energy complementary strategy, collect the health status of energy storage equipment, battery temperature, number of charge and discharge cycles, ambient temperature and load demand changes in real time, and optimize the configuration of new energy power generation and energy storage by dynamically comparing multiple indicators such as charging and discharging efficiency, response time, and degree of aging of energy storage equipment under different energy storage configurations in combination with grid frequency fluctuations.

[0012] Preferably, a load forecasting model is constructed as follows:

[0013] The sensors collect historical electricity consumption data, real-time weather data and external factor data, and transmit them to the central control center as inputs to the prediction model; the weather data includes temperature, humidity and wind speed; the external factors include holidays and electricity price fluctuations;

[0014] The load forecasting model is as follows:

[0015] ,

[0016] Where:

[0017] represents the load demand at time t;

[0018] Indicates based on temperature ,humidity and wind speed Forecasting load demand;

[0019] Indicates that given a random variable Under the condition of Expected value;

[0020] Indicates weather conditions;

[0021] Statistical analysis is performed on historical electricity consumption data and real-time weather data to construct the uncertainty distribution of variables. Weather conditions are set as normal distributions, and the corresponding probability distribution model of electricity load demand is constructed based on the historical fluctuation range to capture uncertainty characteristics.

[0022] Based on the captured uncertainty characteristics, discretization processing is performed. According to the fluctuation range of the uncertainty variables, the continuous variables of weather conditions and power load demand are divided into finite discrete intervals, and each discrete interval is assigned a corresponding occurrence probability;

[0023] The discretized weather conditions and electricity load demand states are introduced into the load forecasting model to analyze and predict future supply and demand changes.

[0024] Preferably, the discretization process is as follows:

[0025] Perform statistical analysis on historical electricity consumption data and real-time weather data, construct uncertainty distribution of variables, and set weather conditions Normal distribution ;in, Indicates weather conditions The mean of Indicates weather conditions Relative to the mean fluctuations;

[0026] The continuous probability distribution of weather conditions and power load demand is processed into discretized weather condition states , where k represents the number of discrete states, and each state corresponds to a probability , the discretized set is expressed as follows:

[0027] ,

[0028] Where:

[0029] Represents the set of all state values ​​after discretization.

[0030] Preferably, a multi-objective optimization model is constructed, specifically as follows:

[0031] The first goal is to maximize the utilization rate of distributed renewable energy generation. The formula is as follows:

[0032] ,

[0033] Where:

[0034] , They represent the solar power generation and wind power generation at time t respectively;

[0035] are the priority weight coefficients of solar energy and wind energy power generation, respectively, used to indicate the priority of solar energy and wind energy power generation;

[0036] The second goal is to minimize the energy loss of distributed renewable energy storage. The formula is as follows:

[0037] ,

[0038] Where:

[0039] represents the load demand at time t;

[0040] is a coefficient used to balance the deviation between load demand and power generation;

[0041] The third goal is to minimize the operating cost of energy storage and dispatch. The formula is as follows:

[0042] ,

[0043] Where:

[0044] represents a cost indicator;

[0045] Indicates at time The weight coefficient of the moment.

[0046] Preferably, the three optimization objectives of maximizing the utilization rate of distributed renewable energy generation, minimizing the energy loss of distributed renewable energy storage, and minimizing the operating costs of energy storage and scheduling are optimized through weight coefficients. Combined into a single goal, as follows:

[0047] ,

[0048] Where:

[0049] represents the comprehensive objective function; is the weight of each goal; Indicates An optimization goal.

[0050] Preferably, the power distribution between renewable energy generation and energy storage is gradually optimized to generate the optimal renewable energy complementary strategy, as follows:

[0051] The comprehensive objective function is expressed as follows: Gradually optimize the power distribution between renewable energy generation and energy storage:

[0052] ,

[0053] Where:

[0054] and are the influence coefficients of solar energy and wind power generation on the comprehensive utilization rate at time t; Represents the weight coefficient of each optimization objective function; represents the penalty coefficient for mismatch with load demand at time t;

[0055] represents the solar power generation power at time t; represents the wind power generation at time t; represents the load demand at time t; represents the maximum load demand at time t;

[0056] represents the adjustment coefficient related to the energy storage efficiency at time t; represents the energy storage at time t; represents the maximum energy storage at time t;

[0057] The state of the energy storage equipment during the optimization process must meet the following constraints:

[0058] The health state of the energy storage device at time t does not exceed its maximum allowable health state:

[0059] ,

[0060] Where:

[0061] Indicates the health status of the energy storage device at time t; Indicates the maximum allowable health state of the energy storage device at time t;

[0062] The battery temperature does not exceed its maximum allowable temperature at time t:

[0063] ,

[0064] Where:

[0065] represents the battery temperature at time t; Represents the maximum allowable temperature at time t.

[0066] Preferably, the optimal new energy complementary strategy is calculated as follows:

[0067] ,

[0068] Where:

[0069] Represents the charging and discharging decisions of power generation and energy storage equipment at all times t.

[0070] Adjust charging and discharging according to the optimal new energy complementary strategy, collect the health status of energy storage equipment, battery temperature, number of charge and discharge cycles, ambient temperature and load demand changes in real time, combined with grid frequency fluctuations, as follows:

[0071] When the amount of electricity generated by renewable energy exceeds the electricity load demand, the energy storage device is charged first according to the following formula:

[0072] ,

[0073] Where:

[0074] Indicates the maximum charging capacity of the energy storage device at time t; represents the charging efficiency at time t;

[0075] When the electricity load demand exceeds the power generation, the energy storage device is discharged as follows:

[0076] ,

[0077] Where:

[0078] Indicates the maximum discharge capacity of the energy storage device at time t; Represents the discharge efficiency at time t.

[0079] Preferably, the configuration of new energy generation and energy storage is optimized by dynamically comparing multiple indicators such as charging and discharging efficiency, response time, and aging degree of energy storage equipment under different energy storage configurations. The formula is as follows:

[0080] ,

[0081] Where:

[0082] represents the solar power generation power at time t; represents the wind power generation at time t; represents the load demand at time t;

[0083] Indicates the state of the energy storage device at time t; represents the response time at time t; Indicates the health status ratio of the energy storage device;

[0084] Indicates the initial time;

[0085] Respectively represent the priority weight coefficients of solar energy and wind power generation;

[0086] Represents the time decay factor.

[0087] A second aspect of the present invention provides a distributed new energy storage optimization configuration system for a distribution network, comprising: a load prediction module, a multi-objective optimization model module, a dynamic configuration optimization module, and a real-time adjustment and optimization module;

[0088] The load forecasting module is used to collect and process historical power consumption data, real-time weather data and external factors, and use the probability discretization method to build an accurate load forecasting model to provide forecast data for future load demand;

[0089] The multi-objective optimization model module is used to maximize the utilization of renewable energy generation, minimize energy storage energy loss, and minimize operating costs;

[0090] The dynamic configuration optimization module is used to iteratively adjust the power generation and energy storage configuration parameters, generate the optimal new energy complementary strategy, and optimize the configuration.

[0091] The real-time adjustment and optimization module is used to monitor and feedback data in real time, automatically adjust the charging and discharging strategies, and optimize the configuration of new energy power generation and energy storage based on actual operating effects and simulation results.

[0092] Compared with the prior art, the beneficial effects of the present invention include at least:

[0093] (1) The present invention constructs a load forecasting model, utilizes historical electricity consumption data, real-time weather data and external factors, and adopts a probabilistic discretization method to process the uncertainty of electricity load and weather conditions, thereby more accurately predicting future load demand and power generation conditions, and avoiding the situation of excess or insufficient power generation;

[0094] (2) The present invention achieves a balance between energy storage equipment during power generation and peak power consumption by adjusting the charging and discharging strategy, optimizes the energy storage and use process, and reduces energy loss caused by unreasonable charging and discharging;

[0095] (3) The present invention introduces a dynamic weighting mechanism in the optimization process, which can flexibly adjust the weight distribution among the three optimization objectives according to real-time monitoring and feedback data. It can not only ensure the optimal scheduling strategy in different scenarios, but also continuously adjust the charging and discharging strategy during operation, thereby reducing the comprehensive operating cost of energy storage and scheduling, and avoiding the waste of resources caused by fixed strategies;

[0096] (4) The present invention automatically adjusts the charging and discharging strategy and combines simulation technology to monitor and evaluate different energy storage configuration schemes in real time, so that the new energy power generation and energy storage configuration can be automatically optimized according to external changes. The automated dynamic optimization process reduces manual intervention and improves the overall operating efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 It is a workflow diagram provided according to an embodiment of the present invention;

[0098] Figure 2 It is a system architecture diagram provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0099] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0100] like Figure 1 As shown, Example 1 of the present invention provides a distributed new energy storage optimization configuration method for a distribution network, comprising the following steps:

[0101] Based on historical electricity consumption data, real-time weather data and external factors, a load forecasting model is constructed using the probability discretization method;

[0102] Preferably, a load forecasting model is constructed as follows:

[0103] The sensors collect historical electricity consumption data, real-time weather data, and external factor data, and transmit them to the central control center as inputs to the prediction model; weather data includes temperature, humidity, and wind speed; external factors include holidays and electricity price fluctuations;

[0104] The load forecasting model is as follows:

[0105] ,

[0106] Where:

[0107] represents the load demand at time t;

[0108] Indicates based on temperature ,humidity and wind speed Forecasting load demand;

[0109] Indicates that given a random variable Under the condition of Expected value;

[0110] Indicates weather conditions;

[0111] Statistical analysis is performed on historical electricity consumption data and real-time weather data to construct the uncertainty distribution of variables. Weather conditions are set as normal distributions, and the corresponding probability distribution model of electricity load demand is constructed based on the historical fluctuation range to capture uncertainty characteristics.

[0112] Based on the captured uncertainty characteristics, discretization processing is performed. According to the fluctuation range of the uncertainty variables, the continuous variables of weather conditions and power load demand are divided into finite discrete intervals, and each discrete interval is assigned a corresponding occurrence probability;

[0113] Preferably, the discretization process is as follows:

[0114] Perform statistical analysis on historical electricity consumption data and real-time weather data, construct uncertainty distribution of variables, and set weather conditions Normal distribution ;in, Indicates weather conditions The mean of Indicates weather conditions Relative to the mean fluctuations;

[0115] The continuous probability distribution of weather conditions and power load demand is processed into discretized weather condition states , where k represents the number of discrete states, and each state corresponds to a probability , the discretized set is expressed as follows:

[0116] ,

[0117] Where:

[0118] Represents the set of all state values ​​after discretization.

[0119] The discretized weather conditions and electricity load demand states are introduced into the load forecasting model to analyze and predict future supply and demand changes.

[0120] According to the load demand data output by the load forecasting model, a multi-objective optimization model is constructed with the optimization goals of maximizing the utilization rate of distributed renewable energy power generation, minimizing the energy loss of distributed renewable energy storage, and minimizing the operating costs of energy storage and scheduling;

[0121] Preferably, a multi-objective optimization model is constructed, specifically as follows:

[0122] The first goal is to maximize the utilization rate of distributed renewable energy generation. The formula is as follows:

[0123] ,

[0124] Where:

[0125] , They represent the solar power generation and wind power generation at time t respectively;

[0126] are the priority weight coefficients of solar energy and wind energy power generation, respectively, used to indicate the priority of solar energy and wind energy power generation;

[0127] The second goal is to minimize the energy loss of distributed renewable energy storage. The formula is as follows:

[0128] ,

[0129] Where:

[0130] represents the load demand at time t;

[0131] is a coefficient used to balance the deviation between load demand and power generation;

[0132] The third goal is to minimize the operating cost of energy storage and dispatch. The formula is as follows:

[0133] ,

[0134] Where:

[0135] represents a cost indicator;

[0136] Indicates at time The weight coefficient of the moment.

[0137] Preferably, the three optimization objectives of maximizing the utilization rate of distributed renewable energy generation, minimizing the energy loss of distributed renewable energy storage, and minimizing the operating costs of energy storage and scheduling are optimized through weight coefficients. Combined into a single goal, as follows:

[0138] ,

[0139] Where:

[0140] represents the comprehensive objective function; is the weight of each goal; Indicates An optimization goal.

[0141] According to the multi-objective optimization model, the weight distribution of the three optimization objectives is adjusted, the dynamic configuration of renewable energy power generation and energy storage is iteratively optimized, and the optimal renewable energy complementary strategy is generated;

[0142] Preferably, the dynamic configuration of renewable energy generation and energy storage is iteratively optimized to generate the optimal renewable energy complementary strategy, as follows:

[0143] The comprehensive objective function is expressed as follows: Iterative optimization by dynamically adjusting weight coefficients:

[0144] ,

[0145] Where:

[0146] and are the influence coefficients of solar energy and wind power generation on the comprehensive utilization rate at time t; Represents the weight coefficient of each optimization objective function; represents the penalty coefficient for mismatch with load demand at time t;

[0147] represents the solar power generation power at time t; represents the wind power generation at time t; represents the load demand at time t; represents the maximum load demand at time t;

[0148] represents the adjustment coefficient related to the energy storage efficiency at time t; represents the energy storage at time t; represents the maximum energy storage at time t.

[0149] Preferably, the optimal new energy complementary strategy is calculated as follows:

[0150] ,

[0151] Where:

[0152] Represents the charging and discharging decisions of power generation and energy storage equipment at all times t.

[0153] According to the optimal new energy complementary strategy, the charging and discharging strategy is automatically adjusted according to the feedback data, and the new energy generation and energy storage configuration is optimized through real-time monitoring and simulation of the effects of different energy storage configurations.

[0154] Preferably, according to the optimal new energy complementary strategy, the charging and discharging strategy is automatically adjusted according to the feedback data, as follows:

[0155] When the amount of electricity generated by renewable energy exceeds the electricity load demand, the energy storage device is charged first according to the following formula:

[0156] ,

[0157] Where:

[0158] Indicates the maximum charging capacity of the energy storage device at time t;

[0159] When the electricity load demand exceeds the power generation, the energy storage device is discharged as follows:

[0160] ,

[0161] Where:

[0162] Represents the maximum discharge capacity of the energy storage device at time t.

[0163] Preferably, the configuration of renewable energy generation and energy storage is optimized by real-time monitoring and simulation of the effects of different energy storage configurations. The formula is as follows:

[0164] ,

[0165] Where:

[0166] represents the solar power generation power at time t; represents the wind power generation at time t; represents the load demand at time t;

[0167] Indicates the state of the energy storage device at time t;

[0168] Indicates the initial time;

[0169] Respectively represent the priority weight coefficients of solar energy and wind power generation;

[0170] Represents the time decay factor, weighting recent data to make it more real-time.

[0171] Integral part: accumulate the overall power generation utilization by integrating the entire time interval (0, T);

[0172] The value range of the objective function represents the comprehensive power generation utilization rate of the system within a given time interval. The larger the value, the higher the power generation utilization rate and the better the complementary effect of new energy. The lower the optimization value, the lower the utilization rate and the need to adjust the power generation and energy storage strategies.

[0173] In the calculation process of this formula, the comprehensive power generation utilization rate of the system in a given time interval is determined by the calculation results. By comparing the optimization values ​​of different time periods, the power generation utilization rate and energy storage efficiency of the system in different time periods can be understood, so as to make corresponding adjustment strategies and optimize the performance of the overall system.

[0174] Example 2 of the present invention provides a distributed new energy storage optimization configuration system for a distribution network, including: a load prediction module, a multi-objective optimization model module, a dynamic configuration optimization module, and a real-time adjustment and optimization module;

[0175] The load forecasting module is used to collect and process historical power consumption data, real-time weather data and external factors, and use the probability discretization method to build an accurate load forecasting model to provide forecast data for future load demand;

[0176] The multi-objective optimization model module is used to maximize the utilization of renewable energy generation, minimize energy storage energy loss, and minimize operating costs;

[0177] The dynamic configuration optimization module is used to iteratively adjust the power generation and energy storage configuration parameters, generate the optimal new energy complementary strategy, and optimize the configuration.

[0178] The real-time adjustment and optimization module is used to monitor and feedback data in real time, automatically adjust the charging and discharging strategies, and optimize the configuration of new energy power generation and energy storage based on actual operating effects and simulation results.

[0179] like Figure 2 As shown, as a preferred solution of the distributed renewable energy storage optimization configuration method for distribution network described in the present invention, it monitors the working conditions of power generation equipment, energy storage equipment and user power equipment in real time, collects system operation data, analyzes system performance, and dynamically adjusts the strategy according to the analysis results to adapt to changes in the environment and load, monitor the status of energy storage equipment, avoid overcharging and over-discharging, and ensure stable operation of the system.

[0180] As a preferred solution of the distributed new energy energy storage optimization configuration method for distribution network described in the present invention, the system architecture adopted by the method includes distributed new energy system, distributed energy storage equipment, smart sensors, Internet of Things equipment, energy management system based on artificial intelligence, and data analysis platform; wherein, the distributed new energy system includes solar panels, wind turbines and corresponding inverters; distributed energy storage equipment, such as lithium battery packs, supercapacitors, etc.; through smart sensors and Internet of Things devices, real-time monitoring of new energy systems and energy storage equipment is achieved; the energy management system includes a data acquisition module, a load forecasting module, and an optimization scheduling module; the data analysis platform is used to store and process historical electricity consumption data, real-time data and forecast data.

[0181] Compared with the prior art, the beneficial effects of the present invention include at least:

[0182] (1) The present invention constructs a load forecasting model, utilizes historical electricity consumption data, real-time weather data and external factors, and adopts a probabilistic discretization method to process the uncertainty of electricity load and weather conditions, thereby more accurately predicting future load demand and power generation conditions, and avoiding the situation of excess or insufficient power generation;

[0183] (2) The present invention achieves a balance between energy storage equipment during power generation and peak power consumption by adjusting the charging and discharging strategy, optimizes the energy storage and use process, and reduces energy loss caused by unreasonable charging and discharging;

[0184] (3) The present invention introduces a dynamic weighting mechanism in the optimization process, which can flexibly adjust the weight distribution among the three optimization objectives according to real-time monitoring and feedback data. It can not only ensure the optimal scheduling strategy in different scenarios, but also continuously adjust the charging and discharging strategy during operation, thereby reducing the comprehensive operating cost of energy storage and scheduling, and avoiding the waste of resources caused by fixed strategies;

[0185] (4) The present invention automatically adjusts the charging and discharging strategy and combines simulation technology to monitor and evaluate different energy storage configuration schemes in real time, so that the new energy power generation and energy storage configuration can be automatically optimized according to external changes. The automated dynamic optimization process reduces manual intervention and improves the overall operating efficiency of the system.

[0186] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0187] 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A distributed renewable energy storage optimization configuration method for a distribution network, characterized in that: The following steps are involved: Based on historical electricity consumption data and real-time weather data, a load forecasting model is constructed using the probability discretization method; According to the load demand data output by the load forecasting model, a multi-objective optimization model is constructed with the optimization goals of maximizing the utilization rate of distributed renewable energy power generation, minimizing the energy loss of distributed renewable energy storage, and minimizing the operating costs of energy storage and scheduling; Construct a multi-objective optimization model as follows: The first goal is to maximize the utilization rate of distributed renewable energy generation. The formula is as follows: Where: , They represent the solar power generation and wind power generation at time t respectively; are the priority weight coefficients of solar energy and wind energy power generation, respectively, used to indicate the priority of solar energy and wind energy power generation; The second goal is to minimize the energy loss of distributed renewable energy storage. The formula is as follows: Where: represents the load demand at time t; is a coefficient used to balance the deviation between load demand and power generation; The third goal is to minimize the operating cost of energy storage and dispatch. The formula is as follows: Where: represents a cost indicator; Indicates at time The weight coefficient of the moment; The three optimization goals of maximizing the utilization rate of distributed renewable energy generation, minimizing the energy loss of distributed renewable energy storage, and minimizing the operating costs of energy storage and scheduling are calculated through weight coefficients. Combined into a single goal, as follows: Where: represents the comprehensive objective function; is the weight of each goal; Indicates Optimization goal; According to the multi-objective optimization model, the weight distribution of the three optimization objectives is adjusted, the power distribution between renewable energy generation and energy storage is gradually optimized, and the optimal renewable energy complementary strategy is generated; Gradually optimize the power distribution between renewable energy generation and energy storage to generate the optimal renewable energy complementary strategy, as follows: The comprehensive objective function is expressed as follows: Gradually optimize the power distribution between renewable energy generation and energy storage: Where: and are the influence coefficients of solar energy and wind power generation on the comprehensive utilization rate at time t; Represents the weight coefficient of each optimization objective function; represents the penalty coefficient for mismatch with load demand at time t; represents the solar power generation power at time t; represents the wind power generation at time t; represents the load demand at time t; represents the maximum load demand at time t; represents the adjustment coefficient related to the energy storage efficiency at time t; represents the energy storage at time t; represents the maximum energy storage at time t; The state of the energy storage equipment during the optimization process must meet the following constraints: The health state of the energy storage device at time t does not exceed its maximum allowable health state: Where: Indicates the health status of the energy storage device at time t; Indicates the maximum allowable health state of the energy storage device at time t; The battery temperature does not exceed its maximum allowable temperature at time t: Where: represents the battery temperature at time t; represents the maximum allowable temperature at time t; Adjust charging and discharging according to the optimal renewable energy complementary strategy, collect the health status of energy storage equipment, battery temperature, number of charge and discharge cycles, ambient temperature and load demand changes in real time, combined with grid frequency fluctuations, including: When renewable energy power generation exceeds power load demand, give priority to charging energy storage equipment; When power load demand exceeds power generation, give priority to discharging energy storage equipment; Adjust charging and discharging according to the optimal new energy complementary strategy, collect the health status of energy storage equipment, battery temperature, number of charge and discharge cycles, ambient temperature and load demand changes in real time, combined with grid frequency fluctuations, as follows: When the amount of electricity generated by renewable energy exceeds the electricity load demand, the energy storage device is charged first according to the following formula: Where: represents the maximum charging capacity of the energy storage device at time t; represents the charging efficiency at time t; When the electricity load demand exceeds the power generation, the energy storage device is discharged as follows: Where: Indicates the maximum discharge capacity of the energy storage device at time t; represents the discharge efficiency at time t; Optimize the configuration of new energy generation and energy storage by dynamically comparing multiple indicators such as charging and discharging efficiency, response time, and aging degree of energy storage equipment under different energy storage configurations; By dynamically comparing multiple indicators such as charging and discharging efficiency, response time, and aging degree of energy storage equipment under different energy storage configurations, the configuration of new energy generation and energy storage is optimized. The formula is as follows: Where: represents the solar power generation power at time t; represents the wind power generation at time t; represents the load demand at time t; Indicates the state of the energy storage device at time t; represents the response time at time t; Indicates the health status ratio of the energy storage device; Indicates the initial time; Respectively represent the priority weight coefficients of solar energy and wind power generation; Represents the time decay factor.

2. A distributed renewable energy storage optimization configuration method for a distribution network according to claim 1, characterized in that: Construct a load forecasting model as follows: The sensors collect historical electricity consumption data, real-time weather data and external factor data, and transmit them to the central control center as inputs to the prediction model; the weather data includes temperature, humidity and wind speed; the external factors include holidays and electricity price fluctuations; The load forecasting model is as follows: Where: represents the load demand at time t; Indicates based on temperature ,humidity and wind speed Forecasting load demand; Indicates that given a random variable Under the condition of Expected value; Indicates weather conditions; Statistical analysis is performed on historical electricity consumption data and real-time weather data to construct the uncertainty distribution of variables. Weather conditions are set as normal distributions, and the corresponding probability distribution model of electricity load demand is constructed based on the historical fluctuation range to capture uncertainty characteristics. Based on the captured uncertainty characteristics, discretization processing is performed. According to the fluctuation range of the uncertainty variables, the continuous variables of weather conditions and power load demand are divided into finite discrete intervals, and each discrete interval is assigned a corresponding occurrence probability; The discretized weather conditions and electricity load demand states are introduced into the load forecasting model to analyze and predict future supply and demand changes.

3. A distributed renewable energy storage optimization configuration method for a distribution network according to claim 2, characterized in that: Discretization processing is as follows: Perform statistical analysis on historical electricity consumption data and real-time weather data, construct uncertainty distribution of variables, and set weather conditions Normal distribution ;in, Indicates weather conditions The mean of Indicates weather conditions Relative to the mean fluctuations; The continuous probability distribution of weather conditions and power load demand is processed into discretized weather condition states , where k represents the number of discrete states, and each state corresponds to a probability , the discretized set is expressed as follows: Where: Represents the set of all state values ​​after discretization.

4. The method for optimizing the configuration of distributed renewable energy storage for distribution network according to claim 1, characterized in that: The optimal new energy complementary strategy is calculated as follows: Where: Represents the charging and discharging decisions of power generation and energy storage equipment at all times t.

5. A distributed new energy storage optimization configuration system for a distribution network, comprising: Load forecasting module, multi-objective optimization model module, dynamic configuration optimization module, and real-time adjustment and optimization module; A distributed renewable energy storage optimization configuration method for a distribution network according to any one of claims 1 to 4 is run, characterized in that: The load forecasting module is used to collect and process historical power consumption data, real-time weather data and external factors, and use the probability discretization method to build an accurate load forecasting model to provide forecast data for future load demand; The multi-objective optimization model module is used to maximize the utilization of renewable energy generation, minimize energy storage energy loss, and minimize operating costs; The dynamic configuration optimization module is used to iteratively adjust the power generation and energy storage configuration parameters, generate the optimal new energy complementary strategy, and optimize the configuration; The real-time adjustment and optimization module is used to monitor and feedback data in real time, automatically adjust the charging and discharging strategies, and optimize the configuration of new energy power generation and energy storage based on actual operating effects and simulation results.

Images