An energy storage configuration optimization method and system based on a local power grid model

Abstract

The present invention discloses an energy storage configuration optimization method and system based on a local power grid model, which relates to the technical field of power grid energy storage. When the system operates, through an information collection module, a data processing module, a model prediction module, and an evaluation trigger module, real-time data is collected to comprehensively monitor the load condition, power generation efficiency, weather condition, and operating state of equipment of the power grid. After being denoised, normalized, and feature-extracted, these data are used to train a deep learning model to construct a local power grid operation model, and the calculated local energy storage regulation index Tkzs is used to optimize the charging and discharging strategies of energy storage devices, so as to cope with immediate and predicted load changes. By matching with a preset local power grid operation energy storage regulation evaluation threshold T, it can automatically determine when to start power grid regulation, and can also dynamically adjust the operating state of energy storage devices according to specific regulation schemes to ensure that the power grid operates under the best conditions.

Description

Technical Field

[0001] The present invention relates to the field of power grid energy storage technology, and in particular to a method and system for optimizing energy storage configuration based on a local power grid model. Background Art

[0002] Local power grids typically include multiple types of energy production, such as solar, wind, and traditional fossil fuel generators. In such systems, energy storage configuration optimization systems play a vital role, balancing production and demand by adjusting the operation of energy storage devices.

[0003] However, existing energy storage configuration optimization systems have certain limitations when dealing with rapidly changing grid conditions. Due to the lack of effective forecasting tools and technologies, these systems are often unable to accurately predict changes in energy demand and supply in local power grids, especially in the case of highly integrated renewable energy. This leads to slow response in grid operations and the inability to adjust the status of energy storage equipment in time to cope with sudden power demand or surplus conditions, which in turn affects the stability and economic efficiency of the grid.

[0004] This limitation mainly stems from the fact that the existing system relies on static data analysis and configuration strategies and lacks dynamic and adaptive forecasting capabilities. Without effective forecasting capabilities, grid operators are often unable to foresee fluctuations in energy supply and demand caused by weather changes, user behavior or market factors. This situation is particularly evident when there is a sudden increase in power load or unstable renewable energy output, which may lead to energy shortages or over-investment, increase operating costs, reduce the system's energy utilization efficiency, and even cause unstable power supply, affecting users' power usage experience. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a method and system for optimizing energy storage configuration based on a local power grid model, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an energy storage configuration optimization system based on a local power grid model, comprising an information acquisition module, a data processing module, a model prediction module and an evaluation trigger module;

[0007] The information acquisition module collects real-time data from the local power grid, including load data, power generation data, weather conditions, and equipment status information, by deploying several sensors at the nodes of the local power grid to form a local real-time information group;

[0008] The data processing module pre-processes the local real-time information group, including data denoising, data formatting and normalization, and then performs feature extraction to form a processed local real-time information group;

[0009] The model prediction module establishes a local power grid operation model for the local real-time information group by using deep learning technology, and obtains the local energy storage regulation index Tkzs through training and fitting the local power grid operation model.

[0010] The evaluation trigger module matches the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain a local power grid regulation plan, and synchronously executes specifically according to the content of the local power grid regulation plan, including regulating the operation state of the local power grid energy storage.

[0011] Preferably, the information collection module includes a collection unit;

[0012] The collection unit collects real-time data in the local power grid by deploying a number of sensors at the nodes of the local power grid, including load data, power generation data, weather conditions, and equipment status information, to form a local real-time information group;

[0013] The sensors include power sensors, environmental sensors, equipment performance sensors, and communication sensors;

[0014] The load data information includes total power consumption, peak load, load rise rate, load fall rate, and power consumption pattern;

[0015] The power generation data information includes total power generation, real-time power output, conversion efficiency, power generation fluctuation rise rate, and power generation fluctuation fall rate;

[0016] The weather condition information includes temperature, wind speed, sunlight intensity, humidity, and rainfall.

[0017] Preferably, the data processing module includes a preprocessing unit and a feature unit;

[0018] The preprocessing unit preprocesses the local real-time information group, including data denoising, outlier processing, data formatting, and normalization processing;

[0019] Data denoising includes using a moving average and a median filter to remove noise and occasional anomalies in the collected data;

[0020] Outlier processing includes using the interquartile range and the Z-score method to identify and process or delete outliers in the data;

[0021] Data formatting converts special data collected into a unified format, including converting time data to a unified timestamp format and converting numerical data to a numerical representation;

[0022] Normalization processing includes Min-Max normalization and Z-score standardization, which convert data of different scales and ranges into a unified proportional scale;

[0023] The feature unit extracts features from the preprocessed local real-time information group, including the periodic changes of the power grid load, peak periods, valley periods, and environmental changes, to form the processed local real-time information group, including the maximum daily load fluctuation Rfz, the maximum output power fluctuation Scmax, the maximum input power fluctuation Srmax, the peak duration Fsc, the valley duration Gsc, the average temperature value Wdz, the maximum sunshine duration Rzmax, and the average sunshine duration Rzz.

[0024] Preferably, the model prediction module includes a modeling unit and a training unit;

[0025] The modeling unit uses deep learning technology to establish a local power grid operation model for the local real-time information group, and through training the local power grid operation model, obtains the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz;

[0026] The training unit fits the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz obtained by training the local power grid operation model to obtain the local energy storage regulation index Tkzs;

[0027] The local energy storage regulation index Tkzs is obtained through the following calculation formula:

[0028]

[0029] In the formula, Tkzs represents the local energy storage regulation index, Fzyz represents the load fluctuation factor, Cnyz represents the energy storage fluctuation factor, Hjyz represents the environmental fluctuation factor, and t1, t2, and t3 respectively represent the proportionality coefficients of the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz;

[0030] Among them, 0 ≤ t1 ≤ 1, 0 ≤ t2 ≤ 1, 0 ≤ t3 ≤ 1, and t1 + t2 + t3 = 1, and W represents the first correction constant.

[0031] Preferably, the load fluctuation factor Fzyz is obtained through the following calculation formula:

[0032]

[0033] In the formula, Fzyz represents the load fluctuation factor, Rfz represents the maximum daily load fluctuation, Fsc represents the peak duration, Scmax represents the maximum output power fluctuation, Rzmax represents the maximum sunshine duration, and f1, f2, f3, and f4 respectively represent the proportionality coefficients of the maximum daily load fluctuation Rfz, the peak duration Fsc, the maximum output power fluctuation Scmax, and the maximum sunshine duration Rzmax;

[0034] Wherein, 0≤f1≤1, 0≤f2≤1, 0≤f3≤1, 0≤f4≤1, and f1 + f2 + f3 + f4 = 1, and K represents the second correction constant.

[0035] Preferably, the energy storage fluctuation factor Cnyz is obtained through the following calculation formula:

[0036]

[0037] In the formula, Cnyz represents the energy storage fluctuation factor, Scmax represents the maximum output power fluctuation, Srmax represents the maximum input power fluctuation, Rzz represents the average sunshine value, Rzmax represents the maximum sunshine duration, c1 and c2 respectively represent the proportionality coefficients of the maximum output power fluctuation Scmax and the maximum input power fluctuation Srmax, c3 represents the proportionality coefficient of the calculation result of the maximum output power fluctuation Scmax and the maximum input power fluctuation Srmax, c4 represents the proportionality coefficient of the average sunshine value Rzz, and c5 represents the proportionality coefficient of the calculation result of the maximum sunshine duration Rzmax and the average sunshine value Rzz;

[0038] Wherein, 0≤c1≤1, 0≤c2≤1, 0≤c3≤1, 0≤c4≤1, 0≤c5≤1, and c1 + c2 + c3 + c4 + c5 = 1, and D represents the third correction constant.

[0039] Preferably, the environmental fluctuation factor Hjyz is obtained through the following calculation formula:

[0040]

[0041] In the formula, Hjyz represents the environmental fluctuation factor, Rzz represents the average sunshine value, Rzmax represents the maximum sunshine duration, Wdz represents the average temperature value, Rfz represents the maximum daily load fluctuation, and h1, h2, h3, and h4 respectively represent the proportionality coefficients of the average sunshine value Rzz, the maximum sunshine duration Rzmax, the average temperature value Wdz, and the maximum daily load fluctuation Rfz;

[0042] Wherein, 0≤h1≤1, 0≤h2≤1, 0≤h3≤1, 0≤h4≤1, and h1 + h2 + h3 + h4 = 1, and L represents the fourth correction constant.

[0043] Preferably, the evaluation trigger module includes a matching unit and an execution unit;

[0044] The matching unit matches the preset relevant information with the required comparison value, including matching the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation scheme;

[0045] The execution unit performs specific executions according to the content of the local power grid regulation plan, including regulating the operation status of the local power grid energy storage, including regulating the charging and discharging strategies, energy storage capacity management, output power regulation, and regulating the working environment status of the energy storage device.

[0046] Preferably, the local power grid regulation plan is obtained through the following matching method:

[0047] When the local energy storage regulation index Tkzs ≤ the local power grid operation energy storage regulation evaluation threshold T, the non-regulation evaluation result of the local power grid is obtained, and the operation status and operation parameters of the power grid energy storage device are not regulated;

[0048] When the local energy storage regulation index Tkzs > the local power grid operation energy storage regulation evaluation threshold T, the regulation evaluation result of the local power grid is obtained, and the operation status and operation parameters of the power grid energy storage device are regulated.

[0049] An energy storage configuration optimization method based on a local power grid model includes the following steps:

[0050] Step 1: The information collection module deploys a number of sensors at the nodes of the local power grid to collect real-time data in the local power grid, including load data, power generation data, weather conditions, and equipment status information, and forms a local real-time information group;

[0051] Step 2: The data processing module preprocesses the local real-time information group, including data denoising, data formatting, and normalization processing, and then performs feature extraction to form the processed local real-time information group;

[0052] Step 3: The model prediction module uses deep learning technology to establish a local power grid operation model for the local real-time information group, and obtains the local energy storage regulation index Tkzs through training and fitting the local power grid operation model;

[0053] Step 4: The evaluation trigger module matches the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation plan, and synchronously performs specific executions according to the content of the local power grid regulation plan, including regulating the operation status of the local power grid energy storage.

[0054] The present invention provides an energy storage configuration optimization method and system based on a local power grid model, having the following beneficial effects:

[0055] (1) When the system is running, through the information collection module, data processing module, model prediction module, and evaluation trigger module, sensors are deployed at key nodes to collect real-time data. This system can comprehensively monitor the load conditions, power generation efficiency, weather conditions, and the operating status of equipment in the power grid. After denoising, standardizing, and feature extraction, these data are used to train a deep learning model to construct a local power grid operation model. The calculated local energy storage regulation index Tkzs is used to optimize the charging and discharging strategies of energy storage devices, so as to cope with immediate and predicted load changes. By matching with the preset local power grid operation energy storage regulation evaluation threshold T, it can automatically determine when to start power grid regulation and dynamically adjust the operating status of energy storage devices according to specific regulation schemes to ensure that the power grid operates under optimal conditions.

[0056] (2) By fitting the load fluctuation factor Fzyz, energy storage fluctuation factor Cnyz, and environmental fluctuation factor Hjyz, the local energy storage regulation index Tkzs is obtained, and then various fluctuation data are integrated to provide a scientific and numerical evaluation result. At the same time, it optimizes the energy distribution and consumption of the power grid, improves the adaptability to environmental changes, especially in modern power grid systems highly dependent on renewable energy. In addition, by precisely controlling the operating status of energy storage devices, the service life of the devices is extended and the maintenance cost is reduced.

[0057] (3) By matching the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs, a local power grid regulation scheme is obtained. This matching method can respond in a timely manner when the operating status and operating parameters of energy storage devices need to be adjusted. For example, increasing discharge during high demand or increasing charging when low-cost electricity is available, and timely managing the total capacity and remaining capacity of energy storage devices. This dynamic regulation not only optimizes energy use, reduces energy waste, but also improves the system's adaptability to peak-valley loads, thereby enhancing the stability and economy of the power grid. By adjusting the output power and working environment status, the system can effectively extend the service life of energy storage devices and keep them operating efficiently, further reducing the maintenance cost and improving the operating efficiency of the entire power grid. Such a system design not only improves the automation level of energy management, but also ensures the high efficiency of power grid operation and environmental sustainability, demonstrating the important application value of smart grid technology in modern energy systems. Description of the Drawings

[0058] Figure 1 It is a schematic diagram of the block diagram process of an energy storage configuration optimization system based on a local power grid model of the present invention;

[0059] Figure 2 It is a schematic diagram of the steps of an energy storage configuration optimization method based on a local power grid model of the present invention. Detailed Embodiments

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0061] A local power grid usually includes various types of energy production methods, such as solar energy, wind energy, and traditional fossil fuel generators. In such a system, an energy storage configuration optimization system plays a crucial role in balancing production and demand by adjusting the operation of energy storage devices.

[0062] However, the existing energy storage configuration optimization systems have certain limitations in dealing with rapidly changing grid conditions. Due to the lack of effective prediction tools and technologies, these systems often cannot accurately predict the changes in energy demand and supply in the local power grid, especially in the case of highly integrated renewable energy, which leads to a slow response in grid operation and the inability to timely adjust the state of energy storage devices to cope with sudden power demands or surpluses, thereby affecting the stability and economic efficiency of the power grid.

[0063] This limitation mainly stems from the fact that existing systems rely on static data analysis and configuration strategies and lack dynamic and adaptive prediction capabilities. Without effective prediction capabilities, grid operators often cannot foresee energy supply and demand fluctuations caused by weather changes, user behavior, or market factors. This situation is particularly obvious when the power load suddenly increases or the output of renewable energy is unstable, which may lead to energy shortages or over-investment, increase operating costs, reduce the energy utilization efficiency of the system, and even cause instability in power supply, affecting the power usage experience of users.

[0064] Embodiment 1

[0065] The present invention provides an energy storage configuration optimization system based on a local power grid model. Please refer to Figure 1 , which includes an information collection module, a data processing module, a model prediction module, and an evaluation trigger module;

[0066] The information collection module collects real-time data in the local power grid by deploying a number of sensors at the nodes of the local power grid, including load data, power generation data, weather conditions, and device status information, to form a local real-time information group;

[0067] The data processing module preprocesses the local real-time information group, including data denoising, data formatting, and normalization processing, and then performs feature extraction to form the processed local real-time information group;

[0068] The model prediction module establishes a local power grid operation model for the local real-time information group by using deep learning technology, and obtains the local energy storage regulation index Tkzs through training and fitting the local power grid operation model.

[0069] The evaluation trigger module matches the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation plan, and synchronously executes specifically according to the content of the local power grid regulation plan, including regulating the operation state of the local power grid energy storage.

[0070] In this embodiment, through the information collection module, data processing module, model prediction module and evaluation trigger module, sensors are deployed at key nodes to collect real-time data. This system can comprehensively monitor the load conditions, power generation efficiency, weather conditions and operation status of equipment of the power grid. After denoising, standardizing and feature extraction, these data are used to train a deep learning model to construct a local power grid operation model, and the calculated local energy storage regulation index Tkzs is used to optimize the charging and discharging strategies of energy storage devices, so as to cope with immediate and predicted load changes. By matching with the preset local power grid operation energy storage regulation evaluation threshold T, it can automatically determine when to start power grid regulation, and can also dynamically adjust the operation state of energy storage devices according to the specific regulation plan to ensure that the power grid operates under the best conditions.

[0071] Embodiment 2

[0072] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: The information collection module includes a collection unit;

[0073] The collection unit collects real-time data in the local power grid by deploying a number of sensors at the nodes of the local power grid, including load data, power generation data, weather conditions and equipment status information, to form a local real-time information group.

[0074] The sensors include power sensors, environmental sensors, equipment performance sensors and communication sensors;

[0075] The load data information includes total power consumption, peak load, load increase rate, load decrease rate and power consumption pattern;

[0076] The power generation data information includes total power generation, real-time power output, conversion efficiency, power generation fluctuation increase rate and power generation fluctuation decrease rate;

[0077] The weather condition information includes temperature, wind speed, sunshine intensity, humidity and rainfall.

[0078] The data processing module includes a preprocessing unit and a feature unit;

[0079] The preprocessing unit preprocesses the local real-time information group, including data denoising, outlier processing, data formatting, and normalization processing;

[0080] Data denoising includes using a moving average and a median filter to remove noise and occasional anomalies in the collected data;

[0081] Outlier processing includes using the interquartile range and the Z-score method to identify and process or remove outliers in the data;

[0082] Data formatting converts the collected special data into a unified format, including converting the time data to a unified timestamp format and converting the numerical data to a numerical representation;

[0083] Normalization processing includes Min-Max normalization and Z-score standardization, which convert data of different scales and ranges into a unified proportional scale;

[0084] The feature unit extracts features from the preprocessed local real-time information group, including the periodic changes of the power grid load, peak periods, valley periods, and environmental changes, and forms the processed local real-time information group, including the maximum daily load fluctuation Rfz, the maximum output power fluctuation Scmax, the maximum input power fluctuation Srmax, the peak duration Fsc, the valley duration Gsc, the average temperature value Wdz, the maximum sunshine duration Rzmax, and the average sunshine value Rzz.

[0085] Embodiment 3

[0086] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: The model prediction module includes a modeling unit and a training unit;

[0087] The modeling unit uses deep learning technology to establish a local power grid operation model for the local real-time information group, and obtains the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz by training the local power grid operation model;

[0088] The training unit fits the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz obtained by training the local power grid operation model to obtain the local energy storage regulation index Tkzs;

[0089] The local energy storage regulation index Tkzs is obtained through the following calculation formula:

[0090]

[0091] In the formula, Tkzs represents the local energy storage regulation index, Fzyz represents the load fluctuation factor, Cnyz represents the energy storage fluctuation factor, Hjyz represents the environmental fluctuation factor, and t1, t2, and t3 respectively represent the proportionality coefficients of the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz;

[0092] Among them, 0 ≤ t1 ≤ 1, 0 ≤ t2 ≤ 1, 0 ≤ t3 ≤ 1, and t1 + t2 + t3 = 1, and W represents the first correction constant.

[0093] The load fluctuation factor Fzyz is obtained through the following calculation formula:

[0094]

[0095] In the formula, Fzyz represents the load fluctuation factor, Rfz represents the maximum daily load fluctuation, Fsc represents the peak duration, Scmax represents the maximum output power fluctuation, Rzmax represents the maximum sunshine duration, and f1, f2, f3, and f4 respectively represent the proportionality coefficients of the maximum daily load fluctuation Rfz, the peak duration Fsc, the maximum output power fluctuation Scmax, and the maximum sunshine duration Rzmax;

[0096] Among them, 0 ≤ f1 ≤ 1, 0 ≤ f2 ≤ 1, 0 ≤ f3 ≤ 1, 0 ≤ f4 ≤ 1, and f1 + f2 + f3 + f4 = 1, and K represents the second correction constant.

[0097] The energy storage fluctuation factor Cnyz is obtained through the following calculation formula:

[0098]

[0099] In the formula, Cnyz represents the energy storage fluctuation factor, Scmax represents the maximum output power fluctuation, Srmax represents the maximum input power fluctuation, Rzz represents the average sunshine duration, Rzmax represents the maximum sunshine duration, c1 and c2 respectively represent the proportionality coefficients of the maximum output power fluctuation Scmax and the maximum input power fluctuation Srmax, c3 represents the proportionality coefficient of the calculation result of the maximum output power fluctuation Scmax and the maximum input power fluctuation Srmax, c4 represents the proportionality coefficient of the average sunshine duration Rzz, and c5 represents the proportionality coefficient of the calculation result of the maximum sunshine duration Rzmax and the average sunshine duration Rzz;

[0100] Among them, 0 ≤ c1 ≤ 1, 0 ≤ c2 ≤ 1, 0 ≤ c3 ≤ 1, 0 ≤ c4 ≤ 1, 0 ≤ c5 ≤ 1, and c1 + c2 + c3 + c4 + c5 = 1, and D represents the third correction constant.

[0101] The environmental fluctuation factor Hjyz is obtained through the following calculation formula:

[0102]

[0103] In the formula, Hjyz represents the environmental fluctuation factor, Rzz represents the average sunshine duration, Rzmax represents the maximum sunshine duration, Wdz represents the average temperature value, Rfz represents the maximum daily load fluctuation, and h1, h2, h3, and h4 respectively represent the proportionality coefficients of the average sunshine duration Rzz, the maximum sunshine duration Rzmax, the average temperature value Wdz, and the maximum daily load fluctuation Rfz;

[0104] Among them, 0 ≤ h1 ≤ 1, 0 ≤ h2 ≤ 1, 0 ≤ h3 ≤ 1, 0 ≤ h4 ≤ 1, and h1 + h2 + h3 + h4 = 1, and L represents the fourth correction constant.

[0105] In this embodiment, through the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz for fitting, the local energy storage regulation index Tkzs is obtained, and then a variety of fluctuation data is integrated, so as to provide a scientific and numerical evaluation result, while optimizing the energy distribution and consumption of the power grid, improving the adaptability to environmental changes, especially in the modern power grid system highly dependent on renewable energy. In addition, by precisely controlling the operating state of the energy storage device, the service life of the device is extended, and the maintenance cost is reduced.

[0106] Embodiment 4

[0107] This embodiment is an explanatory description carried out in Embodiment 1, please refer to Figure 1 , specifically: the evaluation trigger module includes a matching unit and an execution unit;

[0108] The matching unit matches through preset relevant information with the required comparison value, including matching the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation plan;

[0109] The execution unit specifically executes according to the content of the local power grid regulation plan, including regulating the operating state of the local power grid energy storage, including regulating the charging and discharging strategies, energy storage capacity management, output power regulation, and regulating the working environment state of the energy storage device.

[0110] The local power grid regulation plan is obtained through the following matching method:

[0111] When the local energy storage regulation index Tkzs ≤ the local power grid operation energy storage regulation evaluation threshold T, the local power grid non-regulation evaluation result is obtained, and the operating state and operating parameters of the power grid energy storage device are not regulated;

[0112] The local energy storage regulation index Tkzs > the local power grid operation energy storage regulation evaluation threshold T, obtain the local power grid regulation evaluation result, and regulate the operation status and operation parameters of the power grid energy storage device, including regulating the charging and discharging strategies, energy storage capacity management, output power regulation, and regulating the working environment status of the energy storage device;

[0113] Charging and discharging strategies: charging power, discharging power, charging time, and discharging time;

[0114] Energy storage capacity management: remaining capacity and total capacity management.

[0115] In this embodiment, by matching the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs, a local power grid regulation scheme is obtained. This matching method can respond in a timely manner when the operation status and operation parameters of the energy storage device need to be adjusted. For example, increasing discharging during high demand or increasing charging when low-cost electricity is available, and timely managing the total capacity and remaining capacity of the energy storage device. This dynamic regulation not only optimizes energy use, reduces energy waste, but also improves the system's adaptability to peak-valley loads, thereby enhancing the stability and economy of the power grid. By adjusting the output power and working environment status, the system can effectively extend the service life of the energy storage device and keep it running efficiently, further reducing maintenance costs and improving the operation efficiency of the entire power grid. Such a system design not only improves the automation level of energy management, but also ensures the high efficiency of power grid operation and environmental sustainability, demonstrating the important application value of smart grid technology in modern energy systems.

[0116] Embodiment 5

[0117] An energy storage configuration optimization method based on a local power grid model, please refer to Figure 2 , specifically: including the following steps:

[0118] Step 1: The information collection module collects real-time data in the local power grid by deploying several sensors at the nodes of the local power grid, including load data, power generation data, weather conditions, and equipment status information, to form a local real-time information group;

[0119] Step 2: The data processing module preprocesses the local real-time information group, including data denoising, data formatting, and normalization processing, and then performs feature extraction to form the processed local real-time information group;

[0120] Step 3: The model prediction module uses deep learning technology to establish a local power grid operation model for the local real-time information group, and obtains the local energy storage regulation index Tkzs through training and fitting the local power grid operation model;

[0121] Step 4: The evaluation trigger module matches the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation plan, and synchronously executes specifically according to the content of the local power grid regulation plan, including regulating the operation state of the local power grid energy storage.

[0122] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An energy storage configuration optimization system based on a local power grid model, characterized in that: It includes an information acquisition module, a data processing module, a model prediction module, and an evaluation trigger module; The information acquisition module collects real-time data in the local power grid by deploying a number of sensors at the nodes of the local power grid, including load data, power generation data, weather conditions, and equipment status information, to form a local real-time information group; The data processing module preprocesses the local real-time information group, including data denoising, data formatting, and normalization processing, and then performs feature extraction to form the processed local real-time information group; The model prediction module uses deep learning technology to establish a local power grid operation model for the local real-time information group, and obtains the local energy storage regulation index Tkzs by training and fitting the local power grid operation model; The model prediction module includes a modeling unit and a training unit; The modeling unit uses deep learning technology to establish a local power grid operation model for the local real-time information group, and obtains the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz by training the local power grid operation model; The training unit fits the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz obtained by training the local power grid operation model to obtain the local energy storage regulation index Tkzs; The local energy storage regulation index Tkzs is obtained through the following calculation formula: In the formula, Tkzs represents the local energy storage regulation index, Fzyz represents the load fluctuation factor, Cnyz represents the energy storage fluctuation factor, Hjyz represents the environmental fluctuation factor, and t1, t2, and t3 respectively represent the proportionality coefficients of the load fluctuation factor Fzyz, the energy storage fluctuation factor Cnyz, and the environmental fluctuation factor Hjyz; Among them, 0 ≤ t1 ≤ 1, 0 ≤ t2 ≤ 1, 0 ≤ t3 ≤ 1, and t1 + t2 + t3 = 1, and W represents the first correction constant; The load fluctuation factor Fzyz is obtained through the following calculation formula: In the formula, Fzyz represents the load fluctuation factor, Rfz represents the maximum daily load fluctuation, Fsc represents the peak duration, Scmax represents the maximum output power fluctuation, Rzmax represents the maximum sunshine duration, and f1, f2, f3, and f4 respectively represent the proportionality coefficients of the maximum daily load fluctuation Rfz, the peak duration Fsc, the maximum output power fluctuation Scmax, and the maximum sunshine duration Rzmax; Among them, 0 ≤ f1 ≤ 1, 0 ≤ f2 ≤ 1, 0 ≤ f3 ≤ 1, 0 ≤ f4 ≤ 1, and f1 + f2 + f3 + f4 = 1, and K represents the second correction constant; The energy storage fluctuation factor Cnyz is obtained through the following calculation formula: In the formula, Cnyz represents the energy storage fluctuation factor, Scmax represents the maximum output power fluctuation, Srmax represents the maximum input power fluctuation, Rzz represents the average sunshine duration, Rzmax represents the maximum sunshine duration, c1 and c2 respectively represent the proportionality coefficients of the maximum output power fluctuation Scmax and the maximum input power fluctuation Srmax, c3 represents the proportionality coefficient of the calculation results of the maximum output power fluctuation Scmax and the maximum input power fluctuation Srmax, c4 represents the proportionality coefficient of the average sunshine duration Rzz, and c5 represents the proportionality coefficient of the calculation results of the maximum sunshine duration Rzmax and the average sunshine duration Rzz; Among them, 0 ≤ c1 ≤ 1, 0 ≤ c2 ≤ 1, 0 ≤ c3 ≤ 1, 0 ≤ c4 ≤ 1, 0 ≤ c5 ≤ 1, and c1 + c2 + c3 + c4 + c5 = 1, D represents the third correction constant; The environmental fluctuation factor Hjyz is obtained through the following calculation formula: In the formula, Hjyz represents the environmental fluctuation factor, Rzz represents the average sunshine duration, Rzmax represents the maximum sunshine duration, Wdz represents the average temperature value, Rfz represents the maximum daily load fluctuation, and h1, h2, h3, and h4 respectively represent the proportionality coefficients of the average sunshine duration Rzz, the maximum sunshine duration Rzmax, the average temperature value Wdz, and the maximum daily load fluctuation Rfz; Among them, 0 ≤ h1 ≤ 1, 0 ≤ h2 ≤ 1, 0 ≤ h3 ≤ 1, 0 ≤ h4 ≤ 1, and h1 + h2 + h3 + h4 = 1, L represents the fourth correction constant; The evaluation trigger module matches the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation plan, and synchronously executes specifically according to the content of the local power grid regulation plan, including regulating the operation state of the local power grid energy storage.

2. The energy storage configuration optimization system based on the local power grid model according to claim 1, wherein: The information collection module includes a collection unit; The collection unit collects real-time data in the local power grid by deploying a number of sensors at the nodes of the local power grid, including load data, power generation data, weather conditions, and equipment status information, to form a local real-time information group; The sensors include power sensors, environmental sensors, equipment performance sensors, and communication sensors; The load data information includes total power consumption, peak load, load increase rate, load decrease rate, and power consumption pattern; The power generation data information includes total power generation, real-time power output, conversion efficiency, power generation fluctuation increase rate, and power generation fluctuation decrease rate; The weather condition information includes temperature, wind speed, sunshine intensity, humidity, and rainfall.

3. The energy storage configuration optimization system based on the local power grid model according to claim 1, characterized in that: The data processing module includes a preprocessing unit and a feature unit; The preprocessing unit preprocesses the local real-time information group, including data denoising, outlier processing, data formatting, and normalization processing; Data denoising includes using a moving average and a median filter to remove noise and occasional anomalies in the collected data; Outlier processing includes using the interquartile range and the Z-score method to identify and process or delete outliers in the data; Data formatting converts the collected special data into a unified format, including converting time data to a unified timestamp format and converting numerical data to a numerical representation; The normalization process includes Min-Max normalization and Z-score standardization, which convert data of different scales and ranges into a unified proportional scale; The feature unit extracts features from the preprocessed local real-time information group, including the periodic changes of the power grid load, peak periods, valley periods, and environmental changes, and forms the processed local real-time information group, including the maximum daily load fluctuation Rfz, the maximum output power fluctuation Scmax, the maximum input power fluctuation Srmax, the peak duration Fsc, the valley duration Gsc, the average temperature value Wdz, the maximum sunshine duration Rzmax, and the average sunshine value Rzz.

4. The energy storage configuration optimization system based on the local power grid model according to claim 1, characterized in that: The evaluation trigger module includes a matching unit and an execution unit; The matching unit matches the preset relevant information with the required comparison values, including matching the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation plan; The execution unit specifically executes according to the content of the local power grid regulation plan, including regulating the operation state of the local power grid energy storage, including regulating the charging and discharging strategies, energy storage capacity management, output power regulation, and regulating the working environment state of the energy storage device.

5. The energy storage configuration optimization system based on the local power grid model according to claim 4, characterized in that: The local power grid regulation plan is obtained through the following matching method: When the local energy storage regulation index Tkzs ≤ the local power grid operation energy storage regulation evaluation threshold T, the local power grid non-regulation evaluation result is obtained, and the operation state and operation parameters of the power grid energy storage device are not regulated; When the local energy storage regulation index Tkzs > the local power grid operation energy storage regulation evaluation threshold T, the local power grid regulation evaluation result is obtained, and the operation state and operation parameters of the power grid energy storage device are regulated.

6. An energy storage configuration optimization method based on a local power grid model, including an energy storage configuration optimization system based on a local power grid model according to any one of the above claims 1 to 5, characterized in that: It includes the following steps: Step 1: The information collection module collects real-time data in the local power grid by deploying several sensors at the nodes of the local power grid, including load data, power generation data, weather conditions, and equipment status information, and forms a local real-time information group; Step 2: The data processing module preprocesses the local real-time information group, including data denoising, data formatting, and normalization processing, and then performs feature extraction to form the processed local real-time information group; Step 3: The model prediction module uses deep learning technology to establish a local power grid operation model for the local real-time information group, and obtains the local energy storage regulation index Tkzs through training and fitting of the local power grid operation model; Step 4: The evaluation trigger module matches the preset local power grid operation energy storage regulation evaluation threshold T with the local energy storage regulation index Tkzs to obtain the local power grid regulation plan, and simultaneously specifically executes according to the content of the local power grid regulation plan, including regulating the operation state of the local power grid energy storage.

Images