A regional power grid energy storage multi-point layout strategy optimization method

Abstract

The application discloses a regional power grid energy storage multi-point layout strategy optimization method and relates to the technical field of power grids, and the technical solution points of the application include the following steps: obtaining historical energy storage layout features of a historical regional power grid, and obtaining comprehensive energy storage verification conditions corresponding to different distribution conditions between load density areas and power grid nodes in the historical regional power grid; processing and analyzing the historical energy storage layout features to obtain first, second and third energy storage correlation coefficients; obtaining a target regional power grid of a to-be-optimized energy storage layout; predicting energy storage demand adjustment of the target regional power grid in an actual operation process according to the first, second and third energy storage correlation coefficients to obtain a first energy storage demand value; and the effect is to optimize and adjust an initial energy storage layout scheme according to the actual energy storage demand value.

Description

Technical Field

[0001] This invention relates to the field of power grid technology, and more specifically, to an optimization method for multi-point layout strategy of regional power grid energy storage. Background Technology

[0002] In the current operation of regional power grids, the deployment of energy storage systems is crucial for ensuring grid stability and improving power utilization efficiency. However, traditional energy storage deployment methods lack sufficient mining and scientific analysis of historical data. For example, some regions have not conducted in-depth research on the impact of historical load density areas and grid node distribution on energy storage demand when deploying energy storage. This leads to a mismatch between energy storage deployment and actual grid operation needs. During peak electricity demand periods, some areas lack sufficient energy storage capacity, failing to effectively alleviate power supply pressure; while during off-peak periods, energy storage devices remain idle, resulting in resource waste. Furthermore, the differences in energy storage demand under different operating scenarios are not considered, and there is a lack of effective verification and correction mechanisms for predicted energy storage demand, making the final energy storage demand data inaccurate and affecting the optimization effect of energy storage deployment schemes. Summary of the Invention

[0003] To address the shortcomings of existing technologies, the present invention aims to provide an optimization method for multi-point layout strategy of regional power grid energy storage.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] An optimization method for multi-point deployment strategy of regional power grid energy storage, the method includes the following steps:

[0006] The historical energy storage layout characteristics of the historical regional power grid are obtained, and the comprehensive energy storage verification conditions corresponding to different distributions of load density areas and grid nodes in the historical regional power grid are obtained.

[0007] The first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient are obtained by processing and analyzing the historical energy storage layout characteristics.

[0008] Obtain the target area power grid for the energy storage layout to be optimized;

[0009] Based on the first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient, the energy storage demand of the target area power grid during actual operation is predicted to obtain the first energy storage demand value; the energy storage demand base value of the target area power grid is predicted under the baseline load scenario to obtain the second energy storage demand value.

[0010] Energy storage preprocessing verification conditions for energy storage demand prediction verification of the target area power grid are selected from the comprehensive energy storage verification conditions; the first energy storage demand value is verified and adjusted according to the energy storage preprocessing verification conditions, and the first actual energy storage demand value and the second actual energy storage demand value are obtained by combining the second energy storage demand value.

[0011] The initial energy storage layout plan is optimized and adjusted based on the first or second actual energy storage demand value.

[0012] Preferably, the comprehensive energy storage verification conditions are obtained based on different distributions of load density areas and grid nodes in the historical regional power grid, specifically including the following steps:

[0013] If a historical regional power grid has load density areas and power grid nodes, and the high load density area is located at the center of the regional power grid, it is marked as power grid layout feature one;

[0014] If a historical regional power grid has load density areas and power grid nodes, and the high load density area is located at the edge of the regional power grid node, then it is marked as power grid layout feature two;

[0015] If the load density area and the power grid node are in an overlapping relationship in terms of location distribution, it is marked as power grid layout feature three;

[0016] If the historical regional power grid only has a single load density area, it is marked as power grid layout feature four;

[0017] If the historical regional power grid has only a single type of power grid node, it is marked as power grid layout feature five;

[0018] The five power grid layout characteristics are combined to form the comprehensive energy storage verification conditions.

[0019] Preferably, the first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient are obtained by processing and analyzing the historical energy storage layout characteristics, specifically including the following steps:

[0020] If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics are fluctuating, then the correlation coefficient between the operating fluctuation of energy storage facilities and energy storage demand is extracted to obtain the first energy storage correlation coefficient.

[0021] If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a stable state, then the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient; and the correlation coefficient between grid node type conversion and energy storage demand is extracted to obtain the third energy storage correlation coefficient.

[0022] Preferably, if the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics fluctuate, then the first energy storage correlation coefficient is obtained by extracting the correlation coefficient between the operating fluctuation of energy storage facilities and energy storage demand. This specifically includes the following steps:

[0023] If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics are fluctuating, then it is marked as energy storage layout characteristic one.

[0024] Obtain the actual energy storage demand of energy storage facilities located in adjacent areas with the same load density type or the same type of grid nodes from historical regional power grids.

[0025] Based on the actual value of energy storage demand and the value of the fluctuation of energy storage facility operation, the correlation coefficient between the fluctuation of energy storage facility operation and energy storage demand is extracted to obtain the first energy storage correlation coefficient.

[0026] Preferably, if the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a steady state, then the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient, which specifically includes the following steps:

[0027] If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a steady state, then it is marked as energy storage layout characteristic two.

[0028] The actual energy storage demand values ​​of energy storage facilities located in adjacent areas of the historical regional power grid, with the upstream section being a high-load-density area and the downstream section a low-load-density area, are obtained.

[0029] Based on the actual value of energy storage demand and the stable value of energy storage facility operation, the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient.

[0030] Preferably, the third energy storage correlation coefficient is obtained by extracting the correlation coefficient between grid node type conversion and energy storage demand, specifically including the following steps:

[0031] The actual energy storage demand values ​​of energy storage facilities located in adjacent positions in the historical regional power grid, with the upstream being a hub-type power grid node and the downstream being a branch-type power grid node, are obtained from each of the following:

[0032] Based on the actual value of energy storage demand and the stable value of energy storage facility operation, the correlation coefficient between grid node type conversion and energy storage demand is extracted to obtain the third energy storage correlation coefficient.

[0033] Preferably, the first energy storage demand value is obtained by predicting the energy storage demand of the target area power grid during actual operation based on the first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient. This specifically includes the following steps:

[0034] Combine energy storage layout feature one and energy storage layout feature two into energy storage training feature set one;

[0035] The first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient are combined to form the second set of energy storage features to be trained.

[0036] Obtain historical energy storage layout schemes and corresponding actual energy storage demand data for the regional power grid.

[0037] A dynamic prediction model for energy storage demand is established based on historical operating parameters of the regional power grid, historical energy storage demand data, and energy storage training feature set one and energy storage training feature set two.

[0038] Obtain the current actual operating scenario characteristics of the power grid in the target area;

[0039] The current operating parameters, current actual operating scenario characteristics, initial energy storage layout scheme, and target area power grid are input into the dynamic prediction model of energy storage demand to obtain the first energy storage demand value by adjusting the energy storage demand of the target area power grid during actual operation.

[0040] Preferably, the second energy storage demand value is obtained by predicting the baseline energy storage demand of the target area power grid under the baseline load scenario, specifically including the following steps:

[0041] Acquire historical standard operating data of the regional power grid under baseline load scenarios;

[0042] Establish a benchmark forecasting model for energy storage demand based on historical standard operating data;

[0043] By collecting data on the load distribution uniformity of the power grid in the target area, the regional load distribution characteristics can be obtained.

[0044] The target area power grid, initial energy storage layout scheme, regional load distribution characteristics and current operating parameters are input into the energy storage demand benchmark prediction model to obtain the basic value of energy storage demand of the target area power grid, and thus the second energy storage demand value.

[0045] Preferably, the energy storage preprocessing verification conditions for energy storage demand forecasting verification of the target area power grid are selected from the comprehensive energy storage verification conditions, specifically including the following steps:

[0046] Target energy storage verification conditions were selected from the comprehensive energy storage verification conditions, which were consistent with the load density region and grid node type distribution of the target area power grid, and the energy storage preprocessing verification conditions were obtained.

[0047] Preferably, the first energy storage demand value is verified and adjusted according to the energy storage pre-processing verification conditions, and the first actual energy storage demand value and the second actual energy storage demand value are obtained by combining the second energy storage demand value. Specifically, this includes the following steps:

[0048] The current operating parameters, current actual operating scenario characteristics, and initial energy storage layout scheme in the energy storage preprocessing verification conditions are input into the energy storage demand dynamic prediction model to obtain the predicted value of the energy storage demand to be compared.

[0049] If the difference between the first energy storage demand value and the predicted energy storage demand value to be compared is within the preset allowable range threshold of energy storage demand error, then the second energy storage demand value and the first energy storage demand value are weighted and integrated to obtain the first actual energy storage demand value.

[0050] If the difference between the first energy storage demand value and the predicted energy storage demand value to be compared is outside the preset allowable range threshold for energy storage demand error, then the first energy storage demand value is corrected for error according to the ratio of the difference between the predicted energy storage demand value to be compared and the first energy storage demand value, to obtain the third energy storage demand value.

[0051] The second actual energy storage demand value is obtained by weighting and integrating the second and third energy storage demand values.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] This invention provides a solid basis for subsequent analysis and verification by acquiring the energy storage layout characteristics of historical regional power grids and the comprehensive energy storage verification conditions corresponding to different load density areas and power grid node distributions. Three types of energy storage correlation coefficients are obtained from the processing and analysis of historical energy storage layout characteristics, quantifying the correlation between different factors and energy storage demand. The first energy storage correlation coefficient reflects the relationship between energy storage facility operation fluctuations and energy storage demand; the second and third correlation coefficients respectively reflect the correlation between load area and power grid node type transformations and energy storage demand. These correlation coefficients lay the foundation for subsequent prediction of energy storage demand, making the prediction of energy storage demand in the target region's power grid more closely aligned with actual operating conditions. Based on the correlation coefficients, the first energy storage demand value during actual operation is predicted, and the second energy storage demand value is predicted under a baseline load scenario, achieving multi-scenario and comprehensive prediction of energy storage demand. By selecting suitable energy storage preprocessing verification conditions from the comprehensive energy storage verification conditions, verifying and adjusting the first energy storage demand value, and combining it with the second energy storage demand value to obtain the actual energy storage demand value, this process can effectively correct prediction errors, thereby improving the accuracy of the energy storage demand value. Based on the actual energy storage demand value, the initial energy storage layout scheme is optimized and adjusted, thereby improving the stability and economy of grid operation, better meeting the power supply and regulation needs of the regional grid, and helping the regional grid to operate efficiently and reliably. Attached Figure Description

[0054] Figure 1 This is a schematic diagram illustrating the steps of an optimization method for multi-point layout strategy of regional power grid energy storage proposed in this invention;

[0055] Figure 2 This is a schematic diagram illustrating the steps of the first energy storage correlation relationship in the regional power grid multi-point layout strategy optimization method proposed in this invention;

[0056] Figure 3 This is a schematic diagram illustrating the steps of the second energy storage correlation relationship in the regional power grid multi-point layout strategy optimization method proposed in this invention. Detailed Implementation

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0060] Reference Figures 1-3 .

[0061] The embodiments further illustrate the optimization method for multi-point layout strategy of regional power grid energy storage proposed in this invention.

[0062] An optimization method for multi-point deployment strategy of regional power grid energy storage, the method includes the following steps:

[0063] The historical energy storage layout characteristics of the historical regional power grid are obtained, and the comprehensive energy storage verification conditions corresponding to different distributions of load density areas and grid nodes in the historical regional power grid are obtained.

[0064] The first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient are obtained by processing and analyzing the historical energy storage layout characteristics.

[0065] Obtain the target area power grid for the energy storage layout to be optimized;

[0066] Based on the first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient, the energy storage demand of the target area power grid during actual operation is predicted to obtain the first energy storage demand value; the energy storage demand base value of the target area power grid is predicted under the baseline load scenario to obtain the second energy storage demand value.

[0067] Energy storage preprocessing verification conditions for energy storage demand prediction verification of the target area power grid are selected from the comprehensive energy storage verification conditions; the first energy storage demand value is verified and adjusted according to the energy storage preprocessing verification conditions, and the first actual energy storage demand value and the second actual energy storage demand value are obtained by combining the second energy storage demand value.

[0068] The initial energy storage layout plan is optimized and adjusted based on the first or second actual energy storage demand value.

[0069] First, the historical energy storage layout characteristics of the regional power grid are obtained. Simultaneously, the comprehensive energy storage verification conditions corresponding to different distributions of load density areas and grid nodes within the historical regional power grid are also acquired. This provides foundational data for subsequent analysis and verification; different distributions will correspond to different verification conditions, facilitating subsequent verification of the target regional power grid. The historical energy storage layout characteristics are processed and analyzed to obtain the first, second, and third energy storage correlation coefficients. These correlation coefficients are key to subsequent predictions of energy storage demand, reflecting the degree of correlation between different factors and energy storage demand.

[0070] Then, the target area power grid for the energy storage layout to be optimized is obtained, the optimization object is identified, and the energy storage demand adjustment of the target area power grid during actual operation is predicted based on the first, second, and third energy storage correlation coefficients, thus obtaining the first energy storage demand value. Simultaneously, the baseline energy storage demand of the target area power grid is predicted under a baseline load scenario to obtain the second energy storage demand value. Predicting energy storage demand through two different scenarios allows for a more comprehensive consideration of the target area power grid's energy storage needs. The actual operation scenario reflects the complex demands of the power grid during real-world operation, while the baseline load scenario provides a stable, basic demand reference.

[0071] Energy storage preprocessing verification conditions are selected from comprehensive energy storage verification conditions to verify energy storage demand forecasting for the target area's power grid. Because the target area's power grid has its own specific load density regions and grid node distribution, it is necessary to select verification conditions that match these characteristics to more accurately verify the energy storage demand value. Based on the selected energy storage preprocessing verification conditions, the first energy storage demand value is verified and adjusted, and combined with the second energy storage demand value to obtain the first and second actual energy storage demand values. This process corrects and integrates the predicted energy storage demand value, ensuring that the final energy storage demand value is more reliable.

[0072] First, a comprehensive and detailed survey of the basic situation of the power grid in the target area is conducted, including the geographical environment of the region, such as whether there are terrain factors such as mountains and rivers that may affect the construction of energy storage facilities; the significant differences in electricity demand in areas with different population densities; and the different electricity consumption patterns and load characteristics of different industries such as industry, commerce, and residence. Simultaneously, historical operating data of the power grid in this region is collected, including peak and valley loads over a period of time, the balance between power supply and consumption, and the fluctuations in electrical parameters such as voltage and current at various nodes in the power grid.

[0073] Based on this foundational data, a preliminary energy storage demand forecast is made. From a load perspective, the load demand at different times and in different regions is determined, thereby identifying which areas require more energy storage to supplement electricity during peak hours and which areas can charge energy storage facilities during off-peak hours. From the perspective of grid operation stability, the required energy storage capacity is considered to smooth power fluctuations when the grid is connected to new energy generation, thereby maintaining the stable operation of the grid.

[0074] Based on the estimated energy storage demand and the characteristics of different energy storage technologies, a suitable type of energy storage technology should be selected for the region. These technologies, such as electrochemical energy storage and pumped hydro storage, differ in energy density, response speed, cost, and lifespan. Preliminary planning for the installation location of the energy storage facilities should be conducted. Locations close to load centers should be considered to reduce losses during power transmission and improve the speed at which energy storage responds to load demands; alternatively, locations near critical nodes in the power grid should be chosen to better regulate the overall grid operation. Site conditions for energy storage facility construction should also be considered, such as the availability of suitable land resources and the completeness of surrounding infrastructure.

[0075] After completing the selection of technology type and preliminary location planning, a cost-benefit assessment is conducted. The construction cost, operation and maintenance cost, and benefits to the power grid are calculated, such as reducing peak-valley differences, reducing grid expansion investment, and improving the absorption capacity of new energy sources, thereby ensuring that the initial layout plan is economically feasible.

[0076] After a series of investigations, demand forecasts, technology selections, location planning, and cost-benefit assessments, an initial energy storage layout plan was formed.

[0077] The initial energy storage layout plan is adjusted based on either the first or second actual energy storage demand value. This optimization, based on the actual energy storage demand, makes the energy storage layout more rational, thereby better meeting the operational needs of the target area's power grid.

[0078] And obtain the comprehensive energy storage verification conditions corresponding to different distributions of load density areas and grid nodes in the historical regional power grid, specifically including the following steps:

[0079] If a historical regional power grid has load density areas and power grid nodes, and the high load density area is located at the center of the regional power grid, it is marked as power grid layout feature one;

[0080] If a historical regional power grid has load density areas and power grid nodes, and the high load density area is located at the edge of the regional power grid node, then it is marked as power grid layout feature two;

[0081] If the load density area and the power grid node are in an overlapping relationship in terms of location distribution, it is marked as power grid layout feature three;

[0082] If the historical regional power grid only has a single load density area, it is marked as power grid layout feature four;

[0083] If the historical regional power grid has only a single type of power grid node, it is marked as power grid layout feature five;

[0084] The five power grid layout characteristics are combined to form the comprehensive energy storage verification conditions.

[0085] This application categorizes and labels the distribution relationship between load density areas and grid nodes in historical regional power grids, thereby combining them into comprehensive energy storage verification conditions. This provides a basis for subsequent regional power grid energy storage verification. Corresponding grid layout characteristics are determined based on different distribution patterns. For example, when a historical regional power grid has both load density areas and grid nodes, and the high load density area is located at the center of the regional power grid, it is marked as power grid layout feature one. For example, the city center is a high load area, and the surrounding grid nodes are distributed around the city center, which conforms to power grid layout feature one. If the high load density area is located at the edge of the regional grid nodes, for example, a large factory on the edge of the city is a high load area, and the nearby grid nodes are around the factory, this situation is marked as power grid layout feature two. If the load density areas and grid nodes show an overlapping relationship in their location distribution, for example, commercial areas and residential areas with different loads in the city are interspersed with grid nodes, it is marked as power grid layout feature three. If the historical regional power grid has only a single load density area, for example, a small county town, the load density of the entire area is relatively uniform, and there is no obvious distinction between high and low load areas, it is marked as power grid layout feature four. If the historical regional power grid has only a single type of grid node, for example, all grid nodes in a small regional power grid are used for the same type of end distribution, that is, there is no distinction between hub type and branch type, it is marked as power grid layout feature five. The five power grid layout characteristics are integrated to form a comprehensive energy storage verification condition. When verifying the energy storage demand forecast of the regional power grid, the corresponding part is selected from the comprehensive energy storage verification condition based on the layout characteristics that the target regional power grid meets.

[0086] The analysis of historical energy storage layout characteristics yields the first, second, and third energy storage correlation coefficients, specifically including the following steps:

[0087] If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics are fluctuating, then the correlation coefficient between the operating fluctuation of energy storage facilities and energy storage demand is extracted to obtain the first energy storage correlation coefficient.

[0088] If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a stable state, then the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient; and the correlation coefficient between grid node type conversion and energy storage demand is extracted to obtain the third energy storage correlation coefficient.

[0089] This application primarily extracts corresponding energy storage correlation coefficients based on the different states of energy storage facility operating parameters in historical energy storage layout characteristics. Specifically, if the operating parameters of energy storage facilities in different load density areas or grid nodes in historical energy storage layout characteristics exhibit fluctuations, the correlation coefficient between the fluctuations in energy storage facility operation and energy storage demand is extracted to obtain the first energy storage correlation coefficient. For example, in areas with concentrated industrial and commercial loads and large differences in electricity consumption periods, the operating parameters of energy storage facility charging and discharging power frequently fluctuate. Therefore, the first energy storage correlation coefficient is obtained by analyzing the relationship between the fluctuations in energy storage facility operation and the energy storage demand in that area. If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a stable state, then on the one hand, the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient. For example, when converting from a high-load industrial area to a low-load residential area, the energy storage demand will change accordingly. By judging the correlation between this conversion and energy storage demand, the second energy storage correlation coefficient is obtained. On the other hand, the correlation coefficient between grid node type conversion and energy storage demand is extracted to obtain the third energy storage correlation coefficient. For example, when a grid node is converted from a hub type to a branch type, the change in energy storage demand is extracted and correlated with the conversion to obtain the third energy storage correlation coefficient.

[0090] If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics fluctuate, then the first energy storage correlation coefficient is obtained by extracting the correlation coefficient between the operating fluctuation of energy storage facilities and energy storage demand. The specific steps include:

[0091] If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics are fluctuating, then it is marked as energy storage layout characteristic one.

[0092] Obtain the actual energy storage demand of energy storage facilities located in adjacent areas with the same load density type or the same type of grid nodes from historical regional power grids.

[0093] Based on the actual value of energy storage demand and the value of the fluctuation of energy storage facility operation, the correlation coefficient between the fluctuation of energy storage facility operation and energy storage demand is extracted to obtain the first energy storage correlation coefficient.

[0094] First, the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics are determined. If these operating parameters show fluctuations, they are marked as energy storage layout characteristic one. For example, in a concentrated commercial area, the difference in electricity load between day and night is large, and the operating parameters of the charging and discharging power of energy storage facilities will fluctuate accordingly, which conforms to energy storage layout characteristic one. The actual energy storage demand values ​​of energy storage facilities in adjacent locations belonging to the same load density type or the same type of grid node are obtained from the historical regional power grid, and these actual energy storage demand values ​​are marked as actual energy storage demand value one. Based on actual energy storage demand value one and the degree of fluctuation in energy storage facility operation, the correlation coefficient between the fluctuation of energy storage facility operation and energy storage demand is extracted, thus obtaining the first energy storage correlation coefficient. For example, the correlation between the fluctuation of energy storage facility operation and the actual energy storage demand of two adjacent commercial blocks is obtained by extracting the corresponding correlation coefficient in this way.

[0095] If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a steady state, then the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient, which specifically includes the following steps:

[0096] If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a steady state, then it is marked as energy storage layout characteristic two.

[0097] The actual energy storage demand values ​​of energy storage facilities located in adjacent areas of the historical regional power grid, with the upstream section being a high-load-density area and the downstream section a low-load-density area, are obtained.

[0098] Based on the actual value of energy storage demand and the stable value of energy storage facility operation, the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient.

[0099] If the operating parameters of energy storage facilities in different load density areas and grid nodes are stable, this situation is marked as energy storage layout characteristic two. For example, in a city, adjacent areas are high-load-density industrial areas and low-load-density residential areas, and the operating parameters of the charging and discharging power of energy storage facilities in these areas are relatively stable without significant fluctuations, which meets the energy storage layout characteristic two. The actual energy storage demand values ​​corresponding to adjacent energy storage facilities located in adjacent areas, with the former being a high-load-density area and the latter a low-load-density area, are obtained from the historical regional power grid; these actual values ​​are called actual energy storage demand value two. Based on actual energy storage demand value two and the stable operating values ​​of energy storage facilities, the correlation coefficient between load area type conversion and energy storage demand is extracted, thus obtaining the second energy storage correlation coefficient. For example, for adjacent high-load industrial areas and low-load residential areas, by judging their actual energy storage demand values ​​and relevant data on the stable operation of energy storage facilities, the degree of correlation between the change in energy storage demand when the load shifts from industrial to residential areas and the change in load area type is obtained, thus obtaining the second energy storage correlation coefficient.

[0100] The third energy storage correlation coefficient is obtained by extracting the correlation coefficient between grid node type conversion and energy storage demand, specifically including the following steps:

[0101] The actual energy storage demand values ​​of energy storage facilities located in adjacent positions in the historical regional power grid, with the upstream being a hub-type power grid node and the downstream being a branch-type power grid node, are obtained from each of the following:

[0102] Based on the actual value of energy storage demand and the stable value of energy storage facility operation, the correlation coefficient between grid node type conversion and energy storage demand is extracted to obtain the third energy storage correlation coefficient.

[0103] This application first obtains the actual energy storage demand values ​​for energy storage facilities located adjacent to each other in the historical regional power grid, with the former being a hub-type grid node and the latter a branch-type grid node. These actual energy demand values ​​are designated as "Actual Energy Storage Demand Value Three." For example, in a regional power grid with adjacent hub-type substations and branch-type distribution nodes, the actual energy storage demand of their respective equipped energy storage facilities is designated as Actual Energy Storage Demand Value Three. Based on Actual Energy Storage Demand Value Three and the stable operating values ​​of the energy storage facilities, a correlation coefficient between grid node type conversion and energy storage demand is extracted, thus obtaining a third energy storage correlation coefficient. For instance, when converting from a hub-type grid node to a branch-type grid node, by analyzing the corresponding actual energy storage demand values ​​and relevant data on the stable operation of the energy storage facilities, the degree of correlation between node type conversion and changes in energy storage demand is clarified, resulting in the third energy storage correlation coefficient.

[0104] Based on the first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient, the energy storage demand of the target area power grid during actual operation is predicted and adjusted to obtain the first energy storage demand value. This process includes the following steps:

[0105] Combine energy storage layout feature one and energy storage layout feature two into energy storage training feature set one;

[0106] The first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient are combined to form the second set of energy storage features to be trained.

[0107] Obtain historical energy storage layout schemes and corresponding actual energy storage demand data for the regional power grid.

[0108] A dynamic prediction model for energy storage demand is established based on historical operating parameters of the regional power grid, historical energy storage demand data, and energy storage training feature set one and energy storage training feature set two.

[0109] Obtain the current actual operating scenario characteristics of the power grid in the target area;

[0110] The current operating parameters, current actual operating scenario characteristics, initial energy storage layout scheme, and target area power grid are input into the dynamic prediction model of energy storage demand to obtain the first energy storage demand value by adjusting the energy storage demand of the target area power grid during actual operation.

[0111] This application combines energy storage layout feature one and energy storage layout feature two to form energy storage training feature set one, which includes different typical states of energy storage layout in history; and combines the first energy storage correlation coefficient, the second energy storage correlation coefficient and the third energy storage correlation coefficient to form energy storage training feature set two, thereby aggregating the correlation between different factors and energy storage demand.

[0112] Obtain historical energy storage layout schemes and corresponding actual energy storage demand data for the regional power grid. For example, collect actual energy storage demand data for different energy storage layout schemes in a city's central business district and suburban industrial area under various operating conditions over the past few years.

[0113] Based on historical operating parameters and energy storage demand data of the regional power grid, a dynamic prediction model for energy storage demand is established using two sets of energy storage training features. Through training with a large amount of historical data, the dynamic prediction model for energy storage demand learns the intrinsic relationship between different energy storage layouts, operating parameters, correlations, and energy storage demand.

[0114] Obtain the current actual operating characteristics of the power grid in the target area. For example, if the target area is in the peak summer electricity consumption period and distributed photovoltaic power is connected to the grid, the actual operating characteristics will affect the demand for energy storage.

[0115] The current operating parameters of the target area's power grid, the characteristics of the current actual operating scenario, the initial energy storage layout plan, and the target area's power grid are input into the dynamic energy storage demand prediction model. Based on learned patterns, the dynamic energy storage demand prediction model obtains the first energy storage demand value of the target area's power grid during actual operation, thus providing crucial demand information for subsequent energy storage layout optimization.

[0116] To derive the second energy storage demand value from the baseline energy storage demand of the target area power grid under a baseline load scenario, the specific steps include:

[0117] Acquire historical standard operating data of the regional power grid under baseline load scenarios;

[0118] Establish a benchmark forecasting model for energy storage demand based on historical standard operating data;

[0119] By collecting data on the load distribution uniformity of the power grid in the target area, the regional load distribution characteristics can be obtained.

[0120] The target area power grid, initial energy storage layout scheme, regional load distribution characteristics and current operating parameters are input into the energy storage demand benchmark prediction model to obtain the basic value of energy storage demand of the target area power grid, and thus the second energy storage demand value.

[0121] First, historical standard operating data of the regional power grid is acquired under a baseline load scenario. This baseline load scenario can be a state where the power grid is stable and without extreme load fluctuations, such as the operating data of a city's power grid during non-holiday and non-peak electricity consumption periods. Then, an energy storage demand baseline prediction model is established based on this historical standard operating data. Through analysis of a large amount of historical stable operating data, the energy storage demand baseline prediction model learns the correlation between power grid operating parameters and energy storage demand under normal conditions. The load distribution uniformity of the target region's power grid is collected to obtain the regional load distribution characteristics. For example, some areas in the target region are densely populated residential areas with concentrated load distribution, while others are parks with sparse load distribution; this reflects the load distribution characteristics. The target region's power grid, the initial energy storage layout scheme, the regional load distribution characteristics, and the current operating parameters are input into the energy storage demand baseline prediction model. Based on the previously learned patterns, the energy storage demand baseline prediction model derives the basic value of the target region's power grid's energy storage demand, thus obtaining the second energy storage demand value.

[0122] The energy storage preprocessing verification conditions for energy storage demand forecasting verification of the target area power grid are selected from the comprehensive energy storage verification conditions, specifically including the following steps:

[0123] Target energy storage verification conditions were selected from the comprehensive energy storage verification conditions, which were consistent with the load density region and grid node type distribution of the target area power grid, and the energy storage preprocessing verification conditions were obtained.

[0124] Target energy storage verification conditions are selected from the comprehensive energy storage verification conditions to match the load density region and grid node type distribution of the target area's power grid, thus obtaining the energy storage preprocessing verification conditions. For example, assuming the comprehensive energy storage verification conditions include the distribution of high load density regions at the grid center and high load density regions at the grid node edges, and the target area's power grid has a high load concentration at the grid center, and the grid node type distribution also matches this, then this corresponding situation is selected from the comprehensive energy storage verification conditions and determined as the energy storage preprocessing verification condition.

[0125] The first energy storage demand value is verified and adjusted according to the energy storage pre-processing verification conditions, and the first actual energy storage demand value and the second actual energy storage demand value are obtained by combining the second energy storage demand value. The specific steps include:

[0126] The current operating parameters, current actual operating scenario characteristics, and initial energy storage layout scheme in the energy storage preprocessing verification conditions are input into the energy storage demand dynamic prediction model to obtain the predicted value of the energy storage demand to be compared.

[0127] If the difference between the first energy storage demand value and the predicted energy storage demand value to be compared is within the preset allowable range threshold of energy storage demand error, then the second energy storage demand value and the first energy storage demand value are weighted and integrated to obtain the first actual energy storage demand value.

[0128] If the difference between the first energy storage demand value and the predicted energy storage demand value to be compared is outside the preset allowable range threshold for energy storage demand error, then the first energy storage demand value is corrected for error according to the ratio of the difference between the predicted energy storage demand value to be compared and the first energy storage demand value, to obtain the third energy storage demand value.

[0129] The second actual energy storage demand value is obtained by weighting and integrating the second and third energy storage demand values.

[0130] First, the current operating parameters, current actual operating scenario characteristics, and initial energy storage layout scheme from the energy storage preprocessing verification conditions are input into the dynamic energy storage demand prediction model to obtain the predicted energy storage demand value to be compared. For example, if the target area's power grid is currently operating during peak electricity consumption, the operating parameters, scenario characteristics, and initial layout scheme at this time are input into the dynamic energy storage demand prediction model to obtain the corresponding predicted value to be compared. The first energy storage demand value and the predicted energy storage demand value to be compared are compared. If the difference between the two is within the preset allowable threshold range for energy storage demand error, it indicates that the accuracy of the first energy storage demand value is relatively high. In this case, the second energy storage demand value and the first energy storage demand value are weighted and integrated to obtain the first actual energy storage demand value. If the difference between the first energy storage demand value and the predicted energy storage demand value to be compared is outside the preset allowable threshold range for energy storage demand error, it indicates that the first energy storage demand value has a deviation. In this case, the first energy storage demand value is corrected for error based on the ratio of the difference between the predicted energy storage demand value to the first energy storage demand value to obtain the third energy storage demand value. The second and third energy storage demand values ​​are weighted and integrated to obtain the second actual energy storage demand value, thereby ensuring the accuracy of the final energy storage demand value and providing a reliable basis for subsequent energy storage layout optimization.

[0131] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the multi-point layout strategy of regional power grid energy storage, characterized in that, The method includes the following steps: The historical energy storage layout characteristics of the historical regional power grid are obtained, and the comprehensive energy storage verification conditions corresponding to different distributions of load density areas and grid nodes in the historical regional power grid are obtained. Specifically, the following steps are included: If a historical regional power grid has load density areas and power grid nodes, and the high load density area is located at the center of the regional power grid, it is marked as power grid layout feature one; If a historical regional power grid has load density areas and power grid nodes, and the high load density area is located at the edge of the regional power grid node, then it is marked as power grid layout feature two; If the load density area and the power grid node are in an overlapping relationship in terms of location distribution, it is marked as power grid layout feature three; If the historical regional power grid only has a single load density area, it is marked as power grid layout feature four; If the historical regional power grid has only a single type of power grid node, it is marked as power grid layout feature five; The power grid layout characteristics 1, 2, 3, 4, and 5 are combined to form the comprehensive energy storage verification conditions; The analysis of historical energy storage layout characteristics yields the first, second, and third energy storage correlation coefficients, specifically including the following steps: If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics are fluctuating, then the correlation coefficient between the operating fluctuation of energy storage facilities and energy storage demand is extracted to obtain the first energy storage correlation coefficient. If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a steady state, then the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient; and the correlation coefficient between grid node type conversion and energy storage demand is extracted to obtain the third energy storage correlation coefficient. Obtain the target area power grid for the energy storage layout to be optimized; Based on the first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient, the energy storage demand of the target area power grid during actual operation is predicted to obtain the first energy storage demand value; the energy storage demand base value of the target area power grid is predicted under the baseline load scenario to obtain the second energy storage demand value. Energy storage preprocessing verification conditions for energy storage demand prediction verification of the target area power grid are selected from the comprehensive energy storage verification conditions; the first energy storage demand value is verified and adjusted according to the energy storage preprocessing verification conditions, and the first actual energy storage demand value and the second actual energy storage demand value are obtained by combining the second energy storage demand value. The initial energy storage layout plan is optimized based on either the first or second actual energy storage demand value, specifically including the following steps: The current operating parameters, current actual operating scenario characteristics, and initial energy storage layout scheme in the energy storage preprocessing verification conditions are input into the energy storage demand dynamic prediction model to obtain the predicted value of the energy storage demand to be compared. If the difference between the first energy storage demand value and the predicted energy storage demand value to be compared is within the preset allowable range threshold of energy storage demand error, then the second energy storage demand value and the first energy storage demand value are weighted and integrated to obtain the first actual energy storage demand value. If the difference between the first energy storage demand value and the predicted energy storage demand value to be compared is outside the preset allowable range threshold for energy storage demand error, then the first energy storage demand value is corrected for error according to the ratio of the difference between the predicted energy storage demand value to be compared and the first energy storage demand value, to obtain the third energy storage demand value. The second actual energy storage demand value is obtained by weighting and integrating the second and third energy storage demand values.

2. The method for optimizing the multi-point layout strategy of regional power grid energy storage according to claim 1, characterized in that, If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics fluctuate, then the first energy storage correlation coefficient is obtained by extracting the correlation coefficient between the operating fluctuation of energy storage facilities and energy storage demand. The specific steps include: If the operating parameters of energy storage facilities in different load density areas or grid nodes in the historical energy storage layout characteristics are fluctuating, then it is marked as energy storage layout characteristic one. Obtain the actual energy storage demand of energy storage facilities located in adjacent areas with the same load density type or the same type of grid nodes from historical regional power grids. Based on the actual value of energy storage demand and the value of the fluctuation of energy storage facility operation, the correlation coefficient between the fluctuation of energy storage facility operation and energy storage demand is extracted to obtain the first energy storage correlation coefficient.

3. The method for optimizing the multi-point layout strategy of regional power grid energy storage according to claim 2, characterized in that, If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a steady state, then the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient, which specifically includes the following steps: If the operating parameters of energy storage facilities in different load density areas and grid nodes in the historical energy storage layout characteristics are in a steady state, then it is marked as energy storage layout characteristic two. The actual energy storage demand values ​​of energy storage facilities located in adjacent areas of the historical regional power grid, with the upstream section being a high-load-density area and the downstream section a low-load-density area, are obtained. Based on the actual value of energy storage demand and the stable value of energy storage facility operation, the correlation coefficient between load area type conversion and energy storage demand is extracted to obtain the second energy storage correlation coefficient.

4. The method for optimizing the multi-point layout strategy of regional power grid energy storage according to claim 3, characterized in that, The third energy storage correlation coefficient is obtained by extracting the correlation coefficient between grid node type conversion and energy storage demand, specifically including the following steps: The actual energy storage demand values ​​of energy storage facilities located in adjacent positions in the historical regional power grid, with the upstream being a hub-type power grid node and the downstream being a branch-type power grid node, are obtained from each of the following: Based on the actual value of energy storage demand and the stable value of energy storage facility operation, the correlation coefficient between grid node type conversion and energy storage demand is extracted to obtain the third energy storage correlation coefficient.

5. The method for optimizing the multi-point layout strategy of regional power grid energy storage according to claim 4, characterized in that, Based on the first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient, the energy storage demand of the target area power grid during actual operation is predicted and adjusted to obtain the first energy storage demand value. This process includes the following steps: Combine energy storage layout feature one and energy storage layout feature two into energy storage training feature set one; The first energy storage correlation coefficient, the second energy storage correlation coefficient, and the third energy storage correlation coefficient are combined to form the second set of energy storage features to be trained. Obtain historical energy storage layout schemes and corresponding actual energy storage demand data for the regional power grid. A dynamic prediction model for energy storage demand is established based on historical operating parameters of the regional power grid, historical energy storage demand data, and energy storage training feature set one and energy storage training feature set two. Obtain the current actual operating scenario characteristics of the power grid in the target area; The current operating parameters, current actual operating scenario characteristics, initial energy storage layout scheme, and target area power grid are input into the dynamic prediction model of energy storage demand to obtain the first energy storage demand value by adjusting the energy storage demand of the target area power grid during actual operation.

6. The method for optimizing the multi-point layout strategy of regional power grid energy storage according to claim 5, characterized in that, To derive the second energy storage demand value from the baseline energy storage demand of the target area power grid under a baseline load scenario, the specific steps include: Acquire historical standard operating data of the regional power grid under baseline load scenarios; Establish a benchmark forecasting model for energy storage demand based on historical standard operating data; By collecting data on the load distribution uniformity of the power grid in the target area, the regional load distribution characteristics can be obtained. The target area power grid, initial energy storage layout scheme, regional load distribution characteristics and current operating parameters are input into the energy storage demand benchmark prediction model to obtain the basic value of energy storage demand of the target area power grid, and thus the second energy storage demand value.

7. The method for optimizing the multi-point layout strategy of regional power grid energy storage according to claim 1, characterized in that, The energy storage preprocessing verification conditions for energy storage demand forecasting verification of the target area power grid are selected from the comprehensive energy storage verification conditions, specifically including the following steps: Target energy storage verification conditions were selected from the comprehensive energy storage verification conditions, which were consistent with the load density region and grid node type distribution of the target area power grid, and the energy storage preprocessing verification conditions were obtained.

Images