Molten salt multi-stage energy storage management method and system

Abstract

The invention discloses a fused salt multistage energy storage management method and system, and the method comprises the steps: obtaining the historical load data of a power grid, carrying out the modeling prediction based on the historical load data of the power grid, and obtaining the load prediction data of the power grid; performing clustering analysis on the load prediction data of the power grid, and determining a power grid load stage in the load prediction data; setting a multi-stage energy storage management strategy based on a power grid load stage, and performing simulation operation according to the multi-stage energy storage management strategy; and evaluating the simulation operation result to obtain a multi-stage energy storage management evaluation value, and adjusting a multi-stage energy storage management strategy based on the multi-stage energy storage management evaluation value. By means of the technical means of modeling prediction, clustering analysis, simulation operation and the like, intelligent scheduling and management of the multi-stage energy storage system are achieved, the multi-stage energy storage management strategy is adjusted by evaluating the simulation operation result, the multi-stage energy storage management strategy is optimized, the energy utilization efficiency of the system is improved, and the energy utilization efficiency of the system is improved. And the flexibility and the response capability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage technology, and in particular to a molten salt multi-stage energy storage management method and system. Background Art

[0002] Molten salt multi-stage energy storage is a new type of energy storage technology. It uses molten salt as the energy storage medium and realizes energy storage and release through heat conversion during the energy storage and release process. It is usually composed of multiple cascaded energy storage units and can provide flexible energy storage and release solutions. It is suitable for various application scenarios such as grid peak regulation, smooth output of renewable energy, and emergency backup power supply.

[0003] The traditional method fails to fully consider the capacity utilization of molten salt multi-stage energy storage equipment during different load periods, resulting in energy waste or energy shortage during certain load periods. For the changes in demand during different load periods, the traditional method fails to provide an effective capacity management strategy and cannot maximize the utilization of the capacity of the energy storage equipment. At the same time, the traditional method also fails to fully consider the charging and discharging power management of the molten salt multi-stage energy storage equipment and cannot dynamically adjust the charging and discharging power according to the load demand and the system operating status, resulting in the charging and discharging power being too large or too small in some cases, affecting the stability and efficiency of the system. In addition, the traditional method fails to provide sufficient system flexibility and cannot make timely adjustments according to the system operation status and changes in the external environment, and lacks the ability to respond flexibly to different scenarios. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a molten salt multi-level energy storage management method and system, comprising:

[0005] Obtain historical load data of the power grid, and perform modeling and prediction based on the historical load data of the power grid to obtain load forecast data of the power grid;

[0006] Performing cluster analysis on the load forecast data of the power grid to determine the load phase of the power grid in the load forecast data;

[0007] Set a multi-level energy storage management strategy based on the grid load stage, and perform simulation operation according to the multi-level energy storage management strategy;

[0008] The simulation operation results are evaluated to obtain the multi-level energy storage management evaluation value, and the multi-level energy storage management strategy is adjusted based on the multi-level energy storage management evaluation value.

[0009] Furthermore, the acquisition of historical load data of the power grid and the modeling and prediction based on the historical load data of the power grid to obtain load prediction data of the power grid include:

[0010] Obtain historical load data of the power grid and preprocess the historical load data;

[0011] A data set is constructed based on the preprocessed historical load data, and an initial load forecasting model of the power grid is constructed based on the data set and a preset neural network model;

[0012] The data set is divided into a training set and a test set, and the initial load forecasting model is trained and tested according to the training set and the test set until the initial load forecasting model meets the preset convergence condition, thereby obtaining the load forecasting model of the power grid;

[0013] According to the load forecasting model of the power grid, forecasts are made to obtain the load forecast data of the power grid in the future.

[0014] Furthermore, the cluster analysis of the load forecast data of the power grid to determine the load stage of the power grid in the load forecast data includes:

[0015] Draw a load forecast curve of the power grid according to the load forecast data of the power grid, and extract load curve shape data and average load value of the load forecast curve;

[0016] A load curve data set is formed according to the load curve shape data and the average load value, and k cluster centers of the load curve data set are randomly selected;

[0017] Calculate the Euclidean distance between each load curve data set and the initial cluster center, and divide each load curve data set into a corresponding cluster according to the Euclidean distance between each load curve data set and the initial cluster center;

[0018] Calculate the average value of all load curve data sets in each cluster, and update the cluster center according to the average value of all load curve data sets in each cluster;

[0019] Repeat the above steps until the cluster center no longer changes, obtain several cluster centers, and determine the load curve data segment corresponding to each cluster center;

[0020] Calculate the load average value of each load curve data segment, and obtain the load duration of each load curve data segment;

[0021] The grid load stage in the load forecast data is determined based on the load average value and load duration of each load curve data segment.

[0022] Further, the determining of the grid load stage in the load forecast data based on the load average value and load duration of each load curve data segment includes:

[0023] Obtain the load duration of each load curve data segment, and remove the load curve data segments whose load duration is less than a preset value, and retain the remaining load curve data segments as candidate load curve data segments;

[0024] The load curve data segment with an average load value greater than the preset maximum value is determined as the high load stage of the power grid, the load curve data segment with an average load value less than the preset minimum value is determined as the low load stage of the power grid, and the load curve data segment with an average load value between the preset maximum value and the preset minimum value is determined as the medium load stage of the power grid.

[0025] Furthermore, the multi-level energy storage management strategy is set based on the power grid load stage, and simulation operation is performed according to the multi-level energy storage management strategy, including:

[0026] Obtain the load peak value in the high load stage, the load valley value in the low load stage, and the load peak value and load valley value in the medium load stage, and calculate the load average values ​​corresponding to the high load stage, the low load stage, and the medium load stage;

[0027] The time period containing the load peak value and higher than the load average value in the high load stage is regarded as the high load period, the time period containing the load valley value and lower than the load average value in the low load stage is regarded as the low load period, and the time period containing the load peak value and the load valley value on both sides of the load average value in the medium load stage is regarded as the fluctuating load period;

[0028] Determine the maximum load value and the minimum load value corresponding to each load period respectively, calculate the difference between the maximum load value and the minimum load value corresponding to each load period, and obtain the capacity of the molten salt multi-stage energy storage device corresponding to each load period;

[0029] The average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period and the charging efficiency or discharging efficiency of the molten salt multi-stage energy storage device are determined respectively, and the charging power or discharging power corresponding to each load period is determined based on the average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period and the charging efficiency or discharging efficiency of the molten salt multi-stage energy storage device.

[0030] Further, the determining of the charging power or discharging power corresponding to each load period based on the average load change rate, load valley value and load peak value corresponding to each load period and the charging efficiency or discharging efficiency of the molten salt multi-stage energy storage device includes:

[0031] If the average load change rate is a positive number, the load period corresponds to the discharge power, and the calculation formula for the discharge power is:

[0032] P1=F*L / N,

[0033] Among them, P1 is the discharge power, F is the average load change rate, L is the minimum load valley value, and N is the discharge efficiency of the molten salt multi-stage energy storage device;

[0034] If the average load change rate is negative, the load period corresponds to the charging power, and the charging power calculation formula is:

[0035] P2=F*H / M,

[0036] Among them, P2 is the charging power, F is the average load change rate, H is the maximum load peak, and M is the charging efficiency of the molten salt multi-stage energy storage device.

[0037] Furthermore, the simulation operation results are evaluated to obtain a multi-level energy storage management evaluation value, including:

[0038] Obtaining the working efficiency of each power grid load stage, and evaluating the working efficiency of each power grid load stage by using the assignment method, and calculating the average value of all the assignment results to obtain the working efficiency evaluation value of each power grid load stage;

[0039] The multi-level energy storage management evaluation value is obtained by performing weighted addition calculation based on the work efficiency evaluation value of each grid load stage and the weight corresponding to the grid load stage.

[0040] Furthermore, the adjusting the multi-level energy storage management strategy based on the multi-level energy storage management evaluation value includes:

[0041] The correspondence between the adjustment coefficient and the multi-level energy storage management evaluation value interval is preset, and the correspondence between the adjustment coefficient and the multi-level energy storage management evaluation value interval is associated with a corresponding adjustment coefficient for each multi-level energy storage management evaluation value interval;

[0042] Obtaining a multi-level energy storage management evaluation value, and based on a mapping relationship between a multi-level energy storage management evaluation value interval to which the multi-level energy storage management evaluation value belongs and an adjustment coefficient corresponding to the multi-level energy storage management evaluation value interval is selected as an adjustment coefficient for adjusting the multi-level energy storage management strategy;

[0043] The multi-level energy storage management strategy is adjusted according to the adjustment coefficient to obtain an adjusted multi-level energy storage management strategy, and management is performed according to the adjusted multi-level energy storage management strategy.

[0044] The present invention also provides a molten salt multi-level energy storage management system, comprising:

[0045] The prediction module is used to obtain the historical load data of the power grid, and to perform modeling and prediction based on the historical load data of the power grid to obtain the load prediction data of the power grid;

[0046] An analysis module, used to perform cluster analysis on the load forecast data of the power grid and determine the load stage of the power grid in the load forecast data;

[0047] A setting module, used to set a multi-level energy storage management strategy based on the power grid load stage, and perform simulation operation according to the multi-level energy storage management strategy;

[0048] The adjustment module is used to evaluate the simulation operation results, obtain the multi-level energy storage management evaluation value, and adjust the multi-level energy storage management strategy based on the multi-level energy storage management evaluation value.

[0049] Compared with the prior art, the molten salt multi-stage energy storage management method and system according to the embodiment of the present invention have the following beneficial effects:

[0050] The present invention can realize accurate prediction and classification of power grid load through modeling prediction and cluster analysis, so that the multi-level energy storage system can be flexibly dispatched according to different load stages to improve energy utilization efficiency;

[0051] Based on the load forecast data and the setting of the load stage, the present invention can formulate targeted multi-level energy storage management strategies, including strategies in charge and discharge power control, capacity utilization, etc., so as to realize intelligent scheduling and optimized management of the energy storage system;

[0052] Through simulation operation and evaluation, the present invention can verify the effect of the multi-level energy storage management strategy under different load conditions and ensure the stability and safety of the system under different working conditions;

[0053] The present invention can improve the energy utilization efficiency of the system, reduce energy costs, and promote the large-scale application of renewable energy by optimizing the multi-level energy storage management strategy, thereby improving the economy and sustainability of the system;

[0054] The entire process of the present invention uses technical means such as modeling prediction, cluster analysis and simulation operation to achieve intelligent scheduling and management of multi-level energy storage systems and improve the flexibility and responsiveness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Schematic diagram of the process structure of the molten salt multi-stage energy storage management method in an embodiment of the present invention;

[0056] Figure 2 It is a schematic diagram of the composition of the molten salt multi-stage energy storage management system in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0058] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0059] The terms "second" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined with "second" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0060] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0061] like Figure 1 As shown, in an embodiment of the present application, a molten salt multi-level energy storage management method is provided, including: S100: acquiring historical load data of the power grid, and performing modeling and prediction based on the historical load data of the power grid to obtain load prediction data of the power grid; S200: performing cluster analysis on the load prediction data of the power grid to determine the load stage of the power grid in the load prediction data; S300: setting a multi-level energy storage management strategy based on the load stage of the power grid, and performing simulation operation according to the multi-level energy storage management strategy; S400: evaluating the simulation operation results to obtain a multi-level energy storage management evaluation value, and adjusting the multi-level energy storage management strategy based on the multi-level energy storage management evaluation value.

[0062] Furthermore, the present invention can achieve accurate prediction and classification of power grid loads through modeling prediction and cluster analysis, so that the multi-level energy storage system can be flexibly scheduled according to different load stages to improve energy utilization efficiency; based on load forecast data and load stage settings, the present invention can formulate targeted multi-level energy storage management strategies, including strategies in terms of charging and discharging power control, capacity utilization, etc., so as to achieve intelligent scheduling and optimized management of the energy storage system; through simulation operation and evaluation, the present invention can verify the effect of the multi-level energy storage management strategy under different load conditions to ensure the stability and safety of the system under different working conditions; by optimizing the multi-level energy storage management strategy, the present invention can improve the energy utilization efficiency of the system, reduce energy costs, and promote the large-scale application of renewable energy, thereby improving the economy and sustainability of the system; the entire process of the present invention uses technical means such as modeling prediction, cluster analysis and simulation operation to achieve intelligent scheduling and management of the multi-level energy storage system and improve the flexibility and responsiveness of the system.

[0063] In an embodiment of the present application, a molten salt multi-level energy storage management method is provided, wherein historical load data of a power grid is obtained, and modeling and prediction are performed based on the historical load data of the power grid to obtain load prediction data of the power grid, including: obtaining historical load data of the power grid, and preprocessing the historical load data; constructing a data set according to the preprocessed historical load data, and constructing an initial load prediction model of the power grid based on the data set and a preset neural network model; dividing the data set into a training set and a test set, and training and testing the initial load prediction model according to the training set and the test set until the initial load prediction model meets preset convergence conditions to obtain a load prediction model of the power grid; and performing prediction according to the load prediction model of the power grid to obtain load prediction data for the power grid for a period of time in the future.

[0064] Specifically, the historical load data of the power grid is obtained, and then the data is preprocessed, including data cleaning, missing value processing, outlier processing, smoothing, etc., to ensure the quality and accuracy of the data; the preprocessed historical load data is constructed into a data set suitable for neural network model training, and then based on this data set and the preset neural network model, the initial load forecasting model of the power grid is constructed; the constructed data set is divided into a training set and a test set, and then the initial load forecasting model is trained using the training set, and the model is tested and evaluated using the test set until the model meets the preset convergence conditions, and the final power grid load forecasting model is obtained; the constructed load forecasting model is used to predict the power grid load in the future, and the predicted data is obtained as the final load forecasting result. This process uses a neural network model to learn and predict historical load data, providing a data-driven modeling method for power grid load forecasting.

[0065] In an embodiment of the present application, a molten salt multi-level energy storage management method is provided, wherein cluster analysis is performed on the load forecast data of the power grid to determine the load stage of the power grid in the load forecast data, including: drawing a load forecast curve of the power grid according to the load forecast data of the power grid, and extracting the load curve shape data and the average load value of the load forecast curve; forming a load curve data set according to the load curve shape data and the average load value, and randomly selecting k clustering centers of the load curve data set; calculating the Euclidean distance of each load curve data set to the initial clustering center, and dividing each load curve data set into a corresponding cluster according to the Euclidean distance of each load curve data set to the initial clustering center; calculating the average value of all load curve data sets in each cluster, and updating the clustering center according to the average value of all load curve data sets in each cluster; repeating the above steps until the cluster center no longer changes, obtaining a plurality of clustering centers, and determining the load curve data segment corresponding to each cluster center; calculating the load average value of each load curve data segment, and obtaining the load duration of each load curve data segment; determining the load stage of the power grid in the load forecast data based on the load average value and load duration of each load curve data segment.

[0066] Specifically, draw the load forecast curve of the power grid, then extract the morphological data of the load curve from the forecast curve, such as peaks, troughs, duration, etc., and calculate the average load value; form a data set with the extracted load curve morphological data and average load value, and randomly select k cluster centers from them; calculate the Euclidean distance of each load curve data set to each initial cluster center, and divide each data set into corresponding clusters according to the distance; calculate the average value of all load curve data sets in each cluster, and use these average values ​​as new cluster centers; continuously update the cluster centers through iterative calculations until the cluster centers no longer change, obtain the final several cluster centers, and determine the load curve data segments corresponding to each cluster center; for each load curve data segment, calculate its load average value and obtain its duration; determine the load stage of the power grid in the load forecast data according to the load average value and duration of each load curve data segment. This process determines the different stages of power grid load through cluster analysis of load curve data, providing a basis for formulating targeted multi-level energy storage management strategies.

[0067] In an embodiment of the present application, a molten salt multi-stage energy storage management method is provided, which determines the power grid load stage in the load forecast data based on the load average value and load duration of each load curve data segment, including: obtaining the load duration of each load curve data segment, and eliminating the load curve data segments with a load duration less than a preset value, and retaining the remaining load curve data segments as candidate load curve data segments; determining the load curve data segments with a load average value greater than a preset maximum value as the high load stage of the power grid, determining the load curve data segments with a load average value less than a preset minimum value as the low load stage of the power grid, and determining the load curve data segments with a load average value between the preset maximum value and the preset minimum value as the medium load stage of the power grid.

[0068] Specifically, the duration of each load curve data segment is calculated, and then the data segments with a duration less than the preset value are eliminated, and the remaining data segments are retained as candidate load curve data segments; according to the preset maximum and minimum load values, the remaining candidate load curve data segments are classified: the average load value greater than the preset maximum value is determined as a high load stage, less than the preset minimum value is determined as a low load stage, and between the preset maximum and minimum values ​​is determined as a medium load stage. This step determines the different load stages of the power grid by screening and classifying the load curve data, providing a basis for further load management and optimization.

[0069] In an embodiment of the present application, a molten salt multi-stage energy storage management method is provided, wherein a multi-stage energy storage management strategy is set based on the load stage of the power grid, and a simulation operation is performed according to the multi-stage energy storage management strategy, including: obtaining the load peak value in the high load stage and the load valley value in the low load stage as well as the load peak value and the load valley value in the medium load stage, and calculating the load average values ​​corresponding to the high load stage, the low load stage and the medium load stage; taking the time period containing the load peak value and higher than the load average value in the high load stage as the high load period, taking the time period containing the load valley value and lower than the load average value in the low load stage as the low load period, and taking the load peak value and the load valley value in the medium load stage as the low load period. The time period when the valley values ​​are continuously on both sides of the load average value is regarded as the fluctuating load period; the maximum load value and the minimum load value corresponding to each load period are determined respectively, and the maximum load value corresponding to each load period is calculated by difference with the minimum load value to obtain the capacity of the molten salt multi-stage energy storage device corresponding to each load period; the average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period and the charging efficiency or discharge efficiency of the molten salt multi-stage energy storage device are determined respectively, and the charging power or discharge power corresponding to each load period is determined based on the average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period and the charging efficiency or discharge efficiency of the molten salt multi-stage energy storage device.

[0070] Specifically, the load peak value in the high-load stage, the load valley value in the low-load stage, and the load peak value and load valley value in the medium-load stage are obtained, and their corresponding load average values ​​are calculated; the time period containing the load peak value and higher than the load average value in the high-load stage is taken as the high-load period, the time period containing the load valley value and lower than the load average value in the low-load stage is taken as the low-load period, and the time period in the medium-load stage where the load peak value and the load valley value are continuously on both sides of the load average value is taken as the fluctuating load period. According to the characteristics of the load stage, different time periods are divided into high-load period, low-load period and fluctuating load period; the maximum load value and minimum load value corresponding to each load period are determined respectively, and the maximum load value and the minimum load value corresponding to each load period are compared. The capacity of the molten salt multi-stage energy storage device corresponding to each load period is obtained by calculating the difference between the maximum load value and the minimum load value, and the capacity of the molten salt multi-stage energy storage device corresponding to different load periods is determined; the average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period, and the charging efficiency or discharge efficiency of the molten salt multi-stage energy storage device are determined respectively, and the charging power or discharge power corresponding to each load period is determined based on the average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period, and the charging efficiency or discharge efficiency of the molten salt multi-stage energy storage device. The charging power or discharge power corresponding to each load period is determined by calculating the average load change rate, the lowest load valley value and the highest load peak value, and considering the charging efficiency or discharge efficiency of the energy storage device. This process determines the capacity of the energy storage device and the charging and discharging power corresponding to different load periods by analyzing the load characteristics and fluctuations, combined with the performance parameters of the energy storage device, and provides an important reference for power grid load management.

[0071] In an embodiment of the present application, a molten salt multi-stage energy storage management method is provided, wherein the charging power or discharging power corresponding to each load period is determined based on the average load change rate, load valley value and load peak value corresponding to each load period and the charging efficiency or discharging efficiency of the molten salt multi-stage energy storage device, including: if the average load change rate is a positive number, then the load period is determined to correspond to the discharging power, and the calculation formula of the discharging power is:

[0072] P1=F*L / N,

[0073] Among them, P1 is the discharge power, F is the average load change rate, L is the minimum load valley value, and N is the discharge efficiency of the molten salt multi-stage energy storage device;

[0074] If the average load change rate is negative, the load period corresponds to the charging power, and the charging power calculation formula is:

[0075] P2=F*H / M,

[0076] Among them, P2 is the charging power, F is the average load change rate, H is the maximum load peak, and M is the charging efficiency of the molten salt multi-stage energy storage device.

[0077] In an embodiment of the present application, a molten salt multi-stage energy storage management method is provided, wherein the simulation operation results are evaluated to obtain a multi-stage energy storage management evaluation value, including: obtaining the working efficiency of each power grid load stage, and assigning and evaluating the working efficiency of each power grid load stage by an assignment method, and calculating the average value of all assignment results to obtain the working efficiency evaluation value of each power grid load stage; performing weighted addition calculation according to the working efficiency evaluation value of each power grid load stage and the weight corresponding to the power grid load stage to obtain the multi-stage energy storage management evaluation value.

[0078] Specifically, the work efficiency of each grid load stage is taken and evaluated using the assignment method, which is based on expert opinions; all assignment results are averaged to obtain the work efficiency evaluation value of each grid load stage; the work efficiency evaluation value is weighted and added with the corresponding weight, considering the impact of different load stages on the overall system; finally, the comprehensive evaluation value of multi-level energy storage management is obtained through weighted addition calculation, which helps decision makers understand the impact of different load stages on energy storage management. This process provides a comprehensive evaluation for multi-level energy storage management through the evaluation and weighted calculation of work efficiency, which helps to formulate more effective energy storage management strategies.

[0079] In an embodiment of the present application, a molten salt multi-level energy storage management method is provided, wherein the multi-level energy storage management strategy is adjusted based on the multi-level energy storage management evaluation value, including: presetting an adjustment coefficient-multi-level energy storage management evaluation value interval correspondence relationship, wherein the adjustment coefficient-multi-level energy storage management evaluation value interval correspondence relationship is associated with a corresponding adjustment coefficient for each multi-level energy storage management evaluation value interval; obtaining the multi-level energy storage management evaluation value, and based on a mapping relationship between the multi-level energy storage management evaluation value interval to which the multi-level energy storage management evaluation value belongs within the adjustment coefficient-multi-level energy storage management evaluation value interval correspondence relationship, selecting the adjustment coefficient corresponding to the multi-level energy storage management evaluation value interval as the adjustment coefficient for adjusting the multi-level energy storage management strategy; adjusting the multi-level energy storage management strategy according to the adjustment coefficient to obtain the adjusted multi-level energy storage management strategy, and managing according to the adjusted multi-level energy storage management strategy.

[0080] Specifically, the correspondence between the multi-level energy storage management evaluation value interval and the adjustment coefficient is determined in advance; the multi-level energy storage management evaluation value is obtained from the actual data, which may be the result of the evaluation process described above; according to the interval to which the multi-level energy storage management evaluation value belongs, the corresponding adjustment coefficient is found, and this adjustment coefficient will be used to adjust the multi-level energy storage management strategy; the multi-level energy storage management strategy is adjusted using the selected adjustment coefficient to obtain the adjusted multi-level energy storage management strategy, and management is performed according to the adjusted multi-level energy storage management strategy. This process provides an adaptive adjustment method for multi-level energy storage management by mapping the multi-level energy storage management evaluation value to the adjustment coefficient and using the adjustment coefficient to adjust the strategy, which can flexibly manage the energy storage strategy according to actual conditions.

[0081] like Figure 2 As shown, in an embodiment of the present application, a molten salt multi-level energy storage management system is provided, including: a prediction module, which is used to obtain historical load data of the power grid, and to perform modeling and prediction based on the historical load data of the power grid to obtain load prediction data of the power grid; an analysis module, which is used to perform cluster analysis on the load prediction data of the power grid to determine the load stage of the power grid in the load prediction data; a setting module, which is used to set a multi-level energy storage management strategy based on the load stage of the power grid, and to perform simulation operation according to the multi-level energy storage management strategy; an adjustment module, which is used to evaluate the simulation operation results, obtain a multi-level energy storage management evaluation value, and adjust the multi-level energy storage management strategy based on the multi-level energy storage management evaluation value.

[0082] In summary, an embodiment of the present invention provides a molten salt multi-level energy storage management method and system, which includes: obtaining historical load data of the power grid, and performing modeling and prediction based on the historical load data of the power grid to obtain load prediction data of the power grid; performing cluster analysis on the load prediction data of the power grid to determine the load stage of the power grid in the load prediction data; setting a multi-level energy storage management strategy based on the load stage of the power grid, and performing simulation operation according to the multi-level energy storage management strategy; evaluating the simulation operation results to obtain a multi-level energy storage management evaluation value, and adjusting the multi-level energy storage management strategy based on the multi-level energy storage management evaluation value. The present invention realizes intelligent scheduling and management of multi-level energy storage systems with the help of technical means such as modeling and prediction, cluster analysis and simulation operation, and adjusts the multi-level energy storage management strategy by evaluating the simulation operation results, optimizes the multi-level energy storage management strategy, improves the energy utilization efficiency of the system, and also improves the flexibility and responsiveness of the system.

[0083] Finally, it should be noted that it is obvious that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0084] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0085] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0086] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0087] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A molten salt multi-stage energy storage management method, characterized in that: include: Obtain historical load data of the power grid, and perform modeling and prediction based on the historical load data of the power grid to obtain load forecast data of the power grid; Performing cluster analysis on the load forecast data of the power grid to determine the load phase of the power grid in the load forecast data; Set a multi-level energy storage management strategy based on the grid load stage, and perform simulation operation according to the multi-level energy storage management strategy; The simulation operation results are evaluated to obtain the multi-level energy storage management evaluation value, and the multi-level energy storage management strategy is adjusted based on the multi-level energy storage management evaluation value.

2. A molten salt multi-stage energy storage management method according to claim 1, characterized in that: The acquiring of historical load data of the power grid and performing modeling and prediction based on the historical load data of the power grid to obtain load prediction data of the power grid includes: Obtain historical load data of the power grid and preprocess the historical load data; A data set is constructed based on the preprocessed historical load data, and an initial load forecasting model of the power grid is constructed based on the data set and a preset neural network model; The data set is divided into a training set and a test set, and the initial load forecasting model is trained and tested according to the training set and the test set until the initial load forecasting model meets the preset convergence condition, thereby obtaining the load forecasting model of the power grid; According to the load forecasting model of the power grid, forecasts are made to obtain the load forecast data of the power grid in the future.

3. A molten salt multi-stage energy storage management method according to claim 2, characterized in that: The cluster analysis of the load forecast data of the power grid to determine the load stage of the power grid in the load forecast data includes: Draw a load forecast curve of the power grid according to the load forecast data of the power grid, and extract load curve shape data and average load value of the load forecast curve; A load curve data set is formed according to the load curve shape data and the average load value, and k cluster centers of the load curve data set are randomly selected; Calculate the Euclidean distance between each load curve data set and the initial cluster center, and divide each load curve data set into a corresponding cluster according to the Euclidean distance between each load curve data set and the initial cluster center; Calculate the average value of all load curve data sets in each cluster, and update the cluster center according to the average value of all load curve data sets in each cluster; Repeat the above steps until the cluster center no longer changes, obtain several cluster centers, and determine the load curve data segment corresponding to each cluster center; Calculate the load average value of each load curve data segment, and obtain the load duration of each load curve data segment; The grid load stage in the load forecast data is determined based on the load average value and load duration of each load curve data segment.

4. A molten salt multi-stage energy storage management method according to claim 3, characterized in that: The step of determining the grid load stage in the load forecast data based on the load average value and load duration of each load curve data segment includes: Obtain the load duration of each load curve data segment, and remove the load curve data segments whose load duration is less than a preset value, and retain the remaining load curve data segments as candidate load curve data segments; The load curve data segment with an average load value greater than the preset maximum value is determined as the high load stage of the power grid, the load curve data segment with an average load value less than the preset minimum value is determined as the low load stage of the power grid, and the load curve data segment with an average load value between the preset maximum value and the preset minimum value is determined as the medium load stage of the power grid.

5. A molten salt multi-stage energy storage management method according to claim 4, characterized in that: The multi-level energy storage management strategy is set based on the power grid load stage, and simulation operation is performed according to the multi-level energy storage management strategy, including: Obtain the load peak value in the high load stage, the load valley value in the low load stage, and the load peak value and load valley value in the medium load stage, and calculate the load average values ​​corresponding to the high load stage, the low load stage, and the medium load stage; The time period containing the load peak value and higher than the load average value in the high load stage is regarded as the high load period, the time period containing the load valley value and lower than the load average value in the low load stage is regarded as the low load period, and the time period containing the load peak value and the load valley value on both sides of the load average value in the medium load stage is regarded as the fluctuating load period; Determine the maximum load value and the minimum load value corresponding to each load period respectively, calculate the difference between the maximum load value and the minimum load value corresponding to each load period, and obtain the capacity of the molten salt multi-stage energy storage device corresponding to each load period; The average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period and the charging efficiency or discharging efficiency of the molten salt multi-stage energy storage device are determined respectively, and the charging power or discharging power corresponding to each load period is determined based on the average load change rate, the lowest load valley value and the highest load peak value corresponding to each load period and the charging efficiency or discharging efficiency of the molten salt multi-stage energy storage device.

6. A molten salt multi-stage energy storage management method according to claim 5, characterized in that: The determining of the charging power or discharging power corresponding to each load period based on the average load change rate, load valley value and load peak value corresponding to each load period and the charging efficiency or discharging efficiency of the molten salt multi-stage energy storage device includes: If the average load change rate is a positive number, the load period corresponds to the discharge power, and the calculation formula for the discharge power is: P1=F*L / N, Among them, P1 is the discharge power, F is the average load change rate, L is the minimum load valley value, and N is the discharge efficiency of the molten salt multi-stage energy storage device; If the average load change rate is negative, the load period corresponds to the charging power, and the charging power calculation formula is: P2=F*H / M, Among them, P2 is the charging power, F is the average load change rate, H is the maximum load peak, and M is the charging efficiency of the molten salt multi-stage energy storage device.

7. A molten salt multi-stage energy storage management method according to claim 5, characterized in that: The simulation operation results are evaluated to obtain a multi-level energy storage management evaluation value, including: Obtaining the working efficiency of each power grid load stage, and evaluating the working efficiency of each power grid load stage by using the assignment method, and calculating the average value of all the assignment results to obtain the working efficiency evaluation value of each power grid load stage; The multi-level energy storage management evaluation value is obtained by performing weighted addition calculation based on the work efficiency evaluation value of each grid load stage and the weight corresponding to the grid load stage.

8. A molten salt multi-stage energy storage management method according to claim 7, characterized in that: The adjusting of the multi-level energy storage management strategy based on the multi-level energy storage management evaluation value includes: The correspondence between the adjustment coefficient and the multi-level energy storage management evaluation value interval is preset, and the correspondence between the adjustment coefficient and the multi-level energy storage management evaluation value interval is associated with a corresponding adjustment coefficient for each multi-level energy storage management evaluation value interval; Obtaining a multi-level energy storage management evaluation value, and based on a mapping relationship between a multi-level energy storage management evaluation value interval to which the multi-level energy storage management evaluation value belongs and an adjustment coefficient corresponding to the multi-level energy storage management evaluation value interval is selected as an adjustment coefficient for adjusting the multi-level energy storage management strategy; The multi-level energy storage management strategy is adjusted according to the adjustment coefficient to obtain an adjusted multi-level energy storage management strategy, and management is performed according to the adjusted multi-level energy storage management strategy.

9. A molten salt multi-level energy storage management system, characterized in that: include: The prediction module is used to obtain the historical load data of the power grid, and to perform modeling and prediction based on the historical load data of the power grid to obtain the load prediction data of the power grid; An analysis module, used to perform cluster analysis on the load forecast data of the power grid and determine the load stage of the power grid in the load forecast data; A setting module, used to set a multi-level energy storage management strategy based on the power grid load stage, and perform simulation operation according to the multi-level energy storage management strategy; The adjustment module is used to evaluate the simulation operation results, obtain the multi-level energy storage management evaluation value, and adjust the multi-level energy storage management strategy based on the multi-level energy storage management evaluation value.

Images