Energy management method and system for lithium battery energy storage box

Abstract

The application provides an energy management method and system of a lithium battery energy storage box, relates to the technical field of intelligent management, obtains a load data set based on historical energy storage record data sets of a first lithium battery energy storage box, performs clustering to obtain N load clustering results, obtains N power intervals in combination with power data set analysis, builds a load-power mapping model, performs interval optimization using an optimization algorithm to obtain N power optimization values, and manages the first lithium battery energy storage box, thereby solving the technical problem that, in the energy management of the lithium battery energy storage box in the prior art, due to inadequate consideration of load and power matching, overload affects the energy supply time limit or no load causes energy loss, and energy scheduling is not accurate enough. By analyzing the mapping relationship between the load and the power, performing optimal power optimization, and modeling for adaptive adjustment, the load and power matching degree in the energy scheduling process is improved, and accurate and reasonable energy scheduling is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent management, and particularly relates to an energy management method and system for a lithium battery energy storage box. BACKGROUND

[0002] The energy management of the lithium battery energy storage box is performed to guarantee the efficient and stable operation of the energy supply system, and the pros and cons of the energy management affect the optimized and safe scheduling of the energy. In view of the problems of unstable load and peak-valley difference in the energy supply process, reasonable planning is performed to avoid the problems, so as to guarantee the comprehensive utilization efficiency of the energy.

[0003] Nowadays, the energy scheduling management is mainly performed by establishing a special energy scheduling management system, but the factors considered are mainly the energy supply and demand configuration problems, and some details defects existing in the management process are ignored, so as to affect the energy scheduling effect and further optimization and improvement are needed.

[0004] In the prior art, in the energy management of the lithium battery energy storage box, the load and power matching is not considered, which leads to overload affecting the energy supply time limit or no-load causing energy loss, so that the energy scheduling is not accurate enough. SUMMARY

[0005] The present application provides an energy management method and system for a lithium battery energy storage box, which is used to solve the technical problem that in the energy management of the lithium battery energy storage box, the load and power matching is not considered, which leads to overload affecting the energy supply time limit or no-load causing energy loss, so that the energy scheduling is not accurate enough.

[0006] In view of the above problems, the present application provides an energy management method and system for a lithium battery energy storage box.

[0007] In a first aspect, the present application provides an energy management method for a lithium battery energy storage box, which comprises:

[0008] According to the data acquisition device, a historical energy storage record data set of a first lithium battery energy storage box is acquired;

[0009] According to the historical energy storage record data set, an energy storage load data set and a power data set are acquired by analysis;

[0010] The energy storage load data set is clustered to obtain N load clustering results;

[0011] Based on the N load clustering results, the N power intervals are obtained by analyzing the power data set, wherein the N load clustering results correspond to the N power intervals;

[0012] According to the N load clustering results and the N power intervals, a load-power mapping model is obtained;

[0013] Based on the load-power mapping model, an optimization algorithm is used to optimize the N power intervals respectively, to obtain N power optimal values, and the first lithium battery energy storage tank is managed by the N power optimal values.

[0014] In a second aspect, the present application provides an energy management system of a lithium battery energy storage tank, the system comprising:

[0015] A data acquisition module is configured to acquire a historical energy storage record data set of a first lithium battery energy storage tank according to the data acquisition device;

[0016] A data analysis module is configured to analyze the historical energy storage record data set to obtain an energy storage load data set and a power data set;

[0017] A data clustering module is configured to cluster the energy storage load data set to obtain N load clustering results;

[0018] A clustering result analysis module is configured to analyze the N load clustering results from the power data set to obtain N power intervals, wherein the N load clustering results correspond to the N power intervals;

[0019] A model acquisition module is configured to obtain a load-power mapping model according to the N load clustering results and the N power intervals;

[0020] An optimization management module is configured to optimize the N power intervals respectively based on the load-power mapping model by using an optimization algorithm, to obtain N power optimal values, and to manage the first lithium battery energy storage tank by the N power optimal values.

[0021] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0022] The energy management method of the lithium battery energy storage box provided by the embodiment of the application comprises the following steps: acquiring historical energy storage record data sets of a first lithium battery energy storage box according to a data acquisition device, and analyzing and acquiring energy storage load data sets and power data sets; clustering the energy storage load data sets to obtain N load clustering results, and analyzing the N load clustering results in combination with the power data sets to obtain N power intervals corresponding to the N load clustering results; obtaining a load-power mapping model according to the N load clustering results and the N power intervals, respectively optimizing the N power intervals by using an optimization algorithm to obtain N power optimal values, and managing the first lithium battery energy storage box by using the N power optimal values. The technical problem that in the prior art, due to the lack of consideration of load-power matching in energy management of a lithium battery energy storage box, overloading affects the energy supply time limit or idling causes energy loss, and energy scheduling is not accurate enough is solved. The mapping relationship between load and power is analyzed, optimal power optimization is performed, and modeling is performed for adaptive adjustment, so as to improve the load-power matching degree in the energy scheduling process, and realize accurate and reasonable scheduling of energy. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 An energy management method flowchart of a lithium battery energy storage box is provided for the application.

[0024] Figure 2 An N load clustering result acquisition flowchart in an energy management method of a lithium battery energy storage box is provided for the application.

[0025] Figure 3 An N power optimal value optimization flowchart in an energy management method of a lithium battery energy storage box is provided for the application.

[0026] Figure 4 An energy management system structure diagram of a lithium battery energy storage box is provided for the application.

[0027] Legend of reference signs: data acquisition module 11, data analysis module 12, data clustering module 13, clustering result analysis module 14, model acquisition module 15, and optimization management module 16. DETAILED DESCRIPTION

[0028] The application provides an energy management method and system for a lithium battery energy storage box. Historical energy storage record data is collected, the mapping relationship between the load and power distribution is analyzed, and then an optimal power distribution parameter under different loads is determined by using an optimization analysis algorithm. Finally, a load adaptive adjustment model is trained and constructed. In addition, a load test scheme is designed to detect the model, so as to achieve reasonable management and scheduling based on energy supply and demand, thereby solving the technical problem that in the prior art, due to the lack of consideration of load and power matching in the energy management of the lithium battery energy storage box, overload affects the energy supply time limit or no-load causes energy loss, resulting in inaccurate energy scheduling.

[0029] Embodiment 1

[0030] As shown in Figure 1 The application provides an energy management method for a lithium battery energy storage box. The method is applied to an energy management system for a lithium battery energy storage box. The system is in communication connection with a data collection device. The method comprises the following steps:

[0031] Step S100: According to the data collection device, historical energy storage record data set of the first lithium battery energy storage box is obtained.

[0032] Specifically, the energy management of the lithium battery energy storage box is performed to ensure the efficient and stable operation of the energy supply system. The quality of the energy management affects the optimized and safe scheduling of the energy. The problems of unstable load and large peak-valley difference in the energy supply process are reasonably planned to avoid them, so as to ensure the comprehensive utilization efficiency of the energy. The energy management method for the lithium battery energy storage box provided by the application is applied to the energy management system. The energy management system is a general control system for energy scheduling management. The system is in communication connection with the data collection device. The data collection device is an auxiliary collection device for obtaining the related demand information of the lithium battery energy storage box.

[0033] Specifically, the first lithium battery energy storage box is a target energy storage box to be subjected to energy scheduling and distribution management. A predetermined time interval, i.e., a time limit range for data collection, is set. Based on the predetermined time interval, the historical energy storage data of the first lithium battery energy storage box is collected, including load equipment and energy supply state. The collected data is identified based on the mapping time node of the data, and the data is sequentially arranged based on the time sequence to generate the historical energy storage record data set. The historical energy storage record data set is used as a reference basis for energy scheduling and operation analysis of the first lithium battery, so as to ensure the consistency of the subsequent analysis results and the first lithium battery energy storage box.

[0034] Step S200: According to the historical energy storage record data set, the energy storage load data set and the power data set are obtained by analysis.

[0035] Step S300: clustering the energy storage load data set to obtain N load clustering results;

[0036] Specifically, the historical energy storage record data of the first lithium battery energy storage box is obtained, each historical energy storage record data is subjected to load correlation part identification and extraction, the extracted data is integrated and regularized to determine a plurality of energy storage load data as the energy storage load data set, the energy storage load data set has the identification of load equipment and load specifications; the execution data in the load energy supply process is determined to determine the allocated power corresponding to the energy storage load, and the power data is integrated as the power data set of the first lithium battery energy storage box, wherein the energy storage load data set and the power data set are mapped and corresponded. Further, the mapping relationship between the energy storage load data set and the power data set is analyzed, the K-means clustering method is used to perform clustering analysis processing on the energy storage load data set, the N load clustering results are generated, and the targeted class level optimal power distribution analysis is performed based on the N load clustering results, thereby effectively improving the analysis efficiency on the basis of ensuring the actual matching of the analysis results.

[0037] Further, as shown in Figure 2 The energy storage load data set is clustered to obtain N load clustering results, and step S300 of the present application further includes:

[0038] Step S310: performing positive sequence processing on the energy storage load data set to obtain a serialized load data set;

[0039] Step S320: determining a K-value clustering interval according to the serialized load data set, wherein K is a positive integer greater than or equal to 2;

[0040] Step S330: performing optimization based on the K-value clustering interval to obtain a first K value;

[0041] Step S340: clustering the energy storage load data set according to the first K value to obtain N load clustering results.

[0042] Further, the K-value clustering interval is optimized to obtain a first K value, and step S330 of the present application further includes:

[0043] Step S331: obtaining a first sample quantization index by performing sample size analysis on the serialized load data set;

[0044] Step S332: taking the first sample quantization index as a constraint condition for optimization of the K-value clustering interval to determine a K-value granularity;

[0045] Step S333: performing optimization in the K-value clustering interval with the K-value granularity to determine the first K value.

[0046] Specifically, the energy storage load data set is clustered, specifically, the data load value is measured and corrected based on the energy storage load data set, and then the positive sequence processing is performed, that is, the load values are sorted from large to small, and the order of the corresponding data of the energy storage load data set is adjusted for the sorting result, and the obtained positive sequence data is taken as the serialized load data set. Based on the serialized load data set, the initial sequence node and the end sequence node are determined, the overall data value interval is determined as the K-value clustering interval. The interval is divided in the K-value clustering interval, and a plurality of clustering item numbers, that is, the number of clustering intervals, are determined as the first K-value, wherein the first K-value is a positive integer greater than or equal to 2.

[0047] Specifically, the data value of the serialized load data set is measured to determine the sample size, that is, the number of sample data, and the first sample quantization index, that is, the size base representing the sample size, is determined by analyzing and converting the sample size. For example, a multi-level sample quantization index is defined, each level corresponds to a different sample size interval, and the sample size is mapped and attributed to the interval. The level corresponding to the attribution interval is taken as the first sample quantization index. The K-value clustering interval is optimized and constrained based on the first sample quantization index, wherein the higher the first sample quantization index, the larger the sample size, and the larger the clustering data size in the single item clustering interval. The K-value clustering interval is attributed to the data item number to determine the single interval attribution data size that is adapted to the K-value clustering interval as the K-value granularity. Based on the K-value granularity, the best clustering interval number is determined as the first K-value by optimizing the K-value clustering interval. The clustering interval is planned by the sample size to ensure the optimality of the determined clustering interval number and to fit the current clustering situation.

[0048] Further, based on the first K-value, K data are randomly extracted from the energy storage load data set as preselected clustering centers, the distance between each data in the energy storage load data set and each preselected clustering center is calculated, and the energy storage load data set is assigned to the preselected clustering center based on the nearest principle to complete the primary clustering division. Further, the clustering center is reselected based on the primary division result, the data measurement attribution is reperformed, and the process is repeated multiple times until the termination clustering condition is met, for example, the clustering center does not change. The current clustering attribution result is taken as the N load clustering result. The data is divided by K-means clustering, which can simply and efficiently realize the attribution division of the energy storage load data set.

[0049] Step S400: based on the N load clustering results, analyze the power dataset to obtain N power intervals, wherein the N load clustering results correspond to the N power intervals;

[0050] Specifically, based on the N load clustering results, the power dataset is mapped and corresponded, for each load clustering result, the energy storage load data contained is extracted, the corresponding power data in the power dataset is mapped and extracted, the extracted power data is sorted from small to large, the head and tail power data is extracted as the critical limit power, the corresponding power interval is determined, the N load clustering results are analyzed and determined respectively to obtain the N power intervals, wherein the N load clustering results correspond to the N power intervals. Further, based on the N load clustering results and the N power intervals, the optimal power distribution parameters under different loads can be analyzed and determined.

[0051] Step S500: according to the N load clustering results and the N power intervals, a load-power mapping model is obtained;

[0052] Specifically, the N load clustering results and the N power intervals are mapped and associated, and then the data association and connection within the single clustering result are performed respectively, which are used as training sample data. Preferably, the training sample data is screened to exclude data deviating from the main mapping rule, so as to ensure data accuracy and improve subsequent training effect. Based on the training sample data, the neural network is trained to generate the load-power mapping model. Preferably, the training sample data can be divided to determine the training set and the test set for training and testing the model. When the output accuracy of the determined model does not meet the standard, the sample division ratio or sample content is adjusted, and the training and testing are performed again until the output accuracy of the model is qualified. Based on the load-power mapping model, the optimal power attribution analysis of different loads can be quickly performed.

[0053] Step S600: based on the load-power mapping model, an optimization algorithm is used to optimize the N power intervals respectively to obtain N power optimal values, and the first lithium battery energy storage box is managed by using the N power optimal values.

[0054] Further, after obtaining the N power optimal values, step S600 of the application further includes:

[0055] Step S610-1: obtain the power data source corresponding to the power dataset, wherein each power data source corresponds to a lithium battery energy storage element;

[0056] Step S620-1: grouping the power dataset based on the power data source, obtaining M power data groups;

[0057] Step S630-1: taking the M power data groups as M adaptive variables, taking the total value of the N power optimal values as the adaptive target, and outputting N groups of power adaptive results based on the M adaptive variables.

[0058] Further, the output of the N groups of power adaptive results based on the M adaptive variables, the step S630-1 of the application further comprises:

[0059] Step S631-1: building a load adaptive adjustment model based on the N groups of power adaptive results;

[0060] Step S632-1: obtaining real-time power data of the first lithium battery energy storage box;

[0061] Step S633-1: inputting the real-time power data into the load adaptive adjustment model, and outputting a first adaptive adjustment result according to the load adaptive adjustment model, wherein the first adaptive adjustment result is load data based on the real-time power data;

[0062] Step S634-1: adjusting the load of the first lithium battery energy storage box according to the first adaptive adjustment result.

[0063] Further, the step S631-1 of the application further comprises:

[0064] Step S6311-1: obtaining a test sample dataset, wherein the test sample dataset is a load-power sample dataset;

[0065] Step S6312-1: inputting the load-power sample dataset into the load adaptive adjustment model for testing, and obtaining a model test result;

[0066] Step S6313-1: analyzing the model test result to obtain an error test coefficient and a stability test coefficient;

[0067] Step S6314-1: obtaining a first optimization instruction based on the error test coefficient and the stability test coefficient, and optimizing the load adaptive adjustment model according to the first optimization instruction.

[0068] Specifically, further, the optimization algorithm is embedded in the load-power mapping model, and the N power intervals are optimized to determine the optimal power allocation parameters under different loads. Wherein, the optimization algorithm can be an adaptive algorithm for the current scenario, without specific limitation requirements, for example, based on simulated annealing algorithm, multiple power data correction iterations are performed until the iteration termination condition is reached, the current best power is determined as power optimal, and the N power optimal values of the N power intervals are determined respectively.

[0069] Further, trace the power data set, specifically, according to the data collection time, collection method, collection place, etc., track and analyze the corresponding data collection components, i.e. the lithium battery energy storage elements, map and integrate the data trace results to generate the power data source, i.e. the data generating components corresponding to each power data, and each power data source corresponds to a lithium battery energy storage element. The difference of the lithium battery energy storage element leads to the difference of the corresponding power, for example, the adaptive power for different loads is different, the load data corresponding to different power conditions is different, and the condition is refined and analyzed, which can further improve the optimization of the final power allocation. The power data source is used as a division standard, and the same power data source, i.e. the same lithium battery energy storage element corresponding to multiple power data, is determined according to the power data set, and the power data is divided and attributed to generate the M power data groups, wherein M is the same as the lithium battery energy storage element. The M power data groups are used as M adaptive variables, and the total value of the N power optimal values is used as the adaptive target to determine N*M configuration results to determine the optimal power allocation parameters corresponding to each data under different loads.

[0070] Specifically, the N groups of adaptive results are obtained, any group of results includes a power optimal value and a plurality of adjustable power data mapped correspondingly. Multiple adjustable power data are used as hierarchical identification data, and the corresponding power optimal value is used as hierarchical decision data to determine N adjustment groups, which are used as sample data for neural network training to generate the load adaptive adjustment model. Based on the load adaptive adjustment model, the optimal power adaptability adjustment configuration of different loads can be directly performed, and the objectivity and accuracy of the adjustment result are guaranteed.

[0071] Specifically, the load adaptive adjustment model is detected based on a load test scheme. Through data statistics, multiple groups of energy supply sample data are determined, data representation methods are adjusted, multiple load-power sequences are generated as the test sample data set. The load-power sample data set is input into the load adaptive adjustment model, and the model analysis outputs power adjustment data, i.e., the model test result. Based on the model test result, the analysis accuracy of the load adaptive adjustment model is evaluated, sample data analysis is performed, power adaptability load data is determined, and the model test result is corrected. Based on the correction result, data adjustment deviation is determined, the error test coefficient is generated, and the data adjustment deviation is proportional to the error test coefficient. The error test coefficient is the representation data of the adjustment deviation. Further, based on the correction result, the frequency of the deviation adjustment data is determined, and the stability test coefficient is generated. The generation method of the stability test coefficient is the same as that of the error test coefficient. The stability test coefficient is proportional to the frequency of the deviation adjustment data, and the stability test coefficient is the representation data of the model stability analysis state. Further, error test coefficient thresholds and stability test coefficient thresholds are configured, and it is judged whether the error test coefficient and the stability test coefficient meet the corresponding test coefficient thresholds. When the error test coefficient and the stability test coefficient do not meet the corresponding test coefficient thresholds, it indicates that the model running mechanism is abnormal and optimization is necessary, and the first optimization instruction, i.e., the start instruction of model optimization, is generated. With the reception of the first optimization instruction, the load adaptive adjustment model is optimized and adjusted. For example, the test sample data can be re-screened for secondary training. Through model running mechanism analysis and evaluation, the abnormal output result caused by the limitation of the model function is avoided.

[0072] Further, the real-time power data of the first lithium battery is collected, the real-time power data is input into the load adaptive adjustment model, data matching analysis and mapping are performed, the adaptability load data of the real-time power data is determined as the first adaptive adjustment result, and the first adaptive adjustment result is output. The load of the first lithium battery energy storage box is determined, the first lithium battery energy storage box is adjusted based on the first adaptive adjustment result, and optimal energy supply is achieved.

[0073] Further, as shown in Figure 3 The step S600 of the present application further includes:

[0074] Step S610-2: Obtain the parameter configuration of the first lithium battery energy storage box, wherein the parameter configuration includes energy storage battery group parameters, energy storage voltage parameters, and energy storage power supply parameters.

[0075] Step S620-2: performing power loss analysis according to the energy storage battery pack parameter, the energy storage voltage parameter and the energy storage power supply parameter, to obtain a first rated power loss;

[0076] Step S630-2: optimizing the N power values according to the first rated power loss, to output N secondary power values.

[0077] Specifically, in the operation process of the first lithium battery energy storage box, there will inevitably be a certain power loss based on multiple influencing factors. To ensure the accuracy of the final load analysis, further optimization and adjustment need to be performed on the power loss. The energy storage battery pack parameter, the energy storage voltage parameter and the energy storage power supply parameter of the first lithium battery energy storage box are collected. Due to the energy scheduling response speed, voltage and current fluctuation and other conditions, there is a power loss. Based on the above parameters, power analysis is performed to determine the first rated power loss. For example, power measurement can be performed based on standard configuration parameter data, deviation analysis is performed on the current power data, and the power difference is taken as the first rated power loss. Based on the first rated power loss, the adjustment direction and adjustment scale are determined, and the N power values are adjusted and optimized respectively to generate the N secondary power values. Through loss analysis and adjustment, the idealization of the determined power values can be further improved, and the scene matching degree can be ensured.

[0078] Embodiment 2

[0079] Based on the same inventive concept as the energy management method of one lithium battery energy storage box in the foregoing embodiments, as shown in Figure 4 The present application provides an energy management system of a lithium battery energy storage box, which comprises:

[0080] A data collection module 11 is configured to obtain historical energy storage record data set of a first lithium battery energy storage box according to the data collection device;

[0081] A data analysis module 12 is configured to analyze the historical energy storage record data set to obtain energy storage load data set and power data set;

[0082] A data clustering module 13 is configured to cluster the energy storage load data set to obtain N load clustering results;

[0083] A clustering result analysis module 14 is configured to analyze the N load clustering results from the power data set to obtain N power intervals, wherein the N load clustering results correspond to the N power intervals;

[0084] The model obtaining module 15 is configured to obtain a load-power mapping model according to the N load clustering results and the N power intervals.

[0085] The optimization management module 16 is configured to perform optimization on the N power intervals respectively based on the load-power mapping model by using an optimization algorithm, to obtain N power optimization values, and to manage the first lithium battery energy storage tank by using the N power optimization values.

[0086] Further, the system further comprises:

[0087] The data processing module is configured to perform positive sequence processing on the energy storage load data set to obtain a serialized load data set.

[0088] The clustering interval determination module is configured to determine a K-value clustering interval according to the serialized load data set, where K is a positive integer greater than or equal to 2.

[0089] The interval optimization module is configured to perform optimization based on the K-value clustering interval to obtain a first K-value.

[0090] The clustering result obtaining module is configured to perform clustering on the energy storage load data set according to the first K-value to obtain N load clustering results.

[0091] Further, the system further comprises:

[0092] The sample amount analysis module is configured to obtain a first sample quantization index by performing sample amount analysis on the serialized load data set.

[0093] The granularity determination module is configured to determine a K-value granularity by taking the first sample quantization index as a constraint condition for optimization of the K-value clustering interval.

[0094] The clustering interval optimization module is configured to perform optimization in the K-value clustering interval based on the K-value granularity to determine the first K-value.

[0095] Further, the system further comprises:

[0096] The data source obtaining module is configured to obtain power data sources corresponding to the power data set, where each power data source corresponds to a lithium battery energy storage element.

[0097] The data grouping module is configured to group the power data set based on the power data sources to obtain M power data groups.

[0098] An adaptive analysis module is configured to take the M power data groups as M adaptive variables, take a total value of the N power optimal values as an adaptive target, and output N groups of power adaptive results based on the M adaptive variables.

[0099] Further, the system further comprises:

[0100] A parameter configuration acquisition module is configured to acquire a parameter configuration of the first lithium battery energy storage box, wherein the parameter configuration comprises energy storage battery group parameters, energy storage voltage parameters, and energy storage power supply parameters.

[0101] A loss analysis module is configured to perform power loss analysis according to the energy storage battery group parameters, the energy storage voltage parameters, and the energy storage power supply parameters, and obtain a first rated power loss.

[0102] A loss optimization module is configured to optimize the N power optimal values according to the first rated power loss, and output N secondary power optimal values.

[0103] Further, the system further comprises:

[0104] A model building module is configured to build a load adaptive adjustment model by using the N groups of power adaptive results.

[0105] A real-time power data acquisition module is configured to acquire real-time power data of the first lithium battery energy storage box.

[0106] An adjustment result output module is configured to input the real-time power data into the load adaptive adjustment model, and output a first adaptive adjustment result according to the load adaptive adjustment model, wherein the first adaptive adjustment result is load data based on the real-time power data.

[0107] A load adjustment module is configured to adjust a load of the first lithium battery energy storage box according to the first adaptive adjustment result.

[0108] Further, the system further comprises:

[0109] A sample acquisition module is configured to acquire a test sample data set, wherein the test sample data set is a load-power sample data set.

[0110] A model test module is configured to input the load-power sample data set into the load adaptive adjustment model for testing, and acquire a model test result.

[0111] a coefficient obtaining module configured to analyze the model test result to obtain an error checking coefficient and a stability checking coefficient;

[0112] a model optimizing module configured to obtain a first optimizing instruction based on the error checking coefficient and the stability checking coefficient, and optimize the load self-adapting adjusting model according to the first optimizing instruction.

[0113] The person skilled in the art can clearly understand the energy management method and system of the lithium battery energy storage box in the embodiment according to the foregoing detailed description of the energy management method of the lithium battery energy storage box. As the device disclosed in the embodiment corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part can be referred to the method part.

[0114] The above description of disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the present application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for energy management of a lithium battery energy storage bank, the method comprising: The method is applied to an energy management system of a lithium battery energy storage box, the system is in communication connection with a data acquisition device, and the method comprises: ​ According to the data acquisition device, a historical energy storage record data set of a first lithium battery energy storage box is acquired; According to the historical energy storage record data set, an energy storage load data set and a power data set are acquired through analysis; The energy storage load data set is clustered to obtain N load clustering results; Based on the N load clustering results, the power data set is analyzed to obtain N power intervals, wherein the N load clustering results correspond to the N power intervals; According to the N load clustering results and the N power intervals, a load-power mapping model is obtained; Based on the load-power mapping model, an optimization algorithm is used to optimize the N power intervals respectively to obtain N power optimal values, and the first lithium battery energy storage box is managed by using the N power optimal values; After the N power optimal values are obtained, the method further comprises: A power data source corresponding to the power data set is acquired, wherein each power data source corresponds to a lithium battery energy storage element; Based on the power data source, the power data set is grouped to obtain M power data groups; The M power data groups are used as M adaptive variables, a total power value in the N power optimal values is used as an adaptive target, and N groups of power adaptive results based on the M adaptive variables are outputted; A load self-adaptive adjustment model is built based on the N groups of power adaptive results; Real-time power data of the first lithium battery energy storage box is acquired; The real-time power data is inputted into the load self-adaptive adjustment model, and a first self-adaptive adjustment result is outputted according to the load self-adaptive adjustment model, wherein the first self-adaptive adjustment result is load data based on the real-time power data; The load of the first lithium battery energy storage box is adjusted according to the first self-adaptive adjustment result.

2. The method of claim 1, wherein, The method for clustering the energy storage load data set to obtain N load clustering results comprises: The energy storage load data set is subjected to positive sequence processing to obtain a sequence load data set; According to the sequence load data set, a K-value clustering interval is determined, wherein K is a positive integer greater than or equal to 2; Based on the K-value clustering interval, a first K value is obtained through optimization; According to the first K value, the energy storage load data set is clustered to obtain N load clustering results.

3. The method of claim 2, wherein, Based on the K-value clustering interval, a first K value is obtained through optimization, which comprises: A first sample quantization index is obtained through sample quantity analysis of the sequence load data set; The first sample quantization index is used as a constraint condition for optimization of the K-value clustering interval to determine a K-value granularity; The K-value granularity is used to optimize the K-value clustering interval to determine the first K value.

4. The method of claim 1, wherein, The method further comprises: A parameter configuration of the first lithium battery energy storage box is acquired, wherein the parameter configuration comprises energy storage battery group parameters, energy storage voltage parameters and energy storage power supply parameters; Perform power loss analysis according to the energy storage battery parameters, the energy storage voltage parameters and the energy storage power parameters, and obtain a first rated power loss; Optimize the N power values according to the first rated power loss, and output N secondary power values.

5. The method of claim 1, wherein, The method further comprises: Obtaining a test sample data set, wherein the test sample data set is a load-power sample data set; Inputting the load-power sample data set into the load adaptive adjustment model for testing, and obtaining a model test result; Analyzing the model test result to obtain an error test coefficient and a stability test coefficient; Based on the error test coefficient and the stability test coefficient, a first optimization instruction is obtained, and the load adaptive adjustment model is optimized according to the first optimization instruction.

6. An energy management system for a lithium battery energy storage tank, the system comprising: The system is in communication connection with a data acquisition device, and the system comprises: A data acquisition module, which is used to obtain a historical energy storage record data set of a first lithium battery energy storage box according to the data acquisition device; A data analysis module, which is used to analyze the historical energy storage record data set to obtain an energy storage load data set and a power data set; A data clustering module, which is used to cluster the energy storage load data set to obtain N load clustering results; A clustering result analysis module, which is used to analyze the N load clustering results from the power data set to obtain N power intervals, wherein the N load clustering results correspond to the N power intervals; A model acquisition module, which is used to obtain a load-power mapping model according to the N load clustering results and the N power intervals; An optimization management module, which is used to use an optimization algorithm to optimize the N power intervals based on the load-power mapping model to obtain N power values, and manage the first lithium battery energy storage box with the N power values; A data source acquisition module, which is used to obtain power data sources corresponding to the power data set, wherein each power data source corresponds to a lithium battery energy storage element; A data grouping module, which is used to group the power data set based on the power data sources to obtain M power data groups; An adaptive analysis module, which is used to take the M power data groups as M adaptive variables, take a total value of the N power values as an adaptive target, and output N groups of power adaptive results based on the M adaptive variables; A model building module, which is used to build a load adaptive adjustment model with the N groups of power adaptive results; A real-time power data acquisition module, which is used to acquire real-time power data of the first lithium battery energy storage box; An adjustment result output module is configured to input the real-time power data into the load adaptive adjustment model, and output a first adaptive adjustment result according to the load adaptive adjustment model, wherein the first adaptive adjustment result is load data based on the real-time power data; A load adjustment module is configured to adjust the load of the first lithium battery energy storage box according to the first adaptive adjustment result.

Images