Load tracking method, device, electronic equipment and medium based on energy storage EMS system

Abstract

The present application relates to a load tracking method, device, electronic device and medium based on an energy storage EMS system, belonging to the technical field of energy storage device management, the method includes: obtaining real-time load consumption data, the real-time load consumption data includes power, voltage and current; obtaining historical load consumption data, the historical load consumption data includes historical power, historical voltage and historical current in a historical preset time period; obtaining future influencing factors in a future preset time period; predicting future load demand data based on the historical load consumption data and a prediction model trained by a machine learning algorithm; adjusting the load demand data based on the future influencing factors and the real-time load consumption data; formulating a control strategy based on the load demand data, and enabling the energy storage system to execute it. The present application has the effect of improving prediction accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of energy storage device management, and in particular to a load tracking method, device, electronic equipment and medium based on an energy storage EMS system. Background Art

[0002] Energy storage EMS system (Energy Management System) is a software system used to manage and optimize the operation of energy storage systems. Energy storage systems such as battery energy storage and supercapacitors, load tracking is one of the key functions. The purpose is to adjust the operation strategy of the energy storage system in real time according to load demand and market conditions to achieve optimal energy utilization and economic benefits.

[0003] Existing load tracking methods include but are not limited to the following:

[0004] The operation strategy of the energy storage system is adjusted by predicting future load demand. The prediction model can be built based on historical data, statistical methods, or machine learning. However, the accuracy of the prediction may be affected by factors such as weather changes and emergencies, resulting in actual results that are not as good as expected.

[0005] The operation of the energy storage system is adjusted according to a series of pre-set rules and strategies. For example, the optimal operation strategy is determined based on factors such as changes in electricity prices and the charging and discharging efficiency of the energy storage system. However, the design of the rules may be too simple and unable to adapt to the complex market environment and changes in load demand, and the prediction accuracy is not high.

[0006] Therefore, there is an urgent need for a load tracking method based on energy storage EMS system that can improve prediction accuracy. Summary of the invention

[0007] In order to improve prediction accuracy, the present application provides a load tracking method, device, electronic device and medium based on an energy storage EMS system.

[0008] In a first aspect, the present application provides a load tracking method based on an energy storage EMS system, which adopts the following technical solution:

[0009] Acquiring real-time load consumption data, wherein the real-time load consumption data includes power, voltage and current;

[0010] Acquire historical load consumption data, wherein the historical load consumption data includes historical power, historical voltage, and historical current within a historical preset time period;

[0011] Obtain future influencing factors for a preset time period in the future;

[0012] Predicting future load demand data based on the historical load consumption data and the prediction model trained using the machine learning algorithm;

[0013] adjusting the load demand data according to the future influencing factors and the real-time load consumption data;

[0014] A control strategy is formulated according to the load demand data and executed by the energy storage system.

[0015] By adopting the above technical solution, by combining historical load consumption data and prediction models, the system can more accurately predict future load demand data. The acquisition of real-time load consumption data enables the system to immediately perceive the current load status and incorporate various influencing factors into the prediction and adjustment process. The system can adapt to different external conditions and provide more accurate prediction results. Through precise load demand prediction and reasonable energy storage system control, this technology helps to reduce energy waste and improve energy utilization efficiency.

[0016] Furthermore, predicting future load demand data based on the historical load consumption data and the prediction model trained by the machine learning algorithm includes:

[0017] Cleaning the historical load consumption data, deleting abnormal data therein, and obtaining cleaned historical load consumption data;

[0018] The cleaned historical load consumption data is input into the prediction model to obtain output future load demand data.

[0019] By adopting the above technical solution, the electronic equipment first cleans the historical load consumption data, deletes the abnormal data, and combines the cleaned historical load consumption data with the prediction model to obtain future load demand data, thereby improving the prediction accuracy.

[0020] Furthermore, if the future influencing factors are economic factors, the obtaining of the future influencing factors in a future preset time period includes:

[0021] Obtain historical economic data, analyze and determine the change trend corresponding to the historical economic data, wherein the change trend includes stability, increase or decrease;

[0022] If the change trend is stable, then the average values ​​corresponding to the plurality of historical economic data are calculated, and the average values ​​are determined as the economic factors within a preset time period in the future;

[0023] If the trend of change is increasing, the growth rates corresponding to the plurality of historical economic data are calculated, and the first future economic factor is calculated based on the most recent historical economic data and the growth rate, and so on, to calculate the economic factors within a preset time period in the future;

[0024] If the changing trend is downward, the decline rates corresponding to the multiple historical economic data are calculated, and the first future economic factor is calculated based on the most recent historical economic data and the decline rate. Similarly, the economic factors within a preset time period in the future are calculated.

[0025] By adopting the above technical solution, the electronic device uses different calculation methods according to the different changing trends of historical economic data to obtain future influencing factors for a preset time period in the future, and obtains more appropriate and accurate prediction results.

[0026] Furthermore, the load demand data is adjusted according to the future influencing factors and the real-time load consumption data to determine the control strategy, including:

[0027] Determining whether the load demand data conforms to the consumption data change trend according to the historical load consumption data and the real-time load consumption data;

[0028] If yes, then obtain the influence coefficient of the future influence factor on the load at each future moment;

[0029] Multiplying the influence coefficient by the load demand data at each future moment to calculate updated load demand data;

[0030] Otherwise, the current influencing factor is obtained, and it is determined whether the overlap between the current influencing factor and the historical influencing factor corresponding to the historical time period is less than a preset value;

[0031] If it is less than the preset value, it is determined that the current influencing factor has an impact on the real-time load consumption data, and the load demand data is adjusted according to the current influencing factor and the future influencing factor.

[0032] By adopting the above technical solution, when the load demand data is regulated, it is first determined whether the real-time load consumption data has changed compared with the historical data. If there is no change, the corresponding influence coefficient is obtained for the future influencing factor, and the influence coefficient is multiplied by the load demand data obtained by the prediction model to obtain the corrected load demand data. If there is a change, the load demand data is adjusted according to the current influencing factors and the real-time load consumption data to make the load demand data more consistent with the actual situation and obtain more accurate data.

[0033] Further, judging whether the load demand data conforms to the consumption data change trend according to the historical load consumption data and the real-time load consumption data includes:

[0034] Comparing the historical load consumption data with each trend model to determine the change type corresponding to the historical load consumption data;

[0035] Compare the real-time load consumption data with the last historical load consumption data to determine whether it conforms to the change type;

[0036] If yes, the load request information is in line with the consumption data change trend;

[0037] If not, the load request information does not conform to the consumption data change trend.

[0038] By adopting the above technical solution, when judging whether the real-time load consumption data conforms to the consumption data change trend, the historical load consumption data is compared with each trend model to determine the change type, and the real-time load consumption data is compared with the last historical load consumption data to judge whether it conforms to the change trend.

[0039] Furthermore, the future influencing factors include future influencing sub-factors corresponding to each future moment, and obtaining the influence coefficient of the future influencing factors on the load at each future moment includes:

[0040] Obtaining a large amount of first load demand data under normal conditions and second load demand data of each of the first load demand data under any sample future influencing factor condition according to the big data, calculating the difference between the first load demand data and the second load demand data, dividing the difference by the first load demand data, and calculating the influence coefficients corresponding to the multiple sample future influencing factor conditions;

[0041] Establishing an analysis table, wherein the analysis table includes multiple sample future influencing factors and an influence coefficient corresponding to each sample future influencing factor;

[0042] Compare the future sub-influencing factor with the analysis table, and determine the influence factor corresponding to the sample future influencing factor that is consistent with the future influencing sub-factor as the first influence coefficient corresponding to the future sub-influencing factor;

[0043] Determine two adjacent first influence coefficients whose difference is greater than a preset value as second influence coefficients;

[0044] Calculate the difference between two adjacent second influence coefficients;

[0045] Comparing the difference with a preset table to determine a correction value corresponding to the difference, wherein the preset table includes a plurality of preset difference values ​​and a correction value corresponding to each of the difference values;

[0046] The second influence coefficient is added to the correction value to calculate an updated influence coefficient.

[0047] By adopting the above technical solution, by subdividing the future influencing factors into future sub-influencing factors and determining their load influence coefficients for each future moment respectively, a refined analysis of the influencing factors is achieved. Through the analysis table established by big data, the system can input the future sub-influencing factors into the model in real time for calculation, obtain the corresponding influence coefficient, determine the two adjacent first influence coefficients with a difference greater than the preset value as the second influence coefficient, and further perform difference calculation and correction value determination on them, which can effectively handle abnormal values ​​and avoid excessive influence of individual extreme data on the overall prediction results. By comparing the difference with the preset table, determining the correction value corresponding to the difference, and adding the correction value to the second influence coefficient, the influence coefficient is updated, and the accuracy of the prediction is further improved. Based on the updated influence coefficient, the system can more accurately predict future load demand data and formulate more reasonable control strategies based on this information.

[0048] Further, the adjusting the load demand data according to the current influencing factors and the future influencing factors includes:

[0049] Compare the current influencing factor with the analysis table to determine a third influencing coefficient corresponding to the current influencing factor;

[0050] Compare the future sub-influence factor with the analysis table to determine a fourth influence coefficient corresponding to the future sub-influence factor;

[0051] Dividing the real-time load consumption data by the third influence coefficient to calculate first load consumption data;

[0052] The first load consumption data is multiplied by each of the fourth influence coefficients to calculate the load demand data corresponding to each future moment.

[0053] By adopting the above technical solution, the electronic device compares the current influencing factor with the analysis table, determines the third influencing coefficient corresponding to the current influencing factor, reversely infers the first load consumption data not affected by the influencing factor based on the third influencing coefficient, and calculates the future load demand data based on the first load consumption data, so as to accurately predict the future load consumption information when the current load consumption information does not conform to the historical trend.

[0054] In the second aspect, the present application provides a load tracking device based on an energy storage EMS system, which adopts the following technical solution:

[0055] A real-time load consumption data acquisition module, used to acquire real-time load consumption data, wherein the real-time load consumption data includes power, voltage and current;

[0056] A historical load consumption data acquisition module is used to acquire historical load consumption data, wherein the historical load consumption data includes historical power, historical voltage and historical current within a historical preset time period;

[0057] A future influencing factor acquisition module, used to acquire future influencing factors in a future preset time period;

[0058] A prediction module, used to predict future load demand data based on the historical load consumption data and a prediction model trained by a machine learning algorithm;

[0059] An adjustment module, configured to adjust the load demand data according to the future influencing factors and the real-time load consumption data;

[0060] The execution module is used to formulate a control strategy according to the load demand data and enable the energy storage system to execute it.

[0061] By adopting the above technical solution, the prediction module combines historical load consumption data and prediction models, so that the system can more accurately predict future load demand data. The real-time load consumption data acquisition module obtains real-time load consumption data, enabling the system to immediately perceive the current load status and incorporate various influencing factors into the prediction and adjustment process. The system can adapt to different external conditions and provide more accurate prediction results. Through precise load demand prediction and reasonable energy storage system control, this technology helps to reduce energy waste and improve energy utilization efficiency.

[0062] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0063] An electronic device, comprising:

[0064] at least one processor;

[0065] Memory;

[0066] At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to: execute the method as described in any one of the first aspects.

[0067] By adopting the above technical solution, the processor executes the computer program in the memory. By combining historical load consumption data and prediction models, the system can more accurately predict future load demand data. The acquisition of real-time load consumption data enables the system to immediately perceive the current load status and incorporate various influencing factors into the prediction and adjustment process. The system can adapt to different external conditions and provide more accurate prediction results. Through accurate load demand prediction and reasonable energy storage system control, this technology helps to reduce energy waste and improve energy utilization efficiency.

[0068] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0069] A computer-readable storage medium stores a computer program that can be loaded by a processor and executes the method as described in any one of the first aspects.

[0070] By adopting the above technical solution, the processor executes the computer program in the computer-readable storage medium. By combining the historical load consumption data and the prediction model, the system can more accurately predict the future load demand data. The acquisition of real-time load consumption data enables the system to immediately perceive the current load status and incorporate various influencing factors into the prediction and adjustment process. The system can adapt to different external conditions and provide more accurate prediction results. Through accurate load demand prediction and reasonable energy storage system control, this technology helps to reduce energy waste and improve energy utilization efficiency.

[0071] In summary, the present application includes at least one of the following beneficial technical effects:

[0072] 1. By combining historical load consumption data and forecasting models, the system can more accurately predict future load demand data. The acquisition of real-time load consumption data enables the system to immediately perceive the current load status and incorporate various influencing factors into the forecasting and adjustment process. The system can adapt to different external conditions and provide more accurate forecast results. Through accurate load demand forecasting and reasonable energy storage system control, this technology helps reduce energy waste and improve energy utilization efficiency.

[0073] 2. When adjusting the load demand data, first determine whether the real-time load consumption data has changed compared with the historical data. If there is no change, obtain the corresponding influence coefficient for the future influencing factors, multiply the influence coefficient with the load demand data obtained by the prediction model, and obtain the corrected load demand data. If there is a change, adjust the load demand data according to the current influencing factors and real-time load consumption data to make the load demand data more consistent with the actual situation and obtain more accurate data. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a flow chart of a load tracking method based on an energy storage EMS system in an embodiment of the present application.

[0075] Figure 2 It is a structural block diagram of a load tracking device based on an energy storage EMS system in an embodiment of the present application.

[0076] Figure 3 It is a structural block diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0078] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0079] The present application embodiment discloses a load tracking method based on an energy storage EMS system. Figure 1 , executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto. It includes (steps S101 to S106):

[0080] Step S101: Acquire real-time load consumption data, which includes power, voltage and current.

[0081] Specifically, the electronic device is connected to the interface of the energy storage device to obtain real-time load consumption data corresponding to the power-consuming device connected to the interface of the energy storage device, wherein the real-time load consumption data can reflect the power consumption status of the power-consuming device.

[0082] Step S102: Acquire historical load consumption data, where the historical load consumption data includes historical power, historical voltage, and historical current within a historical preset time period.

[0083] Specifically, after the electronic device obtains the real-time load consumption data, it saves it to the database, so the electronic device can query the historical load consumption data from the database at any time. Among them, the preset time period can be set as needed, and in order to improve the accuracy of the calculation, the preset time period can be appropriately shortened.

[0084] Step S103: Obtain future influencing factors in a future preset time period.

[0085] Specifically, future influencing factors may include seasonal factors, weather factors, economic factors, time factors, technical factors, and social factors, etc.

[0086] Among them, the seasonal factor refers to the season corresponding to the preset time period in the future. Because the load demand is affected by seasonal changes, in winter, the demand for heating increases and the power load is often at its peak; in summer, the use of refrigeration equipment such as air conditioners will also lead to an increase in power load.

[0087] Weather factors include temperature, humidity, wind speed and other weather conditions in a preset time period in the future. Extreme weather conditions, such as high temperature or severe cold, will significantly increase the power load. On the other hand, weather factors will also affect the power generation of renewable energy, indirectly affecting the power load. Therefore, electronic devices obtain weather factors through weather forecast information on the Internet.

[0088] Economic factors include energy prices and electricity prices within a preset time period. The level of economic development and industrial structure determine the total amount and structure of power load. Industrialization and economic growth usually lead to an increase in power load. Economic factors within a preset time period in the future cannot be predicted completely accurately. Electronic equipment obtains historical economic factors and estimates the economic factors within a preset time period in the future based on the changing trends of historical economic factors.

[0089] For example, the electronic device obtains a plurality of historical economic data and analyzes and determines the corresponding change trends of the historical economic data, including stability, increase or decrease.

[0090] If the trend of change is stable, the average values ​​corresponding to multiple historical economic data are calculated and the average values ​​are determined as the economic factors in the future preset time period;

[0091] If the trend is rising, the growth rates corresponding to multiple historical economic data are calculated, and the first future economic factor is calculated based on the most recent historical economic data and the growth rate. This is repeated to calculate the economic factors within a preset time period in the future.

[0092] If the trend of change is downward, the decline rate corresponding to multiple historical economic data is calculated. Based on the most recent historical economic data and the decline rate, the first future economic factor is calculated. Similarly, the economic factors within a preset time period in the future are calculated.

[0093] The time factor is the time period corresponding to the preset time period in the future. Usually, the power load is higher during the day due to work, production and other activities, while it is relatively lower at night. On the other hand, holidays and special events will also have an impact on the power load demand.

[0094] The technical factors include the efficiency of power equipment and the level of energy storage technology. Efficient power equipment can reduce power losses, while high-level energy storage technology can smooth out power load fluctuations.

[0095] Social factors include the population size, population density, and population structure in the area where the power equipment is located. Social factors will affect the demand for power load. For example, the power load in densely populated urban areas is usually higher, and the power load in areas with a large young population is also higher.

[0096] However, the changes in technical and social factors are not obvious and do not change all the time. Therefore, electronic equipment can evaluate the efficiency of power equipment and check the level of energy storage technology at regular intervals, while obtaining updated social factors through the Internet.

[0097] Step S104: predict future load demand data based on historical load consumption data and a prediction model trained using a machine learning algorithm.

[0098] Step S104 includes (step S1041 to step S1042):

[0099] Step S1041: clean the historical load consumption data, delete the abnormal data therein, and obtain the cleaned historical load consumption data.

[0100] Specifically, there may be erroneous items, duplicate items, incomplete or inaccurate data in the historical load consumption data. Before cleaning, select the original data and use visualization tools such as tables, histograms, scatter plots, etc. to check the data so as to find abnormal data and delete them.

[0101] If there are missing data, the mean of the two adjacent data is used to fill the missing data.

[0102] Step S1042: Input the cleaned historical load consumption data into the prediction model to obtain output future load demand data.

[0103] Specifically, electronic devices pre-apply machine learning algorithms to train prediction models, such as recurrent neural network models such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit), or MLP (Multi-Layer Perceptron) and DNN (Deep Neural Network), which can be used to process complex feature combinations and interactions in power loads, and then predict power loads.

[0104] When training the prediction model, the electronic device pre-sets the historical load consumption data of the preset time period and the future load demand data of the future preset time period as a set of sample data. The preset time period is equal to the future preset time period in length and the time is continuous. The future load demand data of the future preset time period in each set of sample data does not consider the influence of future influencing factors, and then sets multiple sets of sample data. The sample data are used as training set, validation set and test set respectively, the prediction model is trained with the training set, the performance of the model is evaluated with the validation set, and the hyperparameters are adjusted as needed. The generalization ability of the model is evaluated with the test set, so as to obtain a trained prediction model.

[0105] The electronic equipment inputs the historical load consumption data after cleaning into the trained prediction model to obtain the output future load demand data. At this time, the future load demand data is calculated based on the rules of the sample data and may not be completely accurate.

[0106] Step S105: Adjust the load demand data according to future influencing factors and real-time load consumption data.

[0107] Step S105 includes (step S1051 to step S1055):

[0108] Step S1051: judging whether the load demand data conforms to the consumption data change trend according to the historical load consumption data and the real-time load consumption data, including (steps Sa to Sd):

[0109] Step Sa: Compare the historical load consumption data with each trend model to determine the change type corresponding to the historical load consumption data.

[0110] Specifically, the electronic device is preset with multiple trend models, including at least three types of trend models: gradually rising, gradually falling and stable. The historical load consumption data and each different trend model are plotted on the same icon, and the model with the highest fit is selected as the data change type based on the degree of fit between the data point and the model curve.

[0111] Step Sb: Compare the real-time load consumption data with the last historical load consumption data to determine whether they meet the change type.

[0112] If yes, execute step Sc: the load request information is consistent with the consumption data change trend.

[0113] Specifically, if the real-time load consumption data is greater than the last historical load consumption data, and the change type of the historical load consumption data is gradually increasing, then the load request information is consistent with the consumption data change trend; if the real-time load consumption data is less than the last historical load consumption data, and the change type of the historical load consumption data is gradually decreasing, then the load request information is consistent with the consumption data change trend; if the real-time load consumption data is equal to the last historical load consumption data, and the change type of the historical load consumption data is stable, then the load request information is consistent with the consumption data change trend.

[0114] If not, execute step Sd: the load request information does not conform to the consumption data change trend.

[0115] Specifically, except for the above three situations, the requested information does not conform to the consumption data change trend.

[0116] If yes, then execute step S1052: obtain the influence coefficient of future influencing factors on the load at each future moment, including (steps S11 to S17):

[0117] Step S11: Obtain a large amount of first load demand data under normal conditions and second load demand data of each first load demand data under any sample future influencing factor condition based on big data, calculate the difference between the first load demand data and the second load demand data, divide the difference by the first load demand data, and calculate the influence coefficients corresponding to multiple sample future influencing factor conditions.

[0118] Step S12: Create an analysis table, which includes multiple sample future influencing factors and the influence coefficient corresponding to each sample future influencing factor.

[0119] Specifically, the electronic device stores a large number of sample future influencing factors and corresponding influencing coefficients to obtain an analysis table, which can also be understood as a data set.

[0120] Step S13: Compare the future sub-influencing factors with the analysis table, and determine the influence coefficient corresponding to the sample future influencing factors that are consistent with the future influencing sub-factors as the first influence coefficient corresponding to the future sub-influencing factors.

[0121] Step S14: Determine two adjacent first influence coefficients whose difference is greater than a preset value as second influence coefficients.

[0122] Specifically, under normal circumstances, since the difference between future influencing factors at two adjacent moments may be very slight, the corresponding first influencing coefficients do not differ much. However, when the difference is greater than a preset value, there may be a more obvious future influencing factor at the two adjacent moments. Therefore, the corresponding first influencing coefficient is determined as the second influencing coefficient.

[0123] Step S15: Calculate the difference between the second second influence coefficient and the first second influence coefficient.

[0124] Step S16: Compare the difference with the preset table to determine the correction value corresponding to the difference.

[0125] Specifically, the staff sets up a table on the electronic device in advance, which includes multiple differences and the correction value corresponding to each difference. In actual situations, sudden changes in influencing factors in the future will have a greater impact on energy storage equipment. In order to be able to respond to sudden increases or decreases in loads in a timely manner, it is necessary to increase reserves. Therefore, the differences in the table are all greater than zero, and the larger the difference, the larger the corresponding correction value. If the difference is not greater than zero, the corresponding correction value is zero.

[0126] Step S17: Add the second influence coefficient to the correction value to calculate an updated influence coefficient.

[0127] Specifically, when the difference between two adjacent second influence coefficients is greater than a preset value, it is caused by a sudden change in the second second influence coefficient, and therefore, the second influence coefficient is added to the correction value to obtain an updated influence coefficient.

[0128] Step S1053: multiply the influence coefficient by the load demand data at each future moment to calculate and obtain updated load demand data.

[0129] Specifically, the electronic device multiplies the influence coefficient with the load demand data at each future moment to calculate updated load demand data. The load demand data after multiplication by the influence coefficient increases, so that the energy storage device stores more energy in advance for emergency use.

[0130] Otherwise, execute step S1054: obtain the current influencing factors and determine whether the current influencing factors have an impact on the real-time load consumption data.

[0131] Specifically, if the electronic device determines that the load demand data does not conform to the consumption data change trend based on the real-time load consumption data, the current influencing factor may have an impact on the real-time load consumption data. In order to determine whether it is caused by the current influencing factor, the electronic device compares the current influencing factor with the historical influencing factor corresponding to the historical time period. If the difference is large, it is determined that the current influencing factor has an impact on the real-time load consumption data.

[0132] Step S1055: If the current influencing factors have an impact on the real-time load consumption data, the load demand data is adjusted according to the current influencing factors and future influencing factors, including (steps S21 to S24):

[0133] Step S21: Compare the current influencing factor with the analysis table to determine the third influencing coefficient corresponding to the current influencing factor.

[0134] Step S22: Compare the future sub-influencing factor with the analysis table to determine the fourth influence coefficient corresponding to the future sub-influencing factor.

[0135] Specifically, the current influencing factors and future influencing sub-factors are compared with the analysis table respectively, and the influence coefficient corresponding to the sample future influencing factors that are consistent with the current influencing factors are determined as the third influence coefficient corresponding to the current influencing factors, and the influence coefficient corresponding to the sample future influencing factors that are consistent with the future sub-influencing factors are determined as the fourth influence coefficient corresponding to the future sub-influencing factors. The third influence coefficient reflects the influence intensity of the current influencing factors on the load demand, and the fourth influence coefficient reflects the influence intensity of the future sub-influencing factors on the load demand.

[0136] Step S23: Divide the real-time load consumption data by the third influence coefficient to calculate and obtain the first load consumption data.

[0137] Specifically, the electronic device divides the real-time load consumption data by the third influence coefficient to calculate the first load consumption data. The first load consumption data can be regarded as the load consumption data without the influence of the current influencing factors. Therefore, the load demand data at future times is estimated based on the first load consumption data combined with the future influencing factors.

[0138] Step S24: multiply the first load consumption data by each fourth influence coefficient to calculate the load demand data corresponding to each future moment.

[0139] Specifically, the electronic device multiplies each fourth influence coefficient by the first load consumption data, and calculates the load demand data under the influence of the future sub-influence factors.

[0140] Step S106: formulate a control strategy according to the load demand data, and enable the energy storage system to execute it.

[0141] Specifically, after the electronic device predicts the load demand data, it compares the total load demand data of the future preset time period with the current energy of the energy storage system. If the current energy is higher than the total load demand data, charging will not be done temporarily; if the current energy is lower than or equal to the total load demand data, the charging strategy will be executed to ensure that the load demand is met at all times.

[0142] In order to better implement the above method, the present application embodiment also provides a load tracking device based on an energy storage EMS system, referring to Figure 2 The load following device 200 based on the energy storage EMS system includes:

[0143] The first acquisition module 201 is used to acquire real-time load consumption data, which includes power, voltage and current;

[0144] The second acquisition module 202 is used to acquire historical load consumption data, where the historical load consumption data includes historical power, historical voltage and historical current within a historical preset time period;

[0145] The third acquisition module 203 is used to acquire future influencing factors in a future preset time period;

[0146] A prediction module 204, for predicting future load demand data based on historical load consumption data and a prediction model trained using a machine learning algorithm;

[0147] An adjustment module 205, for adjusting the load demand data according to future influencing factors and real-time load consumption data;

[0148] The execution module 206 is used to formulate a control strategy according to the load demand data and enable the energy storage system to execute it.

[0149] Furthermore, the prediction module 204 is specifically used for:

[0150] Clean the historical load consumption data, delete the abnormal data therein, and obtain the cleaned historical load consumption data;

[0151] The cleaned historical load consumption data is input into the prediction model to obtain the output future load demand data.

[0152] Furthermore, if the future influencing factor is an economic factor, the third acquisition module 203 is specifically used to:

[0153] Obtain multiple historical economic data, analyze and determine the corresponding change trends of the historical economic data, and the change trends include stability, increase or decrease;

[0154] If the trend of change is stable, the average values ​​corresponding to multiple historical economic data are calculated and the average values ​​are determined as the economic factors in the future preset time period;

[0155] If the trend is rising, the growth rates corresponding to multiple historical economic data are calculated, and the first future economic factor is calculated based on the most recent historical economic data and the growth rate. This is repeated to calculate the economic factors within a preset time period in the future.

[0156] If the trend of change is downward, the decline rate corresponding to multiple historical economic data is calculated. Based on the most recent historical economic data and the decline rate, the first future economic factor is calculated. Similarly, the economic factors within a preset time period in the future are calculated.

[0157] Furthermore, the adjustment module 205 is specifically used for:

[0158] Determine whether the load demand data conforms to the consumption data change trend based on historical load consumption data and real-time load consumption data;

[0159] If so, the influence coefficient of the future influencing factors on the load at each future moment is obtained;

[0160] Multiply the influence coefficient by the load demand data at each future moment to calculate updated load demand data;

[0161] Otherwise, the current influencing factor is obtained, and it is determined whether the overlap between the current influencing factor and the historical influencing factor corresponding to the historical time period is less than a preset value;

[0162] If it is less than the preset value, it is determined that the current influencing factors have an impact on the real-time load consumption data, and the load demand data is adjusted according to the current influencing factors and future influencing factors.

[0163] Furthermore, the adjustment module 205 determines whether the load demand data conforms to the consumption data change trend according to the historical load consumption data and the real-time load consumption data, specifically for:

[0164] Compare the historical load consumption data with each trend model to determine the type of change corresponding to the historical load consumption data;

[0165] Compare the real-time load consumption data with the last historical load consumption data to determine whether it meets the change type;

[0166] If yes, the load request information is consistent with the consumption data change trend;

[0167] If not, the load request information does not conform to the consumption data change trend.

[0168] Furthermore, the future influencing factors include future influencing sub-factors corresponding to each future moment, and the adjustment module 205 obtains the influence coefficient of the future influencing factors on the load at each future moment, specifically for:

[0169] Obtain a large amount of first load demand data under conventional conditions and second load demand data of each first load demand data under any sample future influencing factor condition according to the big data, calculate the difference between the first load demand data and the second load demand data, divide the difference by the first load demand data, and calculate the influence coefficients corresponding to the multiple sample future influencing factor conditions;

[0170] Establish an analysis table, which includes multiple sample future influencing factors and the corresponding influence coefficient of each sample future influencing factor;

[0171] Compare the future sub-influencing factors with the analysis table, and determine the influencing factors corresponding to the sample future influencing factors that are consistent with the future influencing sub-factors as the first influencing coefficients corresponding to the future sub-influencing factors;

[0172] Determine two adjacent first influence coefficients whose difference is greater than a preset value as second influence coefficients;

[0173] Calculate the difference between two adjacent second influence coefficients;

[0174] Compare the difference with a preset table to determine a correction value corresponding to the difference, wherein the preset table includes a plurality of preset differences and a correction value corresponding to each difference;

[0175] The second influence coefficient is added to the correction value to calculate an updated influence coefficient.

[0176] Furthermore, the adjustment module 205 adjusts the load demand data according to current influencing factors and future influencing factors, specifically for:

[0177] Compare the current influencing factor with the analysis table to determine the third influencing coefficient corresponding to the current influencing factor;

[0178] Compare the future sub-influencing factors with the analysis table to determine the fourth influence coefficient corresponding to the future sub-influencing factors;

[0179] Dividing the real-time load consumption data by the third influence coefficient to calculate the first load consumption data;

[0180] The first load consumption data is multiplied by each fourth influence coefficient to calculate the load demand data corresponding to each future moment.

[0181] The various variations and specific examples of the methods in the aforementioned embodiments are also applicable to the load tracking device based on the energy storage EMS system in this embodiment. Through the aforementioned detailed description of the load tracking method based on the energy storage EMS system, those skilled in the art can clearly know the implementation method of the load tracking device based on the energy storage EMS system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0182] In order to better implement the above method, the present application embodiment provides an electronic device, referring to Figure 3 , the electronic device 300 includes: a processor 301, a memory 303 and a display screen 305. Among them, the memory 303 and the display screen 305 are connected to the processor 301, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0183] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0184] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc.

[0185] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0186] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0187] Figure 3 The electronic device 300 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0188] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, the load tracking method based on the energy storage EMS system provided in the above embodiment is implemented. The processor executes the computer program in the computer-readable storage medium. By combining historical load consumption data and prediction models, the system can more accurately predict future load demand data. The acquisition of real-time load consumption data enables the system to immediately perceive the current load status and incorporate various influencing factors into the prediction and adjustment process. The system can adapt to different external conditions and provide more accurate prediction results. Through accurate load demand prediction and reasonable energy storage system control, this technology helps to reduce energy waste and improve energy utilization efficiency.

[0189] In this embodiment, the computer-readable storage medium may be a tangible device that holds and stores instructions used by the instruction execution device. The computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a podium random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0190] The computer program in this embodiment includes program codes for executing all the aforementioned methods, and the program codes may include instructions corresponding to the steps of the methods provided in the above embodiments. The computer program can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network (such as the Internet, a local area network, a wide area network, and / or a wireless network). The computer program can be executed completely on the user's computer or as an independent software package.

[0191] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

[0192] In addition, it is to be understood that relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprises," "comprising," or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or elements that are inherent to such process, method, article, or device.

Claims

1. A load following method based on an energy storage EMS system, characterized in that: include: Acquiring real-time load consumption data, wherein the real-time load consumption data includes power, voltage and current; Acquire historical load consumption data, wherein the historical load consumption data includes historical power, historical voltage, and historical current within a historical preset time period; Obtain future influencing factors for a preset time period in the future; Predicting future load demand data based on the historical load consumption data and the prediction model trained using the machine learning algorithm; adjusting the load demand data according to the future influencing factors and the real-time load consumption data; Formulate a control strategy based on the load demand data and execute it on the energy storage system; The step of adjusting the load demand data according to the future influencing factors and the real-time load consumption data to determine the control strategy includes: Determining whether the load demand data conforms to the consumption data change trend according to the historical load consumption data and the real-time load consumption data; If yes, then obtain the influence coefficient of the future influence factor on the load at each future moment; Multiplying the influence coefficient by the load demand data at each future moment to calculate updated load demand data; Otherwise, the current influencing factor is obtained, and it is determined whether the overlap between the current influencing factor and the historical influencing factor corresponding to the historical time period is less than a preset value; If it is less than the preset value, it is determined that the current influencing factor has an impact on the real-time load consumption data, and the load demand data is adjusted according to the current influencing factor and the future influencing factor; The future influencing factors include future sub-influencing factors corresponding to each future moment, and obtaining the influence coefficient of the future influencing factors on the load at each future moment includes: Obtaining a large amount of first load demand data under normal conditions and second load demand data of each of the first load demand data under any sample future influencing factor condition according to the big data, calculating the difference between the first load demand data and the second load demand data, dividing the difference by the first load demand data, and calculating the influence coefficients corresponding to the multiple sample future influencing factor conditions; Establishing an analysis table, wherein the analysis table includes multiple sample future influencing factors and an influence coefficient corresponding to each sample future influencing factor; Compare the future sub-influencing factor with the analysis table, and determine the influencing factor corresponding to the sample future influencing factor that is consistent with the future sub-influencing factor as the first influencing coefficient corresponding to the future sub-influencing factor; Determine two adjacent first influence coefficients whose difference is greater than a preset value as second influence coefficients; Calculate the difference between two adjacent second influence coefficients; Comparing the difference with a preset table to determine a correction value corresponding to the difference, wherein the preset table includes a plurality of preset difference values ​​and a correction value corresponding to each of the difference values; The second influence coefficient is added to the correction value to calculate an updated influence coefficient.

2. The method according to claim 1, characterized in that: The predicting of future load demand data based on the historical load consumption data and the prediction model trained by the machine learning algorithm includes: Cleaning the historical load consumption data, deleting abnormal data therein, and obtaining cleaned historical load consumption data; The cleaned historical load consumption data is input into the prediction model to obtain output future load demand data.

3. The method according to claim 1, characterized in that If the future influencing factors are economic factors, the obtaining of the future influencing factors for a preset time period includes: Acquire multiple historical economic data, analyze and determine the change trend corresponding to the historical economic data, wherein the change trend includes stability, increase or decrease; If the change trend is stable, then the average values ​​corresponding to the plurality of historical economic data are calculated, and the average values ​​are determined as the economic factors within a preset time period in the future; If the trend of change is increasing, the growth rates corresponding to the plurality of historical economic data are calculated, and the first future economic factor is calculated based on the most recent historical economic data and the growth rate, and so on, to calculate the economic factors within a preset time period in the future; If the changing trend is downward, the decline rates corresponding to the multiple historical economic data are calculated, and the first future economic factor is calculated based on the most recent historical economic data and the decline rate. Similarly, the economic factors within a preset time period in the future are calculated.

4. The method according to claim 1, characterized in that The determining whether the load demand data conforms to the consumption data change trend according to the historical load consumption data and the real-time load consumption data includes: Comparing the historical load consumption data with each trend model to determine the change type corresponding to the historical load consumption data; Compare the real-time load consumption data with the last historical load consumption data to determine whether it conforms to the change type; If yes, the load demand data is in line with the consumption data change trend; If not, the load demand data does not conform to the consumption data change trend.

5. The method according to claim 1, characterized in that The adjusting the load demand data according to the current influencing factors and the future influencing factors includes: Compare the current influencing factor with the analysis table to determine a third influencing coefficient corresponding to the current influencing factor; Compare the future sub-influence factor with the analysis table to determine a fourth influence coefficient corresponding to the future sub-influence factor; Dividing the real-time load consumption data by the third influence coefficient to calculate first load consumption data; The first load consumption data is multiplied by each of the fourth influence coefficients to calculate the load demand data corresponding to each future moment.

6. A load following device based on an energy storage EMS system, characterized in that: include: A first acquisition module, used to acquire real-time load consumption data, wherein the real-time load consumption data includes power, voltage and current; A second acquisition module is used to acquire historical load consumption data, wherein the historical load consumption data includes historical power, historical voltage and historical current within a historical preset time period; The third acquisition module is used to obtain future influencing factors in a future preset time period; A prediction module, used to predict future load demand data based on the historical load consumption data and a prediction model trained by a machine learning algorithm; An adjustment module, configured to adjust the load demand data according to the future influencing factors and the real-time load consumption data; An execution module, used to formulate a control strategy according to the load demand data and enable the energy storage system to execute the strategy; The adjustment module is specifically used for: Determining whether the load demand data conforms to the consumption data change trend according to the historical load consumption data and the real-time load consumption data; If yes, then obtain the influence coefficient of the future influence factor on the load at each future moment; Multiplying the influence coefficient by the load demand data at each future moment to calculate updated load demand data; Otherwise, the current influencing factor is obtained, and it is determined whether the overlap between the current influencing factor and the historical influencing factor corresponding to the historical time period is less than a preset value; If it is less than the preset value, it is determined that the current influencing factor has an impact on the real-time load consumption data, and the load demand data is adjusted according to the current influencing factor and the future influencing factor; The future influencing factors include future sub-influencing factors corresponding to each future moment, and obtaining the influence coefficient of the future influencing factors on the load at each future moment includes: Obtaining a large amount of first load demand data under normal conditions and second load demand data of each of the first load demand data under any sample future influencing factor condition according to the big data, calculating the difference between the first load demand data and the second load demand data, dividing the difference by the first load demand data, and calculating the influence coefficients corresponding to the multiple sample future influencing factor conditions; Establishing an analysis table, wherein the analysis table includes multiple sample future influencing factors and an influence coefficient corresponding to each sample future influencing factor; Compare the future sub-influencing factor with the analysis table, and determine the influencing factor corresponding to the sample future influencing factor that is consistent with the future sub-influencing factor as the first influencing coefficient corresponding to the future sub-influencing factor; Determine two adjacent first influence coefficients whose difference is greater than a preset value as second influence coefficients; Calculate the difference between two adjacent second influence coefficients; Comparing the difference with a preset table to determine a correction value corresponding to the difference, wherein the preset table includes a plurality of preset difference values ​​and a correction value corresponding to each of the difference values; The second influence coefficient is added to the correction value to calculate an updated influence coefficient.

7. An electronic device, characterized in that: include: at least one processor; Memory; At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to: execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 5.

Images