Angelica keiskei electricity demand prediction method, smart battery and medium

Abstract

The invention discloses a prediction method for an electricity consumption demand of an angelica keiskei, an intelligent battery and a medium, and relates to the field of batteries, and the method comprises the steps: determining the daily discharge depth of the battery in each year of an analysis age limit based on the historical discharge data of the battery in the analysis age limit; according to the daily discharge depth of the battery in each year of the analysis age limit, determining the daily average discharge depth in one year; and obtaining the date of the angelica keiskei, and taking the average discharge depth corresponding to the date of the angelica keiskei as the predicted discharge depth of the angelica keiskei to realize prediction of the electricity demand of the angelica keiskei. According to the method, the discharge depth, namely the power demand, of the angelica keiskei is predicted based on big data analysis, so that charging is performed in time when the remaining capacity of the battery does not meet the power demand of the angelica keiskei, and the problems that the power demand of the angelica keiskei cannot be accurately predicted at present and power supply of the battery is affected when the remaining capacity of the battery does not meet the power demand of the angelica keiskei are solved.

Description

Technical Field

[0001] The present application relates to the field of batteries, and in particular to a method for predicting tomorrow's electricity demand, a smart battery and a medium. Background Art

[0002] Smart battery, also known as smart battery system (SBS), is a battery that integrates a management system and its supporting electronic circuits. This battery can not only store electrical energy, but also self-monitor and report key data, such as battery voltage, current, temperature, remaining power, and health status. This data is collected and processed by the microprocessor inside the battery, and can communicate with external devices or management systems through specific communication protocols (such as SMBus).

[0003] Currently, the use of smart batteries is very common, but there is a problem that it is impossible to predict tomorrow's electricity demand, resulting in the battery power supply being affected when the remaining power of the battery does not meet tomorrow's electricity demand. Summary of the invention

[0004] The purpose of this application is to provide a method for predicting tomorrow's electricity demand, a smart battery and a medium to solve the problem that tomorrow's electricity demand cannot be accurately predicted, which affects the battery's power supply tomorrow when the remaining power of the battery does not meet tomorrow's electricity demand.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for predicting tomorrow's electricity demand, comprising:

[0007] Determining the depth of discharge of the battery for each day of each year of the analysis period based on historical discharge data of the battery during the analysis period;

[0008] Determine the average daily depth of discharge in a year based on the daily depth of discharge of the battery in each year of the analysis period;

[0009] The date of tomorrow is obtained, and the average discharge depth corresponding to the date of tomorrow is used as the predicted discharge depth of tomorrow, so as to realize the prediction of the electricity demand of tomorrow.

[0010] Optionally, determining the average daily depth of discharge in a year according to the daily depth of discharge of the battery in each year of the analysis period includes:

[0011] Divide the daily discharge depths of each year of the analysis period by month and by the corresponding weekday of each day of each month to obtain all daily discharge depths of each weekday of each month of each year of the analysis period;

[0012] The following processing is performed on the daily discharge depth of each week day of each month in a year to obtain the average discharge depth of each week day of each month in a year, that is, the average discharge depth of each day in a year:

[0013] The daily discharge depths of the same day of the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of the corresponding day of the week of the corresponding month in the year.

[0014] Optionally, determining the average daily depth of discharge in a year according to the daily depth of discharge of the battery in each year of the analysis period includes:

[0015] Dividing the daily discharge depth in each year of the analysis period according to working days and holidays to obtain the discharge depth of each working day and each holiday in each year of the analysis period;

[0016] Divide the discharge depth of each working day in each year of the analysis period by month and by the corresponding weekday of each day in each month to obtain all daily discharge depths of each weekday corresponding to the working day of each month in each year of the analysis period; and divide the discharge depth of each holiday in each year of the analysis period by month to obtain all daily discharge depths of holidays in each month in each year of the analysis period;

[0017] The following processing is performed on the daily discharge depth of each weekday corresponding to the working day of each month in a year and the daily discharge depth of each holiday in each month in a year to obtain the average discharge depth of each weekday corresponding to the working day of each month in a year and the average discharge depth of each holiday in each month, that is, the average discharge depth of each day in a year:

[0018] The daily discharge depths of the same weekday corresponding to the working days of the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of the weekday corresponding to the working days of the corresponding month in the year; and the daily discharge depths of holidays in the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of holidays in the corresponding month in the year.

[0019] Optionally, taking the average discharge depth corresponding to the date of tomorrow as the predicted discharge depth of tomorrow includes:

[0020] According to tomorrow's date, the day of tomorrow is determined, and the average discharge depth of the day of tomorrow in the month in which tomorrow is located is used as the predicted discharge depth of tomorrow.

[0021] Optionally, taking the average discharge depth corresponding to the date of tomorrow as the predicted discharge depth of tomorrow includes:

[0022] According to tomorrow's date, determine whether tomorrow is a working day or a holiday;

[0023] When tomorrow is a holiday, the average discharge depth of the holidays corresponding to the month in which tomorrow is located is used as the predicted discharge depth of tomorrow;

[0024] When tomorrow is a working day, the day of tomorrow is determined, and the average discharge depth of the day of tomorrow corresponding to the working day of the month in which tomorrow is located is used as the predicted discharge depth of tomorrow.

[0025] Optionally, the method for predicting tomorrow's electricity demand further includes:

[0026] After obtaining the predicted discharge depth for tomorrow, determining the predicted deviation rate for each day in the predicted time period according to the predicted discharge depth and the actual discharge depth for each day in the predicted time period;

[0027] Predicting tomorrow's prediction deviation rate based on the daily prediction deviation rate within the prediction time period;

[0028] The predicted discharge depth for tomorrow is corrected by using the predicted deviation rate for tomorrow to obtain a final predicted discharge depth for tomorrow.

[0029] Optionally, predicting tomorrow's prediction deviation rate based on the daily prediction deviation rate within the prediction time period includes:

[0030] The daily predicted deviation rate within the predicted time period is input into the constructed deviation rate prediction model, and the deviation rate prediction model predicts and outputs the predicted deviation rate for tomorrow.

[0031] Optionally, the method for predicting tomorrow's electricity demand further includes:

[0032] After the predicted discharge depth for tomorrow is obtained, when the battery is not charged, if the SOC of the battery acquired in real time is not greater than the predicted discharge depth for tomorrow, the user is reminded to charge.

[0033] In a second aspect, the present application provides a smart battery, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-mentioned methods for predicting tomorrow's electricity demand.

[0034] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting tomorrow's electricity demand.

[0035] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0036] The present application provides a method for predicting tomorrow's electricity demand, a smart battery and a medium. The method determines the daily discharge depth of the battery in each year of the analysis period based on the historical discharge data of the battery in the analysis period, determines the average daily discharge depth in the year according to the daily discharge depth of the battery in each year of the analysis period, and after obtaining the date of tomorrow, uses the average discharge depth corresponding to the date of tomorrow as the predicted discharge depth of tomorrow, thereby predicting tomorrow's discharge depth, i.e., electricity demand, based on big data analysis, so that the battery can be charged in time when the remaining power of the battery does not meet the electricity demand of tomorrow. The method solves the problem that the electricity demand of tomorrow cannot be accurately predicted at present, which affects the power supply of the battery tomorrow when the remaining power of the battery does not meet the electricity demand of tomorrow. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 This is a flow chart of a method for predicting tomorrow's electricity demand in one embodiment of the present application;

[0039] Figure 2 A schematic diagram of functional modules of a device for predicting tomorrow's electricity demand provided in one embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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.

[0041] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0042] In an exemplary embodiment, Figure 1 As shown, a method for predicting tomorrow's electricity demand is provided, comprising the following steps 101 to 103. Among them:

[0043] Step 101, based on the historical discharge data of the battery in the analysis period, determine the daily discharge depth of the battery in each year of the analysis period.

[0044] In an embodiment of the present application, the analysis period refers to the period involved in the historical electricity consumption data. The present application does not make any specific limitation on the analysis period, and it can be set according to actual needs. For example, the battery discharge data of the three years before the current period is used as the historical discharge data for the analysis period. For smart batteries, the discharge data can be obtained from the battery data stored in its battery management system. The discharge data includes the start time, start SOC, end time and end SOC of each discharge. The depth of discharge is the ratio of the change in battery SOC caused by battery discharge to the start SOC of battery discharge.

[0045] Step 102, determining an average daily depth of discharge in a year based on the daily depth of discharge of the battery in each year of the analysis period.

[0046] In the embodiment of the present application, the average discharge depth per day in a year is the average value of the discharge depth on each same date in the analysis year. For example, the historical discharge data of the analysis period is set to be the battery discharge data of the three years before the current period. Then, based on step 101, the discharge depth on each same date in the three years before the current period can be obtained. On each date of the year, the three discharge depths with the same date in the daily discharge depths of the three years before the current period are averaged to obtain the average discharge depth per day in the year. For example, the current period is 2024, the first year before the current period is 2023, the second year before the current period is 2022, and the third year before the current period is 20231. The three years before the current period, i.e., 2023 to 2021, the discharge depth on February 1, 2023 is 0.9, the discharge depth on February 1, 2022 is 0.85, and the discharge depth on February 1, 2021 is 0.95. Then, the average discharge depth on February 1 of the year is (0.9+0.85+0.95) / 3=0.9.

[0047] Step 103, obtaining tomorrow's date, taking the average discharge depth corresponding to tomorrow's date as tomorrow's predicted discharge depth, and realizing prediction of tomorrow's electricity demand.

[0048] In the embodiment of the present application, the current date is obtained, and tomorrow's date can be obtained by adding 1 to the current date.

[0049] Implement the above steps 101 to 103, determine the discharge depth of the battery on each day of each year in the analysis period based on the historical discharge data of the battery in the analysis period, determine the average discharge depth for each day of the year based on the discharge depth of the battery on each day of each year in the analysis period, and after obtaining tomorrow's date, use the average discharge depth corresponding to tomorrow's date as tomorrow's predicted discharge depth, thereby realizing the prediction of tomorrow's discharge depth, i.e., electricity demand, based on big data analysis.

[0050] As an optional implementation, step 101 is replaced by the following steps 201 to 204.

[0051] in:

[0052] Step 201 , obtaining historical discharge data of the battery in the analysis period, wherein the historical discharge data includes the start time, start SOC, end time and end SOC of each discharge of the battery.

[0053] In the embodiment of the present application, after obtaining the historical discharge data of the battery in the analysis period, it can be stored in a feature database for later use. The historical discharge data of the battery in the analysis period can be extracted using machine learning or other methods, or an extraction algorithm can be formulated according to actual needs.

[0054] Step 202, determining the number of discharges of the battery per day in each year of the analysis period according to the start time and the end time of each discharge of the battery.

[0055] Step 203, calculating the discharge depth of the battery for each discharge on each day of each year in the analysis period, wherein the discharge depth is the difference between the start SOC and the end SOC of a single discharge of the battery.

[0056] Step 204, determining the depth of discharge of the battery for each day in each year of the analysis period based on the number of discharges of the battery for each day in each year of the analysis period and the depth of discharge of each discharge for each day, comprises:

[0057] When the battery is discharged only once in a day, the discharge depth of the discharge is taken as the discharge depth of the battery on that day;

[0058] When the battery is discharged multiple times in one day, the discharge depths of all discharges are accumulated as the discharge depth of the battery on that day.

[0059] For example, there are the following historical discharge data: start time: 10:00 on January 3, 2023, end time: 11:00 on January 3, 2023, start SOC: 0.8, end SOC: 0.6; start time: 14:00 on January 3, 2023, end time: 15:00 on January 3, 2023, start SOC: 0.7, end SOC: 0.5; according to the start time and end time of each discharge of the battery, it is determined that the number of discharges of the battery on January 3, 2023 is 2, and the discharge depths of the two discharges are calculated to be 0.2 and 0.2 respectively, then they are added together to obtain the discharge depth of the battery on January 3, 2023 as 0.4.

[0060] In another exemplary embodiment of the present application, before step 202, the following step is further included:

[0061] The historical discharge data is preprocessed.

[0062] In the embodiment of the present application, the preprocessing includes missing value processing and outlier processing. Missing values ​​are divided into long-term continuous data missing and discontinuous data missing. For the case of long-term continuous data missing, it is considered that the data of this period of time is not available for calculation and is directly deleted. For the problem of discontinuous occasional data missing, the data of the previous time point is directly used to supplement. For example: SOC: 0.80, 0.79, 0.78, missing, 0.78, then the previous data 0.78 is used to fill. Outlier processing is mainly used to judge SOC. SOC data has the characteristic that big data changes will not occur, such as: 0.80, 0.79, 0.78, 0.83, 0.78. If the data suddenly changes from 0.78 to 0.83, 0.83 is judged to be an outlier, abnormal data, and the previous data is replaced.

[0063] As an optional implementation, in order to more accurately predict tomorrow's predicted discharge depth, the above step 102 is replaced by the following steps 301 to 302, wherein:

[0064] Step 301, divide the daily discharge depths of each year of the analysis period according to the month and the corresponding day of the week in each month, and obtain all daily discharge depths of each week in each month of each year of the analysis period, wherein the daily discharge depth is the discharge depth of a single day.

[0065] In the embodiment of the present application, the week number includes Monday to Sunday. The following is an example of dividing the daily discharge depth in 2022 according to step 301:

[0066] date month Week number Daily discharge depth ... ... ... ... 2022-01-01 January Saturday 0.90 2022-01-02 January Sunday 0.85 2022-01-03 January Monday 0.85 ... ... ... ... 2022-01-31 January Monday 0.70 2022-02-01 February Tuesday 0.65 2022-02-02 February Wednesday 0.60 ... ... ... ...

[0067] Step 302, perform the following processing on the daily discharge depth of each weekday of each month in a year to obtain the average discharge depth of each weekday of each month in a year:

[0068] The daily discharge depths of the same day of the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of the corresponding day of the week of the corresponding month in the year.

[0069] In the embodiment of the present application, the daily discharge depths of the same week number of the same month in all the years of the analysis period are averaged, that is, the sum of all daily discharge depths of the same week number of the same month in all the years of the analysis period is divided by the number of the same week number of the same month in all the years. For example, the analysis period is the three years before the current period. In the three years before, there are 5 Mondays in a certain month of the first year, 3 Mondays in the month of the second year, and 4 Mondays in the month of the third year. Then, the daily discharge depths of 12 (5+3+4) Mondays in the month of the three years before should be summed and divided by the number of Mondays in the month of the three years before, which is 12, to obtain the average discharge depth of Mondays in the month of the year. And by analogy, the average discharge depth from Tuesday to Sunday of the month and the average discharge depth from Monday to Sunday of other months of the year are obtained, that is, the average discharge depth of each day in the year is obtained.

[0070] In the embodiment of the present application, the average discharge depth of each week number of each month and day in a year is obtained, that is, the average discharge depth of each day in a year is obtained. The following is an example of obtaining the average discharge depth of each day in a year according to step 302:

[0071]

[0072] As an optional implementation manner, taking the average discharge depth corresponding to the date of tomorrow as the predicted discharge depth of tomorrow includes:

[0073] According to tomorrow's date, the day of tomorrow is determined, and the average discharge depth of the day of tomorrow in the month in which tomorrow is located is used as the predicted discharge depth of tomorrow.

[0074] As an optional implementation, in order to more accurately predict tomorrow's predicted discharge depth, the above step 102 is replaced by the following steps 401 to 403, wherein:

[0075] Step 401 , dividing the daily discharge depth in each year of the analysis period according to working days and holidays, and obtaining the discharge depth of each working day and each holiday in each year of the analysis period.

[0076] In the embodiments of the present application, the holidays generally refer to statutory holidays, and the dates of the year to which they refer may also be defined according to needs.

[0077] Step 402, divide the discharge depth of each working day in each year of the analysis period according to the month and according to the weekday corresponding to each day of each month, and obtain the discharge depth of all days on each weekday corresponding to the working day of each month in each year of the analysis period; and divide the discharge depth of each holiday in each year of the analysis period according to the month, and obtain the discharge depth of all days on the holiday of each month in each year of the analysis period.

[0078] In the embodiment of the present application, the following is an example of dividing the discharge depth of each day in each year of the analysis period according to step 401 to step 402:

[0079] date month Week number Is it a working day? Daily discharge depth ... ... ... ... ... 2022-01-01 January Saturday no 0.90 2022-01-02 January Sunday no 0.85 2022-01-03 January Monday yes 0.85 ... ... ... ... ... 2022-01-31 January Monday yes 0.70 2022-02-01 February Tuesday yes 0.65 2022-02-02 February Wednesday yes 0.60 ... ... ... ... ...

[0080] Step 403, the following processing is performed on the daily discharge depth of each weekday corresponding to the working day of each month in a year and the daily discharge depth of each holiday in each month in a year to obtain the average discharge depth of each weekday corresponding to the working day of each month in a year and the average discharge depth of each holiday in that month:

[0081] The daily discharge depths of the same weekday corresponding to the working days of the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of the weekday corresponding to the working days of the corresponding month in the year; and the daily discharge depths of holidays in the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of holidays in the corresponding month in the year.

[0082] In the embodiment of the present application, the daily discharge depths of the same weekday corresponding to the working days of the same month in all years of the analysis period are averaged, that is, the daily discharge depths of the same weekday corresponding to the working days of the same month in all years of the analysis period are summed and divided by the number of the same weekday corresponding to the working days of the same month in all years. For example, the analysis period is the first three years of the current period. In the first three years, there are 5 Mondays as working days in a certain month of the first year, 3 Mondays as working days in the month of the second year, and 4 Mondays as working days in the month of the third year. Then, the daily discharge depths of 12 (5+3+4) Mondays as working days in the month of the first three years should be summed and divided by the number of Mondays as working days in the month of the first three years, 12, to obtain the average discharge depth of the Monday corresponding to the working day of the month in the year. The average discharge depth of the Monday that is a working day in the month. By analogy, the average discharge depth from Tuesday to Sunday corresponding to the working day of the month in the year and the average discharge depth from Monday to Sunday corresponding to the working days of other months of the year can be obtained.

[0083] In the embodiment of the present application, the average discharge depth of each weekday corresponding to the working day of each month in a year and the average discharge depth of each holiday of each month in a year are obtained, that is, the average discharge depth of each day in a year is obtained. The following is an example of obtaining the average discharge depth of each day in a year according to step 403:

[0084]

[0085] As an optional implementation manner, taking the average discharge depth corresponding to the date of tomorrow as the predicted discharge depth of tomorrow includes:

[0086] According to tomorrow's date, determine whether tomorrow is a working day or a holiday;

[0087] When tomorrow is a holiday, the average discharge depth of the holidays corresponding to the month in which tomorrow is located is used as the predicted discharge depth of tomorrow;

[0088] When tomorrow is a working day, the day of tomorrow is determined, and the average discharge depth of the day of tomorrow corresponding to the working day of the month in which tomorrow is located is used as the predicted discharge depth of tomorrow.

[0089] In the embodiment of the present application, for example, if tomorrow is New Year's Day in January, the average discharge depth of 0.2 during the holidays in January is used as the predicted discharge depth for tomorrow. For another example, if tomorrow is Monday in January, the average discharge depth of 0.86 during Monday in January is used as the predicted discharge depth for tomorrow.

[0090] In another exemplary embodiment of the present application, in order to further improve the prediction accuracy of tomorrow's predicted discharge depth, the method for predicting tomorrow's electricity demand further includes the following steps 104 to 106.

[0091] in:

[0092] Step 104, after obtaining the predicted discharge depth for tomorrow, determine the predicted deviation rate for each day in the prediction time period according to the predicted discharge depth and the actual discharge depth for each day in the prediction time period.

[0093] In the embodiment of the present application, the prediction time period is not specifically limited and can be set according to actual needs. For example, the m days before the day of predicting the power consumption depth of tomorrow are selected as the prediction time period. According to the predicted discharge depth and the actual discharge depth of each day in the prediction time period, the prediction deviation rate of each day in the prediction time period is determined, that is, the predicted discharge depth of each day is used as the predicted value, and the actual discharge depth of each day is used as the actual value. The predicted value and the actual value are substituted into the calculation formula of the prediction deviation rate to calculate the prediction deviation rate of each day in the prediction time period.

[0094] Step 105: predict tomorrow's prediction deviation rate based on the daily prediction deviation rate within the prediction time period.

[0095] Step 106: correct the predicted depth of discharge for tomorrow using the predicted deviation rate for tomorrow, and use the corrected predicted depth of discharge as the final predicted depth of discharge for tomorrow.

[0096] In the embodiment of the present application, the predicted discharge depth for tomorrow is corrected using the predicted deviation rate for tomorrow, that is, the predicted deviation rate for tomorrow and the predicted deviation rate for tomorrow are substituted into the calculation formula of the predicted deviation rate in step 101, and the actual discharge depth calculated is the final predicted discharge depth for tomorrow.

[0097] As an optional implementation, the prediction deviation rate is calculated according to the following formula:

[0098] Prediction deviation rate = (actual discharge depth - predicted discharge depth) × 100%.

[0099] At this time, when the predicted discharge depth for tomorrow is corrected using the predicted deviation rate for tomorrow, the actual discharge depth=the predicted discharge depth minus the predicted discharge depth after the predicted deviation rate is divided by 100%.

[0100] As an optional implementation, the prediction deviation rate is calculated according to the following formula:

[0101] Prediction deviation rate = actual discharge depth / Predict the depth of discharge.

[0102] At this time, when the predicted discharge depth for tomorrow is corrected by using the predicted deviation rate for tomorrow, the actual discharge depth=the predicted deviation rate multiplied by the predicted discharge depth.

[0103] As an optional implementation, the prediction deviation rate is calculated according to the following formula:

[0104] Prediction deviation rate = predicted discharge depth / Actual depth of discharge.

[0105] At this time, when the predicted discharge depth for tomorrow is corrected by using the predicted deviation rate for tomorrow, the actual discharge depth=the predicted discharge depth divided by the predicted deviation rate.

[0106] In another exemplary embodiment of the present application, predicting tomorrow's prediction deviation rate based on the daily prediction deviation rate within the prediction time period includes:

[0107] The daily predicted deviation rate within the predicted time period is input into the constructed deviation rate prediction model, and the deviation rate prediction model predicts and outputs the predicted deviation rate for tomorrow.

[0108] In the embodiment of the present application, a deviation rate prediction model is constructed, and the daily predicted deviation rate within the prediction time period is used as the input of the model, which can achieve a fast and accurate prediction of tomorrow's predicted deviation rate.

[0109] As an optional implementation, the deviation rate prediction model is constructed according to the following process:

[0110] Step 501, obtain the daily forecast deviation rate in the data collection period, and obtain historical forecast deviation rate data.

[0111] In an embodiment of the present application, the data collection time period is the time period involved in the historical prediction deviation rate data, and the data collection time period is much longer than the time period corresponding to the input data of the deviation rate prediction model, that is, the length of the historical prediction deviation rate data is much longer than the length of the input data of the deviation rate prediction model. There is no specific limitation on the data collection time period and the time period corresponding to the input data, and they can be set according to needs. For example, the daily prediction deviation rate in the 60 days before the day of predicting tomorrow's electricity demand is obtained, and the historical prediction deviation rate data is obtained. Then the data collection time period is the 60 days before the day of predicting tomorrow's electricity demand. The input data of the deviation rate prediction model is the data collected from the historical prediction deviation rate data using the sliding window technology, and the input data of the deviation rate prediction model is the prediction deviation rate for 5 consecutive days in the data collection time period, so as to predict the prediction deviation rate of the 6th day by the prediction deviation rate of the past 5 days.

[0112] Step 502, normalization processing is performed to map the daily prediction deviation rate of day N+1 to the interval [0,1] to improve the training efficiency of the model.

[0113] Step 503, for the historical prediction deviation rate data, a sliding window is used to generate a sample set, and the time step of the sliding window is set to N, so as to predict the prediction deviation rate of the N+1th day based on the prediction deviation rate data of the past N days.

[0114] Step 504: construct an initial model.

[0115] Step 505, divide the sample set into a training set and a test set, use an appropriate loss function (such as mean square error) and optimization algorithm (such as Adam optimizer) to train the initial model, and optimize the initial deviation rate prediction model parameters through multiple iterations.

[0116] Step 506, using a test set to test the trained deviation rate prediction model to evaluate the performance of the deviation rate prediction model, and the deviation rate prediction with good performance is the deviation rate prediction model finally constructed.

[0117] As an optional implementation, in order to improve the prediction accuracy of the predicted deviation rate for tomorrow, the deviation rate prediction model adopts a CNN-LSTM prediction model.

[0118] As an optional implementation, the first layer of the CNN-LSTM prediction model is a convolutional layer, which uses a multi-channel convolution operation to extract the local features of the input feature vector (composed of the daily prediction deviation rate within the prediction time period); then one or more layers of long short-term memory (LSTM) networks are connected to capture the long-term and short-term dependencies in the time series; finally, the fully connected layer is connected to output the prediction result.

[0119] In another exemplary embodiment of the present application, in order to avoid the situation that the user finds that the power is insufficient and cannot complete the work in time when using electricity the next day, that is, tomorrow, or the situation that the charging time is too long and the work cannot be completed smoothly, the method for predicting the power demand for tomorrow also includes:

[0120] Step 107 : after obtaining the predicted discharge depth for tomorrow, when the battery is not charged, if the SOC of the battery obtained in real time is not greater than the predicted discharge depth for tomorrow, reminding the user to charge.

[0121] In the embodiment of the present application, the user can be reminded to charge by SMS, APP, WeChat and other methods, and the specific method can be selected according to the actual needs of the user. The predicted discharge depth for tomorrow can be the predicted discharge depth for tomorrow obtained in step 103, or the final predicted discharge depth for tomorrow obtained after correction in step 106.

[0122] In another exemplary embodiment of the present application, the method for predicting tomorrow's electricity demand, after obtaining the predicted discharge depth for tomorrow, further includes:

[0123] Step 108, after obtaining the predicted depth of discharge for tomorrow, when charging the battery, determine the shortest charging time according to the charging power and the predicted depth of discharge for tomorrow, and ensure that the SOC of the battery is greater than the predicted depth of discharge for tomorrow when the shortest charging time is reached.

[0124] Based on the same inventive concept, the embodiment of the present application also provides a device for predicting tomorrow's electricity demand for implementing the method for predicting tomorrow's electricity demand involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the device for predicting tomorrow's electricity demand provided below can refer to the limitations of the method for predicting tomorrow's electricity demand above, and will not be repeated here.

[0125] In an exemplary embodiment, Figure 2 As shown, a device 60 for predicting tomorrow's electricity demand is provided, comprising:

[0126] A daily discharge depth determination module 601 is used to determine the daily discharge depth of the battery in each year of the analysis period based on the historical discharge data of the battery in the analysis period;

[0127] An average discharge depth determination module 602 is used to determine an average discharge depth per day in a year according to the discharge depth of the battery per day in each year of the analysis period;

[0128] The tomorrow's discharge depth prediction module 603 is used to obtain tomorrow's date, and use the average discharge depth corresponding to tomorrow's date as tomorrow's predicted discharge depth, so as to realize the prediction of tomorrow's electricity demand.

[0129] As an optional implementation manner, the daily discharge depth determination module 601 includes:

[0130] A historical discharge data acquisition module 6011 is used to acquire the historical discharge data of the battery in the analysis period, wherein the historical discharge data includes the start time, start SOC, end time and end SOC of each discharge of the battery;

[0131] A daily discharge times determination module 6012, configured to determine the daily discharge times of the battery in each year of the analysis period according to the start time and end time of each discharge of the battery;

[0132] A single discharge depth calculation module 6013 is used to calculate the discharge depth of each discharge of the battery every day in each year of the analysis period, wherein the discharge depth is the difference between the start SOC and the end SOC of a single discharge of the battery;

[0133] The daily discharge depth calculation module 6014 is used to determine the daily discharge depth of the battery in each year of the analysis period based on the number of daily discharges of the battery in each year of the analysis period and the discharge depth of each daily discharge, including:

[0134] When the battery is discharged only once in a day, the discharge depth of the discharge is taken as the discharge depth of the battery on that day;

[0135] When the battery is discharged multiple times in one day, the discharge depths of all discharges are accumulated as the discharge depth of the battery on that day.

[0136] As an optional implementation manner, the daily discharge depth determination module 601 further includes:

[0137] The data preprocessing module 6015 is used to preprocess the historical discharge data before determining the number of daily discharges of the battery in each year of the analysis period according to the start time and end time of each discharge of the battery. In the embodiment of the present application, the relevant introduction of the preprocessing is detailed in the description of the above method embodiment, which will not be repeated here.

[0138] As an optional implementation, the average discharge depth determination module 602 includes:

[0139] The first grouping module 6021 is used to divide the daily discharge depths of each year of the analysis period according to the month and the corresponding day of the week in each month, so as to obtain all daily discharge depths of each day of the week in each month of each year of the analysis period, wherein the daily discharge depth is the discharge depth of a single day;

[0140] The first discharge depth determination submodule 6022 is used to perform the following processing on the daily discharge depth of each week day of each month in a year to obtain the average discharge depth of each week day of each month in a year:

[0141] The daily discharge depths of the same day of the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of the corresponding day of the week of the corresponding month in the year.

[0142] As an optional implementation, the average discharge depth determination module 602 includes:

[0143] The second grouping module 6023 is used to divide the daily discharge depth in each year of the analysis period according to working days and holidays, and obtain the discharge depth of each working day and each holiday in each year of the analysis period;

[0144] The third grouping module 6024 is used to divide the discharge depth of each working day in each year of the analysis period according to the month and the corresponding weekday of each day in each month, so as to obtain the discharge depth of all days under each weekday of each month in each year of the analysis period; and divide the discharge depth of each holiday in each year of the analysis period according to the month, so as to obtain the discharge depth of all days on holidays of each month in each year of the analysis period;

[0145] The second discharge depth determination submodule 6025 is used to perform the following processing on the daily discharge depths of each weekday of each month that is a working day and the daily discharge depths of each holiday of each month in a year to obtain the average discharge depth of each weekday of each month that is a working day and the average discharge depth of the holiday of the month:

[0146] The daily discharge depths of the same weekday with the same month as a working day in all the years of the analysis period are averaged, and the average value is used as the average discharge depth of the corresponding weekday with the corresponding month as a working day in the year; and the daily discharge depths of holidays in the same month in all the years of the analysis period are averaged, and the average value is used as the average discharge depth of the holidays in the corresponding month of the year.

[0147] As an optional implementation manner, the tomorrow discharge depth prediction module 603 includes:

[0148] The first discharge depth prediction submodule 6031 is used to determine the day of tomorrow according to tomorrow's date, and use the average discharge depth of the day of tomorrow in the month in which tomorrow is located as the predicted discharge depth of tomorrow.

[0149] As an optional implementation manner, the tomorrow discharge depth prediction module 603 includes:

[0150] The second discharge depth prediction submodule 6032 is used to:

[0151] According to tomorrow's date, determine whether tomorrow is a working day or a holiday;

[0152] When tomorrow is a holiday, the average discharge depth of the holidays corresponding to the month in which tomorrow is located is used as the predicted discharge depth of tomorrow;

[0153] When tomorrow is a working day, the day of tomorrow is determined, and the average discharge depth of the day of tomorrow in the month where tomorrow is a working day is taken as the predicted discharge depth of tomorrow.

[0154] As an optional implementation manner, the device 60 for predicting tomorrow's electricity demand further includes:

[0155] A historical prediction deviation rate determination module 604 is used to determine the prediction deviation rate for each day in the prediction time period according to the predicted discharge depth and the actual discharge depth for each day in the prediction time period;

[0156] Tomorrow's prediction deviation rate prediction module 605 is used to predict tomorrow's prediction deviation rate based on the daily prediction deviation rate within the prediction time period;

[0157] The tomorrow's predicted discharge depth correction module 606 is used to correct the tomorrow's predicted discharge depth by using the tomorrow's predicted deviation rate, and use the corrected predicted discharge depth as the final tomorrow's predicted discharge depth.

[0158] In the embodiments of the present application, the relevant introduction of the predicted deviation rate is detailed in the description of the above method embodiments and will not be repeated here.

[0159] As an optional implementation manner, the tomorrow prediction deviation rate prediction module 605 is further used to:

[0160] The daily predicted deviation rate within the predicted time period is input into the constructed deviation rate prediction model, and the deviation rate prediction model predicts and outputs the predicted deviation rate for tomorrow.

[0161] In the embodiments of the present application, the relevant introduction of the deviation rate prediction model is detailed in the description of the above method embodiments, which will not be repeated here.

[0162] As an optional implementation manner, the device 60 for predicting tomorrow's electricity demand further includes:

[0163] The charging reminder module 607 is used to remind the user to charge after obtaining the predicted discharge depth for tomorrow, when the battery is not charged, if the SOC of the battery obtained in real time is not greater than the predicted discharge depth for tomorrow. The predicted discharge depth for tomorrow can be the predicted discharge depth for tomorrow obtained in step 103 of the above method embodiment, or the final predicted discharge depth for tomorrow obtained after correction in step 106.

[0164] As an optional implementation manner, the device 60 for predicting tomorrow's electricity demand further includes:

[0165] The shortest charging time determination module 608 is used to determine the shortest charging time according to the charging power and the predicted discharge depth of tomorrow when the battery is charged, to ensure that the SOC of the battery is greater than the predicted discharge depth of tomorrow when the shortest charging time is reached. The predicted discharge depth of tomorrow can be the predicted discharge depth of tomorrow obtained in step 103 of the above method embodiment, or it can be the final predicted discharge depth of tomorrow obtained after correction in step 106.

[0166] In an exemplary embodiment, a smart battery is provided, which includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the smart battery is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores a computer program and a database. The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. The database of the smart battery is used to store relevant data of a method for predicting tomorrow's electricity demand. The input / output interface of the smart battery is used to exchange information between the processor and its external devices. The communication interface of the smart battery is used for the smart battery to communicate with its external devices through a network connection. When the computer program is executed by the processor, a method for predicting tomorrow's electricity demand is implemented.

[0167] In an exemplary embodiment, a smart battery is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0168] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0169] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0170] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0171] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0172] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0173] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0174] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting tomorrow's electricity demand, characterized in that: The method for predicting tomorrow's electricity demand includes: Determining the depth of discharge of the battery for each day of each year of the analysis period based on historical discharge data of the battery during the analysis period; Determine the average daily depth of discharge in a year based on the daily depth of discharge of the battery in each year of the analysis period; The date of tomorrow is obtained, and the average discharge depth corresponding to the date of tomorrow is used as the predicted discharge depth of tomorrow, so as to realize the prediction of the electricity demand of tomorrow.

2. The method for predicting tomorrow's electricity demand according to claim 1, characterized in that: Determining the average daily depth of discharge in a year according to the daily depth of discharge of the battery in each year of the analysis period includes: Divide the daily discharge depths of each year of the analysis period by month and by the corresponding weekday of each day of each month to obtain all daily discharge depths of each weekday of each month of each year of the analysis period; The following processing is performed on the daily discharge depth of each week day of each month in a year to obtain the average discharge depth of each week day of each month in a year, that is, the average discharge depth of each day in a year: The daily discharge depths of the same day of the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of the corresponding day of the week of the corresponding month in the year.

3. The method for predicting tomorrow's electricity demand according to claim 1, characterized in that: Determining the average daily depth of discharge in a year according to the daily depth of discharge of the battery in each year of the analysis period includes: Dividing the daily discharge depth in each year of the analysis period according to working days and holidays to obtain the discharge depth of each working day and each holiday in each year of the analysis period; Divide the discharge depth of each working day in each year of the analysis period by month and by the corresponding weekday of each day in each month to obtain all daily discharge depths of each weekday corresponding to the working day of each month in each year of the analysis period; and divide the discharge depth of each holiday in each year of the analysis period by month to obtain all daily discharge depths of holidays in each month in each year of the analysis period; The following processing is performed on the daily discharge depth of each weekday corresponding to the working day of each month in a year and the daily discharge depth of each holiday in each month in a year to obtain the average discharge depth of each weekday corresponding to the working day of each month in a year and the average discharge depth of each holiday in each month, that is, the average discharge depth of each day in a year: The daily discharge depths of the same weekday corresponding to the working days of the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of the weekday corresponding to the working days of the corresponding month in the year; and the daily discharge depths of holidays in the same month in all years of the analysis period are averaged, and the average value obtained is used as the average discharge depth of holidays in the corresponding month in the year.

4. The method for predicting tomorrow's electricity demand according to claim 2, characterized in that: The taking the average discharge depth corresponding to the date of tomorrow as the predicted discharge depth of tomorrow includes: According to tomorrow's date, the day of tomorrow is determined, and the average discharge depth of the day of tomorrow in the month in which tomorrow is located is used as the predicted discharge depth of tomorrow.

5. The method for predicting tomorrow's electricity demand according to claim 3, characterized in that: The taking the average discharge depth corresponding to the date of tomorrow as the predicted discharge depth of tomorrow includes: According to tomorrow's date, determine whether tomorrow is a working day or a holiday; When tomorrow is a holiday, the average discharge depth of the holidays corresponding to the month in which tomorrow is located is used as the predicted discharge depth of tomorrow; When tomorrow is a working day, the day of tomorrow is determined, and the average discharge depth of the day of tomorrow corresponding to the working day of the month in which tomorrow is located is used as the predicted discharge depth of tomorrow.

6. The method for predicting tomorrow's electricity demand according to claim 1, characterized in that: Also includes: After obtaining the predicted discharge depth for tomorrow, determining the predicted deviation rate for each day in the predicted time period according to the predicted discharge depth and the actual discharge depth for each day in the predicted time period; Predicting tomorrow's prediction deviation rate based on the daily prediction deviation rate within the prediction time period; The predicted discharge depth for tomorrow is corrected by using the predicted deviation rate for tomorrow to obtain a final predicted discharge depth for tomorrow.

7. The method for predicting tomorrow's electricity demand according to claim 6, characterized in that: The predicting of tomorrow's prediction deviation rate based on the daily prediction deviation rate within the prediction time period includes: The daily predicted deviation rate within the predicted time period is input into the constructed deviation rate prediction model, and the deviation rate prediction model predicts and outputs the predicted deviation rate for tomorrow.

8. The method for predicting tomorrow's electricity demand according to any one of claims 1 to 7, characterized in that: Also includes: After the predicted discharge depth for tomorrow is obtained, when the battery is not charged, if the SOC of the battery acquired in real time is not greater than the predicted discharge depth for tomorrow, the user is reminded to charge.

9. A smart battery, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for predicting tomorrow's electricity demand as described in any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting tomorrow's electricity demand according to any one of claims 1 to 8 are implemented.

Images