Monthly electricity sale quantity prediction method and device, terminal and storage medium

Abstract

The invention discloses a monthly electricity sale quantity prediction method and device, a terminal and a storage medium. The method comprises the following steps: acquiring a first prediction variable corresponding to first data, a first prediction variable corresponding to second data, a third prediction variable corresponding to third data, a fourth prediction variable corresponding to fourth data and a fifth prediction variable corresponding to fifth data; and presetting an electricity sale quantity prediction model, and obtaining a target predicted electricity sale quantity according to the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable. The invention aims to accurately predict the monthly electricity sale quantity of the target region.

Description

Technical Field

[0001] The present application relates to the field of power data processing, and in particular to a method, device, terminal and storage medium for predicting monthly power sales. Background Art

[0002] Power business expansion, also known as business expansion or business expansion application, is an important business process in the power industry. It mainly involves power companies providing new power supply services to users or expanding existing power supply services based on the users' electricity demand. Power business expansion data is very important for power companies. It can not only help power companies better understand customer needs, rationally plan grid construction, and improve service quality, but also predict future power demand through analysis of these data, and provide support for the stable development of the power market.

[0003] However, the existing electricity sales forecasting methods have the following shortcomings: electricity sales are affected by multiple factors, such as economic activities, weather conditions, policies and regulations, etc., and there are complex interactions between these factors; at the same time, the existing historical data requires a lot of preprocessing work, such as data cleaning, feature extraction, etc., which are tedious and error-prone; manual forecasting of electricity sales by technicians may be difficult to effectively deal with this problem of multi-factor coupling, and thus it is difficult to accurately predict electricity sales. Summary of the invention

[0004] The main purpose of this application is to provide a monthly electricity sales forecasting method, device, terminal and storage medium, aiming to accurately forecast the monthly electricity sales in a target area.

[0005] To achieve the above purpose, the present application provides a monthly electricity sales forecasting method, which is applied to a monthly electricity sales forecasting system. The monthly electricity sales forecasting system is used to forecast the monthly electricity sales data of a target area under the state of power industry expansion. The method includes:

[0006] Obtaining a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area;

[0007] By presetting the electricity sales volume forecasting model, the target forecasted electricity sales volume is obtained according to the first forecasting variable, the second forecasting variable, the third forecasting variable, the fourth forecasting variable and the fifth forecasting variable.

[0008] Specifically, obtaining a first prediction variable corresponding to a first preprocessing of the first data, a first prediction variable corresponding to a second preprocessing of the second data, a third prediction variable corresponding to a third preprocessing of the third data, a fourth prediction variable corresponding to a fourth preprocessing of the fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of the fifth data includes:

[0009] Acquire the first data, and obtain the first prediction variable according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the first data;

[0010] Obtaining second data, and obtaining the second prediction variable based on the second data, the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the lagged effect of the power industry expansion application capacity in the power industry expansion situation of the target area on the power sales volume of the target area;

[0011] Acquire third data, and obtain the third prediction variable based on the third data and the impact of the temperature change in the target area on the electricity sales in the target area;

[0012] Acquire fourth data, and obtain the fourth prediction variable according to the Spring Festival situation corresponding to the target area and the epidemic situation corresponding to the target area;

[0013] The fifth data is obtained, and the fifth prediction variable is obtained according to the Spring Festival conditions corresponding to the target area, the epidemic conditions corresponding to the target area and the fifth data.

[0014] Specifically, before obtaining the first prediction variable corresponding to the first preprocessing of the first data, the first prediction variable corresponding to the second preprocessing of the second data, the third prediction variable corresponding to the third preprocessing of the third data, the fourth prediction variable corresponding to the fourth preprocessing of the fourth data, and the fifth prediction variable corresponding to the fifth preprocessing of the fifth data, the method further includes:

[0015] According to the Spring Festival conditions, construct the Spring Festival impact factor;

[0016] According to the epidemic situation, an epidemic impact factor is constructed.

[0017] Specifically, obtaining the first prediction variable according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the first data includes:

[0018] Based on the epidemic impact factor and the Spring Festival impact factor, split the first data to obtain a split result, wherein the split result includes the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor;

[0019] Based on the splitting result, the part affected by the epidemic and the part affected by the Spring Festival are eliminated from the first data to obtain the first prediction variable.

[0020] Specifically, the second data includes power industry expansion data and power industry expansion and reduction data, and the second prediction variables include prediction variables corresponding to the power industry expansion data and prediction variables corresponding to the power industry expansion and reduction data;

[0021] The second prediction variable is obtained based on the second data, the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the lagged effect of the power industry expansion application capacity in the power industry expansion situation of the target area on the power sales volume of the target area, including:

[0022] Based on the epidemic impact factor and the Spring Festival impact factor, the power industry expansion data and the power industry expansion and reduction data are split respectively to obtain the split results corresponding to the power industry expansion data and the split results corresponding to the power industry expansion and reduction data, wherein the split results corresponding to the power industry expansion data and the split results corresponding to the power industry expansion and reduction data both include the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor;

[0023] Based on the splitting results corresponding to the power industry expansion data and the splitting results corresponding to the power industry expansion and reduction data, the part affected by the epidemic and the part affected by the Spring Festival are removed from the second data to obtain adjusted second data;

[0024] Determine the weight of lagged power industry expansion based on the lagged effect of the power industry expansion application capacity in the power industry expansion status of the target area on the power sales volume of the target area;

[0025] Based on the lagged power expansion weight and the adjusted second data, the predicted variables corresponding to the power expansion quantity data and the predicted variables corresponding to the power expansion reduction data are calculated.

[0026] Specifically, the target region includes at least one sub-region;

[0027] The obtaining of the third prediction variable based on the third data and the influence of the temperature change in the target area on the power sales volume in the target area includes:

[0028] Determining a temperature division threshold based on the impact of the temperature change of the sub-region on the electricity sales of the sub-region;

[0029] Based on the temperature division threshold, the daily average temperature value of the sub-region in the third data is divided into a daily high-temperature cooling demand value and a daily low-temperature warming demand value;

[0030] The daily high temperature cooling demand value and the daily low temperature warming demand value are converted into the monthly temperature index corresponding to the sub-region by a preset conversion formula;

[0031] The monthly temperature index corresponding to the target area is obtained according to the monthly temperature index corresponding to the sub-area by weighted average method, and the monthly temperature index of the target area is determined as the third prediction variable.

[0032] Specifically, the fifth prediction variable is obtained according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area and the fifth data, including:

[0033] Converting the quarterly GDP data of the target region in the fifth data into monthly GDP data of the target region by linear interpolation;

[0034] Based on the epidemic impact factor and the Spring Festival impact factor, split the monthly GDP data of the target area to obtain a split result, wherein the split result includes the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor;

[0035] Based on the splitting result, the part affected by the epidemic and the part affected by the Spring Festival are eliminated from the monthly GDP data of the target area to obtain the adjusted monthly GDP data, and the adjusted monthly GDP data is determined as the fifth prediction variable.

[0036] To achieve the above purpose, the present application also provides a monthly electricity sales forecasting device, which is applied to a monthly electricity sales forecasting system. The monthly electricity sales forecasting system is used to forecast the monthly electricity sales data of a target area under the state of power industry expansion. The monthly electricity sales forecasting device includes:

[0037] A first unit is used to obtain a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area;

[0038] The second unit is used to obtain a target predicted power sales amount according to the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable by using a preset power sales amount prediction model.

[0039] To achieve the above-mentioned purpose, the present application also provides a terminal, including a memory storing multiple instructions; the processor loads instructions from the memory to execute the steps in any one of the methods provided in the present application.

[0040] To achieve the above objectives, the present application also provides a storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the steps in any method provided in the present application.

[0041] The present application provides a monthly electricity sales forecasting method, device, terminal and storage medium, which can first obtain a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area; then, through a preset electricity sales forecasting model, according to the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable, an accurate target predicted electricity sales volume is finally obtained.

[0042] This application can make an accurate forecast of the monthly electricity sales volume in the target area based on the power industry expansion data through a pre-set electricity sales volume forecasting model. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flowchart of a method for predicting monthly electricity sales provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of a rolling regression method with a fixed origin provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of the one-step-ahead forecast MAPE (%) for some industries provided in the embodiments of the present application;

[0046] Figure 4 A schematic diagram of the structure of a monthly electricity sales prediction device provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] 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 those skilled in the art without creative work are within the scope of protection of this application.

[0049] The existing electricity sales forecasting methods have the following shortcomings: electricity sales are affected by multiple factors, such as economic activities, weather conditions, policies and regulations, etc., and there are complex interactions between these factors; at the same time, the existing historical data requires a lot of preprocessing work, such as data cleaning, feature extraction, etc., which are cumbersome and error-prone; manual forecasting of electricity sales by technical personnel may be difficult to effectively deal with this problem of multi-factor coupling, and thus it is difficult to accurately predict electricity sales.

[0050] Therefore, the embodiments of the present application provide a monthly electricity sales forecasting method, device, terminal and storage medium to solve practical technical problems.

[0051] In some embodiments, the device may be specifically integrated into an electronic device, which may be a terminal, a server or other device.

[0052] In some embodiments, the server may also be implemented in the form of a terminal.

[0053] Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0054] The terminal may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server may be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0055] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0056] An embodiment of the present application provides a monthly electricity sales forecasting method, which can make an accurate forecast of the monthly electricity sales in a target area based on power industry expansion data through a pre-set electricity sales forecasting model.

[0057] In some embodiments, the method is applied to a monthly electricity sales forecasting system, which is used to forecast monthly electricity sales data of a target region under a state of power industry expansion.

[0058] Specifically, the monthly electricity sales forecasting system may include the following parts:

[0059] Data acquisition module:

[0060] First data: characterizes the electricity sales situation in the target area, such as historical electricity sales data; second data: characterizes the expansion of the power industry in the target area, such as the number of new users, new electricity consumption capacity, etc.; third data: characterizes the temperature conditions in the target area, such as average temperature, maximum temperature, minimum temperature, etc.; fourth data: characterizes the electricity price situation in the target area, such as electricity prices in different time periods, changes in electricity price policies, etc.; fifth data: characterizes the gross domestic product situation in the target area, such as GDP growth rate, industrial added value, etc.;

[0061] Data preprocessing module:

[0062] Preprocessing the collected data, including data cleaning, missing value filling, outlier processing, feature extraction, etc., to generate the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable;

[0063] Prediction Model Module:

[0064] Use a preset electricity sales prediction model to make predictions based on the preprocessed prediction variables. The electricity sales prediction model can be any one of linear regression, decision tree, random forest, support vector machine (SVM), and neural network;

[0065] Result output module:

[0066] The output results of the forecasting model are collated and displayed to generate a monthly electricity sales forecast report for the target area.

[0067] like Figure 1 , the specific process of the method can be as follows:

[0068] S110, obtaining a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the electricity industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area.

[0069] In some embodiments, before obtaining the first prediction variable corresponding to the first preprocessing of the first data, the first prediction variable corresponding to the second preprocessing of the second data, the third prediction variable corresponding to the third preprocessing of the third data, the fourth prediction variable corresponding to the fourth preprocessing of the fourth data, and the fifth prediction variable corresponding to the fifth preprocessing of the fifth data, the method further includes steps R1 to R2 as shown below:

[0070] R1. Construct the Spring Festival impact factor based on the Spring Festival conditions.

[0071] In some embodiments, by separately constructing CNY l,m and These three monthly frequency factors are used to measure the impact of the Spring Festival factors before, during and after the festival, so as to construct the Spring Festival impact factor, where l represents the year, l = l1,…,l L, m represents the month, m = 1, 2, ..., 12. In addition, the lengths before the festival (d1), during the festival (d2) and after the festival (d3) can be selected based on the BIC (Bayesian Information Criterion), AIC (Akaike Information Criterion) and the number of outliers in January and February of the x-13 model. The smaller the BIC value, AIC value and the number of outliers in January and February, the better the selected lengths before the festival, during the festival and after the festival. The corresponding intervals before the festival, during the festival and after the festival are [d1 days before New Year's Eve, 1 day before New Year's Eve], [New Year's Eve, (d2-1) days after New Year's Eve] and [d2 days after New Year's Eve, (d3-d2-1) days after New Year's Eve].

[0072] Specifically, the Spring Festival impact factor can be expressed by the following expression:

[0073]

[0074] According to the above expression, through decentralized processing, the Spring Festival can be further obtained as expressed by the following expression:

[0075]

[0076] R2. Construct the epidemic impact factor based on the epidemic situation.

[0077] In some embodiments, Covid l,m to represent the epidemic dummy variable, where l represents the year, l=l1,…,l L , m represents the month, m = 1, 2, ..., 12. The variable value 0 represents the non-epidemic period, and 1 represents the epidemic period (January 2020-December 2022). Therefore, the epidemic virtual variable can be expressed by the following expression:

[0078]

[0079] According to the above-mentioned epidemic virtual variable, the epidemic impact factor is obtained through decentralized processing. The epidemic virtual variable and the epidemic impact factor can be respectively expressed by the following expressions:

[0080]

[0081] In some embodiments, the step of obtaining a first prediction variable corresponding to a first preprocessing of the first data, a first prediction variable corresponding to a second preprocessing of the second data, a third prediction variable corresponding to a third preprocessing of the third data, a fourth prediction variable corresponding to a fourth preprocessing of the fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of the fifth data includes the following steps S111 to S115:

[0082] S111. Obtain first data, and obtain the first prediction variable according to the Spring Festival conditions corresponding to the target area, the epidemic conditions corresponding to the target area, and the first data.

[0083] In some embodiments, the first data may be the monthly electricity sales data y of industry i in period t obtained by summing up the daily electricity sales data of the industry provided by State Grid Electric Power Co., Ltd. in the target area. i,t .

[0084] In some embodiments, the Spring Festival effect and the impact of the epidemic in the first data can be removed through the X13-ARIMA-SEAT seasonal adjustment program.

[0085] X13-ARIMA-SEATS is a widely used seasonal adjustment procedure that combines the ARIMA (Autoregressive Integrated Moving Average) and SEATS (Signal Extraction in ARIMA Time Series) methods to seasonally adjust time series data in order to better analyze and understand the trend and cyclical components of the data.

[0086] Specifically, whether the variance of the first data is stable can be determined based on the time series diagram. When the variance of the first data is heterogeneous, especially when the variance of the first data increases with time, the first data can be log-transformed to help stabilize the variance in the time series. X13-ARIMA-SEATS can also automatically choose whether to perform a log-transform on the first data.

[0087] In some embodiments, obtaining the first prediction variable according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the first data includes the following steps S1111 to S1112:

[0088] S1111. Split the first data based on the epidemic impact factor and the Spring Festival impact factor to obtain a split result, wherein the split result includes the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor.

[0089] Specifically, the epidemic impact factor and the Spring Festival impact factor are input into X13-ARIMA-SEATS, and the first data is split by X13-ARIMA-SEATS to obtain the split results shown below:

[0090]

[0091] Among them, the split results include five parts: growth trend (TR), seasonal fluctuations (M), Spring Festival impact part (CNY), epidemic impact part (Covid) and irregular fluctuations (I).

[0092] S1112. Based on the splitting result, remove the part affected by the epidemic and the part affected by the Spring Festival from the first data to obtain the first prediction variable.

[0093] Continuing with the above embodiment, based on the split result, the Spring Festival impact part (CNY) and the epidemic impact part (Covid) are removed from the first data to obtain the first prediction variable shown below:

[0094]

[0095] S112. Obtain second data, and obtain the second prediction variable based on the second data, the Spring Festival conditions corresponding to the target area, the epidemic conditions corresponding to the target area, and the lagged impact of the power industry expansion application capacity in the power industry expansion conditions in the target area on the power sales volume in the target area.

[0096] In some embodiments, the second data includes electric power industry expansion data and electric power industry expansion and reduction data, and the second prediction variables include prediction variables corresponding to the electric power industry expansion data and prediction variables corresponding to the electric power industry expansion and reduction data.

[0097] In some embodiments, the second data may be monthly business expansion data provided by State Grid Corporation of China in the target area, and the monthly business expansion data flow types include 16 categories. Specifically, the 16 types of business expansion data may be combined into the following two categories: i,t XN i,t (XP i,t With XP i,t are all non-negative values):

[0098] XP i,t = Temporary electricity consumption for high voltage meter installation it +Temporary power supply with low voltage meter it +High Voltage New Installation it + New low voltage residential equipment it + Low voltage non-residential new installationit +Low voltage batch new installation it +Reduction and recovery it + Pause Resume it +High Voltage Capacity Increase it + Low voltage residential capacity increase it + Low voltage non-residential capacity increase it

[0099] XN i,t =Cancel account it +Pause it +Capacity reduction it +Permanent reduction it

[0100] In some embodiments, the second prediction variable is obtained based on the second data, the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the lagged effect of the power industry expansion application capacity in the power industry expansion situation of the target area on the power sales volume of the target area, including the steps S1121 to S1124 as shown below:

[0101] S1121. Based on the epidemic impact factor and the Spring Festival impact factor, the power industry expansion data and the power industry expansion / reduction data are split respectively to obtain the split results corresponding to the power industry expansion data and the split results corresponding to the power industry expansion / reduction data, wherein the split results corresponding to the power industry expansion data and the split results corresponding to the power industry expansion / reduction data both include the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor.

[0102] S1122. Based on the splitting results corresponding to the power industry expansion data and the splitting results corresponding to the power industry expansion and reduction data, remove the part affected by the epidemic and the part affected by the Spring Festival from the second data to obtain adjusted second data.

[0103] In some embodiments, the part affected by the epidemic and the part affected by the Spring Festival can be removed from the second data by X13-ARIMA-SEATS to obtain adjusted second data. The adjusted second data includes and

[0104] S1123. Determine the weight of the lagged power expansion based on the lagged effect of the power expansion application capacity in the power expansion status of the target area on the power sales volume of the target area.

[0105] S1124. Based on the lagged power expansion weight and the adjusted second data, the predicted variables corresponding to the power expansion quantity data and the predicted variables corresponding to the power expansion reduction data are calculated.

[0106] Continuing with the above-mentioned embodiment, considering that the impact of business expansion application capacity on electricity sales has a lag, in order to improve the prediction effect, business expansion variables with lags of 1 to 6 (t-1, t-2, ..., t-6 periods) are taken into consideration for the prediction of electricity sales data at t+h. However, too high a variable dimension will cause overfitting problems. In order to reduce the number of estimated parameters and improve the model prediction ability, business expansion variables with lags of 1 to 6 are integrated in the form of weighted mean, that is, the prediction variables corresponding to the power business expansion increase data and the prediction variables corresponding to the power business expansion decrease data:

[0107]

[0108] in, as well as The lagged power industry expansion weight includes the weight corresponding to the power industry expansion quantity data Weights corresponding to the expansion and reduction data of the power industry

[0109] Specifically, for the weight With weight The calculation of can consider the seven types of weights shown in Table 1 below; one type of weight only considers the first-order lagged business expansion information, the second, third, and fourth types of weight only consider the first to third-order lagged business expansion information, and the fifth, sixth, and seventh types of weight consider the first to sixth-order lagged business expansion information; the second and fifth types of weights assume that with the increase of time distance, the impact of business expansion on electricity sales weakens, the third and sixth types of weights assume that within the third or sixth lag period, the impact of business expansion on electricity sales does not change with the change of time distance, and the fourth and seventh types of weights assume that with the increase of time distance, the impact of business expansion on electricity sales first increases and then weakens. As for the weight With weight The selection of can select the local optimal weight according to the prediction effect of the model on the electricity sales volume in period t+h. Through the origin fixed rolling regression, the MAPE based on the 18-period forecast value is used to select the weight.

[0110]

[0111] Table 1. Weights of lagged power industry expansion

[0112] S113: Acquire third data, and obtain the third prediction variable based on the third data and the impact of the temperature change in the target area on the electricity sales in the target area.

[0113] In some embodiments, the target region includes at least one sub-region.

[0114] Specifically, the target region may be a province, such as Fujian Province, and the sub-region may be any prefecture-level city in the province.

[0115] Continuing with the above embodiment, the third prediction variable is obtained based on the third data and the influence of the temperature change in the target area on the power sales in the target area, including the steps S1131 to S1134 as shown below:

[0116] S1131. Determine a temperature division threshold based on the impact of the temperature change in the sub-region on the electricity sales amount in the sub-region.

[0117] S1132. Based on the temperature division threshold, divide the daily average temperature value of the sub-region in the third data into a daily high-temperature cooling demand value and a daily low-temperature warming demand value.

[0118] S1133. Convert the daily high-temperature cooling demand value and the daily low-temperature warming demand value into a monthly temperature index corresponding to the sub-region through a preset conversion formula.

[0119] S1134. Obtain the monthly temperature index corresponding to the target area according to the monthly temperature index corresponding to the sub-area by weighted average method, and determine the monthly temperature index of the target area as the third prediction variable.

[0120] In some embodiments, the city-level daily average temperature data of nine cities in Fujian Province (daily average temperature = [daily maximum temperature + daily minimum temperature] / 2) can be obtained from the China Weather Network, and the temperature can be calculated by using Tem c,l,m,d It represents the daily electricity sales volume in region c on day d of year l month m.

[0121] Continuing with the above example, the seasonal fluctuation part of the daily electricity sales data provided by Fujian State Grid Electric Power Co., Ltd. is extracted. Specifically, the X13-ARIMA-SEAT seasonal adjustment program is used to extract the monthly electricity sales of region c in month m of year l, y c,l,m , split into three parts: long-term trend, seasonal fluctuation and irregular fluctuation, and then calculate the daily electricity sales volume of area c on day d of year l month m, y c,l,m,d , the medium- and long-term trend part and the irregular fluctuation part are removed, leaving only the adjusted daily electricity sales data containing seasonal fluctuation components And Normal standardization can be expressed by the following expression:

[0122]

[0123] Continuing with the above example, the relationship between the data can be intuitively judged through the scatter plot between the daily power sales and the daily average temperature, and a model can be preliminarily selected to fit the nonlinear relationship between power sales and temperature. Then adjust the parameters to improve the fitting effect of the model, and finally select the temperature value where the marginal effect of daily temperature on daily electricity sales is zero as the temperature division threshold. For example, the nonlinear relationship between electricity sales and temperature can be fitted by polynomial regression. where a1, a2, …, a q is the coefficient of the polynomial model. In addition, based on the visualization of the model fitting effect, model evaluation indicators such as AIC and BIC are used to select the polynomial model order q, and finally the temperature value where the marginal effect of daily temperature on daily electricity sales is zero is selected as the temperature division threshold Tem c,ref Specifically, the temperature division threshold Tem c,ref The regions in Fujian Province are Fuzhou (19.5℃), Xiamen (18.79℃), Putian (21.18℃), Sanming (17.62℃), Quanzhou (16.25℃), Zhangzhou (23.06℃), Nanping (22.39℃), Longyan (23.66℃) and Ningde (21.73℃).

[0124] Continuing with the above embodiment, based on the temperature division threshold, the daily average temperature value of the sub-region in the third data is divided into a daily high temperature cooling demand value and a daily low temperature warming demand value, which can be represented by the following expression:

[0125] HDD c,l,m,d =max{Tem c,ref -Tem c,l,m,d ,0}

[0126] CDD c,l,m,d =max{Tem c,l,m,d -Tem c,ref ,0}

[0127] Among them, the daily high temperature cooling demand value is CDD c,l,m,d The daily low temperature warmth requirement is HDD c,l,m,d .

[0128] Continuing with the above embodiment, the daily high temperature cooling demand value and the daily low temperature warming demand value are converted into the monthly temperature index corresponding to the sub-region through a preset conversion formula. Specifically, the daily temperature index of region C is converted into the monthly temperature index of region C. The preset conversion formula can be expressed by the following expression:

[0129]

[0130] Continuing with the above embodiment, the temperature thresholds and economic levels of different regions are different, so the impact of different urban temperature on the total power sales of the province is different. The monthly temperature index of each urban area is integrated in the form of weighted average to obtain the monthly temperature index of the target area, which can be expressed by the following expression:

[0131]

[0132] Among them, w c It is the cumulative GDP share of region c from the first quarter of 2019 to the second quarter of 2024, and the period t is month m of year l.

[0133] S114. Obtain fourth data, and obtain the fourth prediction variable according to the Spring Festival conditions corresponding to the target area and the epidemic conditions corresponding to the target area.

[0134] Continuing with the above example, the monthly average electricity price of industry i in period t can be calculated by providing the monthly total electricity sales and monthly electricity sales revenue receipts of Fujian State Grid Electric Power Co., Ltd. i,t (Monthly electricity sales revenue / monthly total electricity sales), in RMB / kWh, and the monthly average electricity price of industry i in period t i,t As the fourth data.

[0135] The fourth data can be adjusted using the X13-ARIMA-SEAT seasonal adjustment program to obtain the average electricity price data after removing the impact of the Spring Festival and the epidemic. The average electricity price data as the fourth predictor variable.

[0136] S115. Obtain the fifth data, and obtain the fifth prediction variable according to the Spring Festival conditions corresponding to the target area, the epidemic conditions corresponding to the target area, and the fifth data.

[0137] In some embodiments, obtaining the fifth prediction variable according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the fifth data includes the following steps S1151 to S1153:

[0138] S1151. Convert the quarterly GDP data of the target region in the fifth data into the monthly GDP data of the target region by linear interpolation.

[0139] S1152. Based on the epidemic impact factor and the Spring Festival impact factor, split the monthly GDP data of the target area to obtain a split result, wherein the split result includes the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor.

[0140] S1153. Based on the split result, the part affected by the epidemic and the part affected by the Spring Festival are removed from the monthly GDP data of the target area to obtain adjusted monthly GDP data, and the adjusted monthly GDP data is determined as the fifth prediction variable.

[0141] Continuing with the above-mentioned embodiment, the quarterly GDP data (QGDP) of Fujian Province can be obtained from the Fujian Province Statistical Yearbook and Statistical Yearbook as the quarterly gross domestic product data of the target region in the fifth data.

[0142] The quarterly GDP data (QGDP) can be converted into monthly GDP data GDP by linear interpolation. t , can be expressed by the following expression:

[0143]

[0144] Here, let t be the kth month of quarter Q, k = 1, 2, 3.

[0145] Continuing from the above example, the X13-ARIMA-SEAT seasonal adjustment procedure is used to adjust the monthly GDP data GDP t Adjustments are made to obtain GDP data after removing the Spring Festival effect and the impact of the epidemic. adj , GDPt adj is determined as the fifth predictor variable.

[0146] S120. Obtain a target predicted electricity sales amount according to the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable, and the fifth prediction variable by using a preset electricity sales amount prediction model.

[0147] Continuing with the above embodiment, the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable are incorporated into the preset power sales forecasting model, i.e., a monthly power sales forecasting model for forecasting h periods ahead (h≥1). The monthly power sales forecasting model for forecasting h periods ahead (h≥1) can be expressed by the following expression:

[0148]

[0149] ∈ i,t+h ~N(0,σ2 )

[0150] Among them, α1, α2, …, α 18 is the coefficient of the preset electricity sales prediction model, It is used to measure seasonal fluctuations that are not captured by predictor variables such as temperature. m,t+h It can be expressed by the following expression:

[0151]

[0152] The target predicted electricity sales amount, that is, the monthly predicted electricity sales amount corresponding to each month in the h months ahead, can be obtained through the above-mentioned monthly electricity sales forecasting model with a forecast leading h periods (h≥1).

[0153] In some embodiments, in order to verify the improvement of the power sales forecasting effect by the preset power sales forecasting model that incorporates the business expansion data, the preset power sales forecasting model (M2) is compared with the forecasting model (M1) that does not incorporate the business expansion data, and the baseline model (M0) is also added for comparison.

[0154] The benchmark model M0 is expressed as:

[0155]

[0156] The prediction model (M1) that does not incorporate business expansion data is expressed as:

[0157]

[0158] ∈ i,t+h ~N(0,σ 2 )

[0159] Continuing with the above-mentioned embodiment, the above-mentioned prediction models, namely the preset power sales prediction model (M2), the prediction model (M1) not incorporating the business expansion data, and the benchmark model (M0) are respectively used, and the following are used: Figure 2 The origin-fixed rolling regression method shown in Figure 2 In the figure, the grey squares correspond to the in-sample data, and the black squares correspond to the predicted values ​​h = 3 steps ahead. Figure 2 The rolling regression method with a fixed origin is used to predict the total social electricity sales in Fujian Province for 18 periods from April 2023 to September 2024 with advance h = 1, 2, 3, and calculate the MAPE (mean absolute percentage error). It is known that the smaller the MAPE, the better the model prediction effect, which can be expressed by the following expression:

[0160]

[0161] Among them, APE t =|(predicted value t -True value i ) / True value i |.

[0162] As shown in Table 2 below, in the monthly forecast of total social electricity sales in Fujian Province for 18 periods from April 2023 to September 2024, the MAPE of the forecast model with business expansion variables with h=1, 2, and 3 steps ahead are lower than that of the model without business expansion M1 and the benchmark model M0; at the same time, Figure 3 In the figure, blue corresponds to the preset electricity sales forecast model (M2), green corresponds to the forecast model that does not include business expansion data (M1), and red corresponds to the benchmark model (M0); Figure 3 It can be seen that in the one-step ahead prediction of electricity sales for the whole society, the first, second, third industries, residents' lives, industry, services and green industries, the MAPE of the prediction model including industry expansion variables is also lower than that of the model without industry expansion. This shows that the preset electricity sales forecast model M2 formed by the addition of industry expansion data can improve the accuracy of the forecast of electricity sales for the whole society and obtain accurate target forecast electricity sales.

[0163] Model h＝1 h＝2 h＝3 <![CDATA[M0]]> 2.5547 3.4501 4.0814 <![CDATA[M1]]> 2.8434 3.9659 4.8449 <![CDATA[M2]]> 3.9712 4.3710 4.5298

[0164] Table 2 MAPE of monthly electricity sales forecast for Fujian Province (%)

[0165] In summary, the present application provides a monthly electricity sales forecasting method, which can first obtain a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area; then, through a preset electricity sales forecasting model, according to the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable, an accurate target predicted electricity sales volume is finally obtained.

[0166] In order to better implement the above method, the embodiment of the present application also provides a monthly electricity sales prediction device, which can be integrated in an electronic device, and the electronic device can be a terminal, a server, etc. Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop, a personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers.

[0167] For example, in this embodiment, the method of the embodiment of the present application is described in detail by taking the monthly electricity sales prediction device being specifically integrated in the terminal as an example.

[0168] For example, Figure 4 As shown, the monthly power sales forecasting device 400 may include a first unit 401 and a second unit 402, which are applied to a monthly power sales forecasting system, wherein the monthly power sales forecasting system is used to forecast monthly power sales data of a target area under a power industry expansion state, and the monthly power sales forecasting device 400 includes:

[0169] The first unit 401 is used to obtain a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area;

[0170] The second unit 402 is used to obtain a target predicted power sales amount according to the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable by using a preset power sales amount prediction model.

[0171] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0172] It can be seen from the above that the embodiments of the present application can make an accurate prediction of the monthly electricity sales volume in the target area based on the power industry expansion data through a pre-set electricity sales volume prediction model.

[0173] The embodiment of the present application also provides an electronic device, which can be a terminal, a server, etc. The terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop, a personal computer, etc. The server can be a single server or a server cluster composed of multiple servers, etc.

[0174] In some embodiments, the product processing device may also be integrated into multiple electronic devices. For example, the product processing device may be integrated into multiple servers, and the monthly electricity sales volume forecasting method of the present application may be implemented by multiple servers.

[0175] In this embodiment, the electronic device of this embodiment is a terminal as an example for detailed description, for example, Figure 5 As shown, it shows a schematic diagram of the structure of the terminal 500 involved in the embodiment of the present application, specifically:

[0176] The terminal 500 may include one or more processors 501 of processing cores, one or more storage media 502, a power supply 503, an input module 504, and a communication module 505. Those skilled in the art will appreciate that Figure 5 The structure of the terminal 500 shown in the figure does not constitute a limitation on the terminal 500, and the terminal 500 may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0177] The processor 501 is the control center of the terminal 500. It uses various interfaces and lines to connect various parts of the entire terminal 500. It executes various functions of the terminal 500 and processes data by running or executing software programs and / or modules stored in the memory 502, and calling data stored in the memory 502, so as to monitor the terminal 500 as a whole. In some embodiments, the processor 501 may include one or more processing cores; in some embodiments, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 501.

[0178] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal 500, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0179] The terminal 500 also includes a power supply 503 for supplying power to various components. In some embodiments, the power supply 503 can be logically connected to the processor 501 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 503 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0180] The terminal 500 may further include an input module 504, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0181] The terminal 500 may also include a communication module 505. In some embodiments, the communication module 505 may include a wireless module. The terminal 500 may perform short-range wireless transmission through the wireless module of the communication module 505, thereby providing the user with wireless broadband Internet access. For example, the communication module 505 may be used to help the user send and receive emails, browse web pages, and access streaming media.

[0182] Although not shown, the terminal 500 may also include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 501 in the terminal 500 will load the executable files corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 501 will run the application programs stored in the memory 502, thereby realizing various functions, as follows:

[0183] Obtaining a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area;

[0184] By presetting the electricity sales volume forecasting model, the target forecasted electricity sales volume is obtained according to the first forecasting variable, the second forecasting variable, the third forecasting variable, the fourth forecasting variable and the fifth forecasting variable.

[0185] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0186] It can be seen from the above that the embodiment of the present application can make an accurate prediction of the monthly electricity sales volume in the target area based on the power industry expansion data through a pre-set electricity sales volume prediction model.

[0187] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a storage medium and loaded and executed by a processor.

[0188] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the monthly electricity sales forecasting methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0189] Obtaining a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area;

[0190] By presetting the electricity sales volume forecasting model, the target forecasted electricity sales volume is obtained according to the first forecasting variable, the second forecasting variable, the third forecasting variable, the fourth forecasting variable and the fifth forecasting variable.

[0191] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0192] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a storage medium. A processor of a computer device reads the computer instructions from the storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional implementations provided in the above embodiments.

[0193] Since the instructions stored in the storage medium can execute the steps in any one of the monthly electricity sales forecasting methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the monthly electricity sales forecasting methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0194] The above is a detailed introduction to a monthly electricity sales forecasting method, device, terminal and storage medium provided in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A monthly electricity sales forecasting method, characterized in that: Applied to a monthly electricity sales forecasting system, the monthly electricity sales forecasting system is used to forecast monthly electricity sales data of a target area under a power industry expansion state, the method comprising: Obtaining a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area; By presetting the electricity sales volume forecasting model, the target forecasted electricity sales volume is obtained according to the first forecasting variable, the second forecasting variable, the third forecasting variable, the fourth forecasting variable and the fifth forecasting variable.

2. The method according to claim 1, characterized in that Obtaining a first prediction variable corresponding to a first preprocessing of the first data, a first prediction variable corresponding to a second preprocessing of the second data, a third prediction variable corresponding to a third preprocessing of the third data, a fourth prediction variable corresponding to a fourth preprocessing of the fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of the fifth data, includes: Acquire the first data, and obtain the first prediction variable according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the first data; Obtaining second data, and obtaining the second prediction variable based on the second data, the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the lagged effect of the power industry expansion application capacity in the power industry expansion situation of the target area on the power sales volume of the target area; Acquire third data, and obtain the third prediction variable based on the third data and the impact of the temperature change in the target area on the electricity sales in the target area; Acquire fourth data, and obtain the fourth prediction variable according to the Spring Festival situation corresponding to the target area and the epidemic situation corresponding to the target area; The fifth data is obtained, and the fifth prediction variable is obtained according to the Spring Festival conditions corresponding to the target area, the epidemic conditions corresponding to the target area and the fifth data.

3. The method according to claim 2, characterized in that Before obtaining the first prediction variable corresponding to the first preprocessing of the first data, the first prediction variable corresponding to the second preprocessing of the second data, the third prediction variable corresponding to the third preprocessing of the third data, the fourth prediction variable corresponding to the fourth preprocessing of the fourth data, and the fifth prediction variable corresponding to the fifth preprocessing of the fifth data, the method further includes: According to the Spring Festival conditions, construct the Spring Festival impact factor; According to the epidemic situation, an epidemic impact factor is constructed.

4. The method according to claim 3, characterized in that The obtaining of the first prediction variable according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area and the first data includes: Based on the epidemic impact factor and the Spring Festival impact factor, split the first data to obtain a split result, wherein the split result includes the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor; Based on the splitting result, the part affected by the epidemic and the part affected by the Spring Festival are eliminated from the first data to obtain the first prediction variable.

5. The method according to claim 3, characterized in that The second data includes power industry expansion data and power industry expansion and reduction data, and the second prediction variables include prediction variables corresponding to the power industry expansion data and prediction variables corresponding to the power industry expansion and reduction data; The second prediction variable is obtained based on the second data, the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area, and the lagged effect of the power industry expansion application capacity in the power industry expansion situation of the target area on the power sales volume of the target area, including: Based on the epidemic impact factor and the Spring Festival impact factor, the power industry expansion data and the power industry expansion and reduction data are split respectively to obtain the split results corresponding to the power industry expansion data and the split results corresponding to the power industry expansion and reduction data, wherein the split results corresponding to the power industry expansion data and the split results corresponding to the power industry expansion and reduction data both include the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor; Based on the splitting results corresponding to the power industry expansion data and the splitting results corresponding to the power industry expansion and reduction data, the part affected by the epidemic and the part affected by the Spring Festival are removed from the second data to obtain adjusted second data; Determine the weight of lagged power industry expansion based on the lagged effect of the power industry expansion application capacity in the power industry expansion status of the target area on the power sales volume of the target area; Based on the lagged power expansion weight and the adjusted second data, the predicted variables corresponding to the power expansion quantity data and the predicted variables corresponding to the power expansion reduction data are calculated.

6. The method according to claim 2, characterized in that The target region includes at least one sub-region; The obtaining of the third prediction variable based on the third data and the influence of the temperature change in the target area on the power sales volume in the target area includes: Determining a temperature division threshold based on the impact of the temperature change of the sub-region on the electricity sales of the sub-region; Based on the temperature division threshold, the daily average temperature value of the sub-region in the third data is divided into a daily high-temperature cooling demand value and a daily low-temperature warming demand value; The daily high temperature cooling demand value and the daily low temperature warming demand value are converted into the monthly temperature index corresponding to the sub-region by a preset conversion formula; The monthly temperature index corresponding to the target area is obtained according to the monthly temperature index corresponding to the sub-area by weighted average method, and the monthly temperature index of the target area is determined as the third prediction variable.

7. The method according to claim 3, characterized in that The fifth prediction variable is obtained according to the Spring Festival situation corresponding to the target area, the epidemic situation corresponding to the target area and the fifth data, including: Converting the quarterly GDP data of the target region in the fifth data into monthly GDP data of the target region by linear interpolation; Based on the epidemic impact factor and the Spring Festival impact factor, split the monthly GDP data of the target area to obtain a split result, wherein the split result includes the epidemic impact part corresponding to the epidemic impact factor and the Spring Festival impact part corresponding to the Spring Festival impact factor; Based on the splitting result, the part affected by the epidemic and the part affected by the Spring Festival are eliminated from the monthly GDP data of the target area to obtain the adjusted monthly GDP data, and the adjusted monthly GDP data is determined as the fifth prediction variable.

8. A monthly electricity sales forecasting device, characterized in that: Applied to a monthly electricity sales forecasting system, the monthly electricity sales forecasting system is used to forecast monthly electricity sales data of a target area under the state of power industry expansion, and the monthly electricity sales forecasting device includes: A first unit is used to obtain a first prediction variable corresponding to a first preprocessing of first data, a first prediction variable corresponding to a second preprocessing of second data, a third prediction variable corresponding to a third preprocessing of third data, a fourth prediction variable corresponding to a fourth preprocessing of fourth data, and a fifth prediction variable corresponding to a fifth preprocessing of fifth data, wherein the first data is used to characterize the electricity sales status of the target area, the second data is used to characterize the power industry expansion status of the target area, the third data is used to characterize the temperature status of the target area, the fourth data is used to characterize the electricity price status of the target area, and the fifth data is used to characterize the gross domestic product status of the target area; The second unit is used to obtain a target predicted power sales amount according to the first prediction variable, the second prediction variable, the third prediction variable, the fourth prediction variable and the fifth prediction variable by using a preset power sales amount prediction model.

9. A terminal, characterized in that: The method comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps in the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method according to any one of claims 1 to 7.

Images