Power load prediction method and system

Abstract

The invention provides a power load prediction method and system, and relates to the field of meteorological and power research, and the method comprises the following steps: S1, obtaining load data and meteorological data in recent two years, and carrying out the date type marking of the data; s2, respectively constructing training data sets for different dates in a short period to carry out training, and obtaining prediction models of the corresponding dates; s3, acquiring input data for carrying out short-term load prediction; and S4, respectively inputting the data obtained in the S3 into corresponding prediction models to obtain a short-term load prediction result. According to the method, power load data of two years in the past and meteorological data in a corresponding time period are utilized to redefine a day time range, working days and non-working days are distinguished, a LightGBM machine learning method is adopted to carry out learning training on short-term power load changes, and power load prediction of 15 minutes per 15 minutes in three days in the future is obtained. The output power load prediction is more accurate and fine, and powerful support is provided for the business decision of the power department.

Description

Technical Field

[0001] The present invention relates to the field of power load forecasting, and in particular to a power load forecasting method and system. Background Art

[0002] With the development of the economy and the acceleration of urbanization, the demand for electricity continues to grow. The supply and demand of electric energy is closely related to weather changes. High temperature, low temperature, dryness and wetness often affect the grid dispatching and control strategy. Wind and light conditions determine the output capacity of new energy. Accurate grid load forecasting is a key factor in ensuring energy supply. In recent years, with the increase in photovoltaic access capacity, the impact of meteorological and other factors on load has become increasingly significant. The efficient operation of new power systems will increasingly rely on the assessment and prediction capabilities and integration level of meteorological factors. The existing algorithm for predicting power load is an artificial intelligence-based power load forecasting method, which can reduce the impact of noise data on the prediction results and improve the accuracy of power load forecasting.

[0003] In the related technology, an application document with publication number CN118520428A discloses an artificial intelligence-based power load forecasting method, which includes: fitting the load data in the acquired historical power load data segment, determining the extreme points of the fitting curve, and then calculating the initial noise level of the historical power load data segment, and the initial noise level of the corresponding historical power grid frequency data segment, as well as the correlation between the historical power load data segment and the corresponding historical power grid frequency data segment to correct the initial noise level, and obtain the final noise level of the historical power load data segment, so as to use the final noise level of each historical power load data segment to weight the predicted value determined by the corresponding historical power load data segment to obtain the final predicted value.

[0004] However, power load is closely related to meteorological factors. The above scheme only uses historical power load data for fitting training. The prediction system only considers the inherent laws of the load, and does not consider the impact of changes in meteorological factors such as temperature, precipitation, and humidity on power load changes. This, to a certain extent, limits the improvement of the accuracy of load forecasting. Summary of the invention

[0005] The object of the present invention is to provide a method and system for predicting electric load.

[0006] According to a first aspect of an embodiment of the present invention, there is provided a method for predicting power load, comprising the following steps:

[0007] S1. Obtain load data and meteorological data in the past two years and mark the data with date type;

[0008] S2. Construct training data sets for different dates in a short period of time and conduct training to obtain prediction models for the corresponding dates;

[0009] S3. Obtain input data for short-term load forecasting;

[0010] S4. Input the data obtained in S3 into the corresponding prediction models to obtain short-term load prediction results.

[0011] According to a first aspect of an embodiment of the present invention, there is provided a power load forecasting system, comprising:

[0012] The historical data acquisition module is used to obtain load data and meteorological data in the past two years and mark the data with date type;

[0013] The model acquisition module is used to construct training data sets for different dates in a short period of time to carry out training and obtain the prediction model for the corresponding date;

[0014] A forecast input data acquisition module is used to acquire input data for short-term load forecasting;

[0015] The load forecast result acquisition module is used to input the forecast input data into the corresponding forecast model to obtain the short-term load forecast result.

[0016] The beneficial effects of the present invention are:

[0017] The power load forecasting method and system of the present invention utilizes the correlation between load and weather elements, applies machine learning algorithms, explores the influence of weather on load, and accurately forecasts short-term power load based on numerical weather forecasts. Based on accurate forecasts, the power sector can formulate load response plans for different scenarios based on load forecasts, increase the scale of adjustable load resource pools, participate in distribution network operation regulation, effectively alleviate the pressure of peak shaving and valley filling of the power grid, maintain power supply balance, and ensure normal power consumption in society. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a flow chart of the power load forecasting method of the present invention;

[0020] Figure 2 is a short-term load forecasting result in an embodiment of the present invention;

[0021] Figure 3 is a schematic diagram comparing the prediction result and the actual load situation in an embodiment of the present invention;

[0022] Figure 4 It is a schematic diagram of the comparison between the forecast and actual load from August 16 to 31, 2024 in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The technical solution of the present invention is described in detail below with reference to the accompanying drawings and specific implementation cases. It should be noted that the embodiments described here are only used for illustration and are not intended to limit the present invention.

[0024] Reference Figure 1 In one embodiment of the present invention, the power load forecasting method and system include the following steps:

[0025] S1: Obtain load data and meteorological data for the past two years and mark the data with date type.

[0026] In this embodiment, the past two years refers to two years counting backward from the current day.

[0027] Specifically, the load data is the real-time historical data of the power dispatching load, and the time resolution of the data is 5 minutes; the meteorological data is the real-time historical data of the meteorological conditions in the same period as the load data, including: temperature TEM, precipitation RAIN, and humidity RH.

[0028] Furthermore, considering the significant difference in power load between weekdays and holidays, all data need to be marked with date type.

[0029] Specifically, the method of marking the date type of the data is: mark working days (such as ordinary Monday to Friday) as 0; mark holidays that are not ordinary Saturdays as 1 (such as Sundays and statutory holidays such as the Spring Festival, Qingming Festival, Dragon Boat Festival, May Day, Mid-Autumn Festival, National Day, New Year's Day, etc.); ordinary Saturdays are marked as 6, and if Saturday happens to be the above-mentioned Spring Festival, Qingming Festival, etc. holidays, it is marked as 1.

[0030] S2: Construct training data sets for different dates in a short period of time and conduct training to obtain prediction models for the corresponding dates.

[0031] Because the marketing decision-making department of the power company focuses on short-term load changes, in this embodiment, the short-term is taken as the next three days, so it is necessary to predict the load changes every 15 minutes in the next three days. In this embodiment, the time range of each day is defined as "08:00 on the first day to 08:00 on the second day".

[0032] Taking into account that the load change patterns in different time periods are different, in this embodiment, corresponding power load forecasting models are established for dates in the short term, that is, the models for predicting the load of "today", "tomorrow" and "the day after tomorrow" are model 1, model 2 and model 3 respectively, and the training data sets input into different models are different.

[0033] Taking model 1 as an example, the method of constructing a training data set includes:

[0034] For the load situation of the day, the actual business operation is "today" and the date is set to t. Collect the actual data of the same period last year and the recent period respectively:

[0035] 1. Go back to the same period last year, i.e. t-1y (y is year); and go forward one month, i.e. t-1y-1m (m is month); take t-1y-1m as the starting time point, and obtain load data for two months in the future, with the time range of t-1y-1m to t-1y+1m. This is equivalent to obtaining the load data data1 for the past two months before and after the same period last year;

[0036] 2. Take the previous day (t-1) as the benchmark, and trace back two months, that is, t-1-2m; and use this as the starting time to collect load data for two consecutive months, with the time range: t-1-2m~t-1. This is equivalent to obtaining the load data data2 within the most recent two months;

[0037] 3. Combine data1 and data2 to form a load data set with similar climate background conditions to "today". This data set includes the load conditions of the same period last year and the recent load conditions.

[0038] Take the collected load data set as the target data and find other data sets that are directly related to the target data:

[0039] 1. Considering the obvious daily variation characteristics of load changes, obtain the number of minutes corresponding to the time span of the target data. For example, the number of minutes corresponding to the target load value at 14:00 on a certain day is 840, that is, 14×60.

[0040] 2. Obtain meteorological data at the same time period and time point as the target data, including TEM, RAIN and RH.

[0041] 3. Considering that the load on working days can better represent the actual situation of social production and living electricity consumption, and the actual load changes continuously, the load situation on the day (d) is not only related to the meteorological conditions of the day, but also closely related to the load and weather changes of the previous few days. Therefore, the load and weather conditions of the five most recent historical working days before the day are obtained.

[0042] For example, for the target load value P at 14:00 on a certain day, if the previous 5 days are exactly 5 consecutive historical working days, then the associated data includes P, TEM, RAIN and RH at 14:00 on d-5, d-4, d-3, d-2 and d-1 in addition to TEM, RAIN and RH at that time on the same day. If one or more days between d-5 and d-1 are non-working days, for example, d-5 and d-4 are Saturday and Sunday respectively, then the 5 historical working days are d-7, d-6, d-3, d-2 and d-1.

[0043] 4. Read the date type data corresponding to the current date of the target data, that is, 0, 1, or 6, as the last associated data.

[0044] 5. Arrange the target load data and all the associated data accordingly to form a training data set for model 1. In this embodiment, the data set is optionally arranged in order, in the following order: minutes, date type data, meteorological data at the same time period and time point as the load data (in order of TEM, RAIN, RH), and historical data of the above five historical working days, where the historical data of each working day is P, TEM, RAIN, and RH in order. The time resolution of the data set is 5 minutes.

[0045] In this embodiment, the basic idea of ​​constructing the training data set of Model 2 and Model 3 is the same as that of Model 1, except that in "obtaining the load and weather conditions of the five most recent historical working days before today", Model 2 and Model 3 respectively take the P, TEM, RAIN and RH data of the working days before d-1 and d-2. The reason is that in Model 2, if you want to predict the load of "tomorrow" (d), the load of "today" (d-1) is still unknown, so you can only use the historical data of the five historical working days before "yesterday" (d-1). Similarly, for Model 3, if you want to predict the load of "the day after tomorrow" (d), the loads of "today" (d-2) and tomorrow (d-1) are unknown, so you can only use the data of the five historical working days before "yesterday" (d-2) to correspond to the target load data.

[0046] In this embodiment, the method for training the model includes:

[0047] Use python to call the LightGBM package as the model framework for machine learning. The parameters of the model can be set as follows: the boost type is "bdbt", the objective function is "regression", the evaluation function is "rmse", the number of leaf nodes is set to 100, the learning rate is set to 0.1, the feature selection ratio for tree building is 0.9, the sample sampling ratio for tree building is 0.8, the number of trees in the model is 2000, the maximum depth of the tree is set to 10, the frequency of integrated learning during training is 5, and other settings are set to default values. The training data sets of each model are input into the framework for learning and training, so as to obtain the load forecasting model based on the corresponding relationship between power load and meteorological factors and the changes in the first 5 consecutive working days. Then the trained models 1, 2 and 3 are obtained.

[0048] S3: Obtain input data for short-term load forecasting.

[0049] After the power load forecasting model is established, the latest numerical weather forecast product is read and the short-term forecast data is input into the model to obtain the power load forecast results within three days. The specific steps are as follows:

[0050] 1. Read the latest numerical weather forecast

[0051] Read site forecast data from the meteorological big data cloud platform every day. For example, obtain site forecast data with the code NAFP_FOR_FTM_LOW_RIOF_JS from the data platform of Jiangsu Meteorological Bureau. The forecast time is 0 to 72 hours, and the time resolution is 3 hours. This data product is updated twice a day at 08:00 in the morning and 20:00 in the evening. The forecast elements used are TEM, RAIN and RH. Because the load forecast results for each 15 minutes are required, the forecast is linearly interpolated to form the TEM, RAIN and RH forecast data for each 15 minutes in the next 72 hours.

[0052] 2. Construct input data sets for different models

[0053] For Model 1, the steps to construct the data are as follows:

[0054] 1. Calculate the number of minutes from "today" 08:00 to "tomorrow" 08:00 for every 15 minutes, for example, the number of minutes at 14:00 is 840;

[0055] 2. Extract the part of the forecast data in step 1 that falls within the time range of "today", specifically from 08:00 "today" to 08:00 "tomorrow";

[0056] 3. Obtain the real-time data of P, TEM, RAIN and RH every 15 minutes for the five most recent historical working days before "today" (t), with the start and end time of each day's data being from 08:00 on the current day to 08:00 on the next day;

[0057] 4. According to the date attribute of "today", get the day type data of "today", that is, 0, 1, or 6;

[0058] 5. Summarize all the data in steps 1 to 4 and arrange them in a certain time and order. The arrangement style is consistent with the arrangement order of the training data set in S2.

[0059] For Model 2 and Model 3, the input data sets are similar to the above steps, with the main differences being that in step 2, the forecast data for "tomorrow" and "the day after tomorrow" in the forecast data of step 1 are intercepted respectively; in step 3, the P, TEM, RAIN and RH data for each of the five historical working days before t-1 (in model 2, "tomorrow" is t) and before t-2 (in model 3, "the day after tomorrow" is t) are obtained respectively; in step 4, the day type data for "tomorrow" and "the day after tomorrow" are obtained respectively.

[0060] S4: Input the data obtained in S3 into the corresponding prediction models to obtain short-term load prediction results.

[0061] Input the data set obtained in S3 into the corresponding model, and automatically obtain the 15-minute load forecast results for "today", "tomorrow" and "the day after tomorrow". Connect these three parts of forecast data in sequence to obtain the short-term power load forecast for the next three days. The forecast results can be automatically generated into Excel files or txt files, or they can be automatically exported as follows: Figure 2 The picture shown is displayed in real time, making the prediction results more intuitive and easier to transmit.

[0062] While realizing the power load forecasting within the next three days based on the LightGBM algorithm, the present invention also provides an automatic verification function for the prediction results, and the verification results can be generated synchronously with the prediction results. Assuming that the power department is concerned about the forecast for the next day every day, the prediction results of "tomorrow" in the output of the prediction model are mainly verified. Assuming that the current day (today) is t, the specific steps are:

[0063] 1. Retrieve the actual load data of yesterday (t-1) for every 5 minutes;

[0064] 2. Retrieve the 15-minute load forecast data for the next day (t-1) reported from the day before yesterday (t-2), which is consistent with the actual load data date in step 1;

[0065] 3. Obtain the actual load data corresponding to the 15-minute load forecast data time, and use the following method: Figure 3The graphical form shown in the figure directly compares the actual and predicted curves, and the root mean square error (RMSE) and mean absolute percentage error (MAPE) between the two can also be calculated. The calculation formulas are as follows:

[0066]

[0067] See also Figure 4 ,As can be seen from the figure, the load forecast during the high temperature period from August 16 to 31 2024 is more accurate, with an average accuracy of 97.4%, and the average prediction accuracy of the daily maximum load value is 97.6%.

[0068] Based on the above embodiment, an embodiment of the present invention further provides a power load forecasting system, including:

[0069] The historical data acquisition module is used to obtain load data and meteorological data in the past two years and mark the data with date type;

[0070] The model acquisition module is used to construct training data sets for different dates in a short period of time to carry out training and obtain the prediction model for the corresponding date;

[0071] A forecast input data acquisition module is used to acquire input data for short-term load forecasting;

[0072] The load forecast result acquisition module is used to input the forecast input data into the corresponding forecast model to obtain the short-term load forecast result.

[0073] In this embodiment, the working process of each module is as described above and will not be repeated here.

[0074] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A method for predicting power load, characterized in that: The following steps are involved: S1. Obtain load data and meteorological data in the past two years and mark the data with date type; S2. Construct training data sets for different dates in a short period of time and conduct training to obtain prediction models for the corresponding dates; S3. Obtain input data for short-term load forecasting; S4. Input the data obtained in S3 into the corresponding prediction models to obtain short-term load prediction results.

2. The power load forecasting method according to claim 1, characterized in that: In step S1, the load data is the real-time historical data of the power dispatching load, and the time resolution of the data is 5 minutes; the meteorological data is the real-time historical data of the meteorological data in the same period as the load data, including: temperature TEM, precipitation RAIN, and humidity RH.

3. The power load forecasting method according to claim 2, characterized in that: The method for marking the data by date type includes: marking a working day as 0, marking a holiday that is not an ordinary Saturday as 1, and marking an ordinary Saturday as 6.

4. The power load forecasting method according to claim 3, characterized in that: In step S2, the method for constructing a training data set includes: obtaining target data and associated data; wherein the method for obtaining target data includes: Get the load data data1 for the past two months before and after the same period last year; Get the load data data2 for the last two months; Merge data1 and data2 as the target data; and The method for obtaining associated data includes: Get the number of minutes corresponding to the time span of the target data; Obtain meteorological data at the same time period and time point as the target data, including TEM, RAIN and RH; Get the load and weather conditions of the last five historical working days before today; Read the date type data corresponding to the current date of the target data, that is, 0, 1, or 6, as the last associated data; The target load data and all associated data are collated to form a training data set.

5. The power load forecasting method according to claim 4, characterized in that: In step S2, the method for training the model includes: Use Python to call the LightGBM package as the model framework for machine learning and set model parameters; The training data sets of each model are input into the framework for learning and training respectively, so as to obtain the prediction model of the corresponding date after training.

6. The power load forecasting method according to claim 5, characterized in that: In step S3, the method for obtaining input data for carrying out short-term load forecasting includes: reading the latest numerical weather forecast and constructing input data sets of different models respectively; The method for constructing input data sets of different models includes: Calculate the number of minutes from 08:00 of the "same day" to 08:00 of the "next day" for every 15 minutes; Extract the part of forecast data that falls within the "today" time range; Get the 15-minute real-time data of P, TEM, RAIN and RH for the five most recent historical working days before "today". The start and end time of each day's data is from 08:00 on the day to 08:00 on the next day. According to the date attribute of "this day", get the day type data of "this day", that is, 0, 1, or 6; The data of each day to be predicted in the short term are summarized separately and arranged in a certain time and sequence to obtain the input data sets of different models.

7. The power load forecasting method according to claim 6, characterized in that: In step S4, the data collected in S3 is sorted into the same format and order as the associated data in the training model, and input into the corresponding model according to different time periods, so as to obtain the short-term 15-minute load forecast results. The forecast data in different time periods are arranged in order, and finally the short-term power load forecast results for the next three days can be obtained.

8. The power load forecasting method according to claim 7, characterized in that: Step S4 also includes: checking the forecast situation of the previous day; The method for testing the forecast situation of the previous day includes: Retrieve yesterday's 5-minute load actual data; Retrieve the 15-minute load forecast data for the next day reported from the day before yesterday; Take the actual load data corresponding to the 15-minute load forecast data time, and verify it through one or more methods of curve comparison, calculation of error root mean square error or calculation of mean absolute percentage error.

9. A power load forecasting system, characterized in that: include: The historical data acquisition module is used to obtain load data and meteorological data in the past two years and mark the data with date type; The model acquisition module is used to construct training data sets for different dates in a short period of time to carry out training and obtain the prediction model for the corresponding date; A forecast input data acquisition module is used to acquire input data for short-term load forecasting; The load forecast result acquisition module is used to input the forecast input data into the corresponding forecast model to obtain the short-term load forecast result.

Images