Method and device for predicting net load reserve capacity demand based on CatBoost and storage medium

A technology of reserve capacity demand and prediction method, which is applied in the field of net load reserve capacity demand evaluation, to achieve the effect of reducing over-fitting, improving prediction accuracy and improving stability

Pending Publication Date: 2022-07-01
HUNAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The present invention provides a CatBoost-based net load reserve capacity demand forecasting method, device and storage medium to solve the problem that the existing load reserve capacity demand forecasting method is difficult under the action of multiple uncertain factors such as wind / light forecasting and load forecasting. The problem of making accurate predictions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for predicting net load reserve capacity demand based on CatBoost and storage medium
  • Method and device for predicting net load reserve capacity demand based on CatBoost and storage medium
  • Method and device for predicting net load reserve capacity demand based on CatBoost and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] like figure 1 As shown, this embodiment provides a CatBoost-based net load reserve capacity demand forecasting method, and the specific steps are as follows:

[0066] S1: Data set construction and division. Construct a forecast dataset of day-ahead net load spare capacity demand in a northwestern province from 2018 to 2021, including input features x i and the corresponding output feature y i ; the input feature x i =[x i1 ,x i2 ,x i3 ,x i4 ,x i5 ] T It is the time x of the predicted daily history of a province obtained from the power grid control center i1 , month x i2 , solar term x i3 , whether it is a holiday x i4 and load / new energy forecast value x i5 , ; the output feature y i It is the forecast error of daily load / new energy forecast. It should be noted that x i5 When representing the load forecast value, x i =[x i1 ,x i2 ,x i3 ,x i4 ,x i5 ] T Constitute the load error prediction feature information, the corresponding output feature y i r...

Embodiment 2

[0087] This embodiment provides a CatBoost-based net load reserve capacity demand forecasting method, which is different from Embodiment 1 in that: when constructing a training set and a test set, the time series samples before April 12, 2021 are used as training set, using April 12-30, 2021 as the test set. Other principles and processes are the same as those in Embodiment 1, and are not repeated here.

[0088] Adopt the method of the present invention and the traditional method to compare, the evaluation result index comparison result is as shown in Table 2:

[0089] Table 2 Comparison of evaluation results and indicators

[0090]

[0091] From April 12 to 30, 2021, the forecast results of the day-ahead net load reserve capacity demand interval based on CatBoost are as follows Figure 4 As shown in Table 2, in terms of comprehensive indicators, the CatBoost ensemble learning method of the present invention has better performance than the traditional method. In this scen...

Embodiment 3

[0094] This embodiment provides a CatBoost-based net load reserve capacity demand forecasting method, which is different from Embodiment 1 in that: on August 2, 2021, the electricity load of the provincial power grid surged, and on August 1, 2021 The previous time series samples were used as the training set, and the summer heavy load period from August 1 to 7, 2021 was used as the test set, and rolling prediction was performed with a step size of 4h (16 moments). Other principles and processes are the same as those in Embodiment 1, and are not repeated here.

[0095] Adopt the method of the present invention and the traditional method to compare, the evaluation result index comparison result is as shown in Table 3:

[0096] Table 3 Comparison of evaluation results and indicators

[0097]

[0098] From August 1st to 7th, 2021, the forecast results of the daily net load reserve capacity demand interval based on CatBoost are as follows Figure 5 shown, from Figure 5 It ca...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a CatBoost-based net load reserve capacity demand prediction method and apparatus, and a storage medium. The method comprises the steps of obtaining prediction feature information of each prediction point in a to-be-predicted time period; inputting the prediction feature information into a load/new energy prediction error prediction model constructed based on a CatBoost ensemble learning method to obtain a load prediction error and a new energy prediction error corresponding to each prediction point; subtracting the load prediction error of each prediction point from the new energy prediction error to obtain a net load reserve capacity demand prediction result of each prediction point; and under a certain confidence level, obtaining the upper and lower limits of the net load reserve capacity demand prediction interval of each prediction point according to the net load reserve capacity demand prediction error cumulative distribution function. The method can be used for day-ahead and intra-day net load reserve capacity demand evaluation, and is high in prediction stability, accuracy, operation speed and operation efficiency and high in universality.

Description

technical field [0001] The invention relates to the technical field of net load spare capacity demand assessment, in particular to a CatBoost-based net load spare capacity demand prediction method, device and storage medium. Background technique [0002] The reserve demand stems from the uncertainty in the operation of the power grid, and on the one hand, the unpredictable power grid accident (accident reserve). On the other hand, the inaccuracy of supply and demand forecast (load reserve) is mainly due to load forecast errors in traditional power grids. my country's power grid has not yet formed a scientific reserve demand assessment method, and cannot fully consider the upward and downward adjustment resource demand of the power grid caused by the uncertainty of new energy generation power. The power grid backup problem involves operation problems at different levels such as frequency control, safety control and economic dispatch. However, the current backup management mo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/06G06F30/27G06N20/20H02J3/00G06F113/04
CPCG06Q10/04G06Q10/0639G06Q50/06G06F30/27G06N20/20H02J3/003G06F2113/04H02J2203/20
Inventor 文云峰王泽
Owner HUNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products