Adaptive Variable Weight Combination Load Forecasting Method and Device

A combined forecasting and load forecasting technology, applied in forecasting, data processing applications, instruments, etc., can solve problems such as low accuracy, and achieve the effects of high accuracy, adaptability and flexibility

Inactive Publication Date: 2021-11-16
BEIJING KEDONG ELECTRIC POWER CONTROL SYST +1
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of this, the purpose of the present invention is to provide an adaptive variable weight combined load forecasting method and device to alleviate the technical problem of low accuracy in the combined forecasting method in the prior art

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
  • Adaptive Variable Weight Combination Load Forecasting Method and Device
  • Adaptive Variable Weight Combination Load Forecasting Method and Device
  • Adaptive Variable Weight Combination Load Forecasting Method and Device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] An adaptive variable weight combination load forecasting method, refer to figure 1 , the method includes:

[0064] S102. Day-ahead load forecasting modeling based on multiple forecasting methods to obtain multiple single day-ahead load forecasting models.

[0065] Among them, the single day-ahead load forecasting model includes the average growth rate forecasting model, the linear quadratic moving average model, the cubic exponential smoothing forecasting model and the gray system theory forecasting model.

[0066] In the embodiment of the present invention, the following four forecasting methods are selected as the basis of combined forecasting, mainly because the method is simple and easy to implement, historical data is easy to obtain, and it has the advantages of high forecasting accuracy. After the verification of the actual electricity consumption data, the errors of the four prediction methods alone can be controlled within 20%.

[0067] (1) Average growth rate...

Embodiment 2

[0171] An adaptive variable weight combination load forecasting device, refer to figure 2 , the device consists of:

[0172] The first modeling module 11 is used for day-ahead load forecasting modeling based on multiple forecasting methods to obtain multiple single day-ahead load forecasting models.

[0173] Wherein, the single day-ahead load forecasting model includes an average growth rate forecasting model, a linear quadratic moving average model, a cubic exponential smoothing forecasting model, and a gray system theory forecasting model.

[0174] The second modeling module 12 is configured to establish a day-ahead load combination forecast model based on multiple single day-ahead load forecast models.

[0175] A weight updating module 13, configured to update the weight of the day-ahead load combination forecasting model based on reinforcement learning.

[0176] Further, the weight update module is specifically used to: take the weight coefficient of the single day-ahea...

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 present invention provides an adaptive variable weight combined load forecasting method and device, which relate to the technical field of power system load forecasting, so as to alleviate the technical problem of low accuracy in the combined forecasting method in the prior art, and improve the accuracy of combined forecasting. And it has the characteristics of simple data requirements, strong flexibility, and adaptability. The adaptive variable weight combined load forecasting method includes: day-ahead load forecasting modeling based on multiple forecasting methods to obtain multiple single day-ahead load forecasting models; building a day-ahead load combined forecasting model based on multiple single day-ahead load forecasting models; The weights of the day-ahead load combination forecasting model are updated.

Description

technical field [0001] The invention relates to the technical field of power system load forecasting, in particular to an adaptive variable weight combined load forecasting method and device. Background technique [0002] With the continuous expansion of the scale of the power system, the structure and operation mode of the power grid become more and more complex. Effectively improving and ensuring the safety and reliability of power systems, power supply quality and operating economy has become an important goal of power system development, and the importance of load forecasting is becoming more and more prominent. How to realize accurate and reliable day-ahead load forecasting has become a universal problem. [0003] Under the market condition of separation of power distribution and sales, traditional power supply companies, power generation companies, and social asset enterprises can apply for and invest in the establishment of electricity sales companies to carry out el...

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 Patents(China)
IPC IPC(8): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06
Inventor 高春成方印史述红代勇顾宇桂刘永辉刘冬汪涛袁明珠王海宁王春艳张琳习培玉吴雨健吕俊良张倩王蕾王清波袁晓鹏李瑞肖万舒路董武军李守保陶力承林赵显谭翔吕文涛刘杰
Owner BEIJING KEDONG ELECTRIC POWER CONTROL SYST
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap