Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Short-term load prediction method based on incremental learning

A technology of short-term load forecasting and incremental learning, applied in forecasting, integrated learning, instruments, etc., can solve problems such as concept drift, forecasting model accuracy decline, and forecasting methods are no longer applicable, and achieve the effect of improving forecasting accuracy and realizing updates

Active Publication Date: 2019-07-05
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is a phenomenon of concept drift in load forecasting
As the distribution of load data changes over time, the accuracy of the forecasting model will decrease, and traditional forecasting methods will no longer be applicable

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
  • Short-term load prediction method based on incremental learning
  • Short-term load prediction method based on incremental learning
  • Short-term load prediction method based on incremental learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0051] figure 1 It is a flowchart of the short-term load forecasting method based on incremental learning in the present invention.

[0052] In this example, if figure 1 As shown, a short-term load forecasting method based on incremental learning of the present invention comprises the following steps:

[0053] S1. Build initial dataset and incremental dataset

[0054] Divide the historical load data by season to obtain the historical load data of the four phases of spring, summer, autumn and winter. Since the distribution of spring load data and summer load data is quite different, we mark spring load data as initial data set and summer load data as incremental data. set, and the data of the remaining two stages are not analyzed;

[0055] S2. Use the correlation analysis algorithm to analyze the initial data set and the incremental data set respectively and extract the input load data

[0056] S2.1. Use the correlation analysis algorithm formula to calculate the correlation ...

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 short-term load prediction method based on incremental learning, and the method comprises the steps: building an initial data set and an incremental data set according to thedivision of seasons, carrying out the correlation analysis, extracting input load data, and carrying out the maximum and minimum normalization processing; using an improved Adaboost. RT integration algorithm for training the initial data set and the incremental data set, establishing an initial integration model and an intermediate integration model, and obtaining an evolution integration model on the basis; and finally, inputting to-be-predicted load data into the initial integration model, the intermediate integration model and the evolutionary integration model at the same time, and performing load prediction by applying a maximum entropy principle based on a particle swarm optimization algorithm in combination with a plurality of models.

Description

technical field [0001] The invention belongs to the technical field of power system load forecasting, and more specifically relates to a short-term load forecasting method based on incremental learning. Background technique [0002] With the rapid development of the global economy, the power industry, especially the development of the smart grid, has put forward higher requirements for all departments of the power system from a monopoly operation model to a competitive relationship. Only by conducting comprehensive and detailed research on the data related to load forecasting, formulating efficient and economical power generation plans, and rationally arranging unit output, the power sector can continuously provide users with safe and reliable power, meet the needs of each user, and ensure the safety and stability of the power system operation, and can reduce power generation costs and improve economic efficiency. [0003] At present, the most commonly used load forecasting...

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): G06Q10/04G06Q50/06G06N20/20
CPCG06Q10/04G06Q50/06Y04S10/50
Inventor 匡洪君叶林海盛瀚民白利兵李元元
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com