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

Large-scale load adjustment prediction method applying machine learning

A large-scale, load forecasting technology, applied in forecasting, data processing applications, special data processing applications, etc., can solve problems such as inability to function and increase consumption of computing resources, to improve forecast accuracy, reduce complexity, and achieve Simple and practical effects

Active Publication Date: 2018-05-08
CHINA SOUTHERN POWER GRID COMPANY
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the problem scale is very large, the above solution may not be effective, because the number of elements of the kernel function matrix is ​​equal to the square of the number of training set samples, which will consume a large amount of computer memory to store the kernel function numerical matrix
In smart grid cloud storage, its power load data is not only massive, but also high-dimensional, which increases the consumption of computing resources

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
  • Large-scale load adjustment prediction method applying machine learning
  • Large-scale load adjustment prediction method applying machine learning
  • Large-scale load adjustment prediction method applying machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] The schematic diagram of the method of the present invention is as figure 1 As shown, the large-scale load forecasting method of the application of machine learning in the present invention.

[0029] Using the MapReduce programming framework, it is different from the traditional ε-SVR load forecasting algorithm that trains all the training set data on a single machine. This load forecasting algorithm divides the training set data into multiple data subsets. Each data subset is trained on a single machine, and the local results of the Map stage are integrated in the Reduce stage. Under the premise of ensuring the accuracy of forecasting, it overcomes the problem of insufficient single-computer computing resources that tends to occur when load forecasting is performed on massive high-dimensional data in smart grids.

[0030] In addition, the distributed data storage strategy of the algorithm also directly affects the performance of the algorithm. This paper proposes to u...

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 provides a large-scale load adjustment prediction method applying machine learning. The method comprises the following steps: 1) training set segmentation; 2) bias term processing; and 3) result processing. The accumulated historical load data are fully utilized so that the accuracy of short-period load prediction can be enhanced, the load prediction speed can be enhanced, and the load prediction demand required for daily scheduling operation and electricity purchasing and selling can be met in time.

Description

technical field [0001] The invention belongs to the field of electric power dispatching automation. The invention relates to a large-scale ground regulation load forecasting method using machine learning, especially a large-scale ground load forecasting method using machine learning, which belongs to the large-scale ground load forecasting method using machine learning. Innovative techniques for load forecasting methods. Background technique [0002] Load forecasting is the basic work of power system planning, planning, power consumption, dispatching and other departments, and its importance has long been recognized by people. At present, the main starting point of the research on load forecasting is to improve the accuracy of forecasting with more advanced theories, and to provide a strong guarantee for the economy and safety of power system operation. [0003] Load forecasting is an important basis for many other analysis and calculation tasks. It is an important means of...

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): G06Q10/04G06Q50/06G06F17/30G06K9/62
CPCG06F16/27G06Q10/04G06Q50/06G06F18/214G06F18/2411Y04S10/50
Inventor 梁寿愚方文崇黄雄何超林朱文周志烽
Owner CHINA SOUTHERN POWER GRID COMPANY
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