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

Power load prediction method based on improved dragonfly and lightweight gradient boosting tree model

A gradient boosting tree and power load technology, applied in power load forecasting and information fields, can solve problems such as low power load forecasting accuracy

Pending Publication Date: 2022-06-03
NANJING TECH UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem of low power load forecasting accuracy, the present invention provides a power load forecasting method based on the improved dragonfly and lightweight gradient boosting tree model

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
  • Power load prediction method based on improved dragonfly and lightweight gradient boosting tree model
  • Power load prediction method based on improved dragonfly and lightweight gradient boosting tree model
  • Power load prediction method based on improved dragonfly and lightweight gradient boosting tree model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] combine figure 1 , the present invention performs power load prediction based on the improved dragonfly and the lightweight gradient boosting tree model, including the following steps:

[0071] A. Collected data processing, data preprocessing includes missing value processing, data normalization, outlier processing and data discretization. And divide training set and test set

[0072] B. The LightGBM model adopts the histogram-based decision tree algorithm. First, the continuous floating-point features in the sample are discretized into k integers, and a histogram with a width of k is constructed. Then when traversing the data, use the discretized value as an index to accumulate statistics in the histogram. After one traversal, the histogram accumulates the required statistics, and finally find the best through the discrete value traversal of the histogram. split point. In this way, large-scale data is placed in the histogram, which makes the memory footprint smaller...

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 power load prediction method based on a dragonfly and lightweight gradient boosting tree model introducing an adaptive learning factor and a differential evolution strategy, and relates to the technical field of information. The method comprises the following steps: firstly, performing data preprocessing, including missing value processing, data normalization, abnormal value processing and data normalization; the improved dragonfly algorithm is used for optimizing parameters of the lightweight gradient boosting decision tree model, and the improved lightweight gradient boosting decision tree model is used for power load prediction. A training set and a test set are divided according to 7: 3, the training set is used for model training, an improved dragonfly algorithm is used for optimization, a lightweight gradient boosting tree model under optimal parameters is obtained, testing is carried out through the test set, and under the condition that a given prediction error is met, the power load is predicted.

Description

technical field [0001] The invention discloses a power load forecasting method based on an improved dragonfly and a light-weight gradient boosting tree model, and relates to the field of information technology and the technical field of power load forecasting. Background technique [0002] At present, the electric power industry is developing rapidly in my country, but it is limited by the current technology that cannot store electric energy on a large scale, and excessive production of electric power will lead to waste of resources, and insufficient electric power production will affect normal economic life. Therefore, designing a high-precision power load forecasting model to predict future electricity consumption is one of the technical problems to be solved. [0003] In the prior art, there are two main types of methods to achieve power load forecasting: one is to use time series methods to achieve forecasting, the essence of which is to fit historical data, and the othe...

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): G06Q10/04G06Q50/06H02J3/00G06N3/00G06K9/62
CPCG06Q10/04G06Q50/06H02J3/003G06N3/006G06F18/24323Y04S10/50
Inventor 梁雪春杜楠楠杨世品
Owner NANJING TECH UNIV
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