Comprehensive energy load prediction method based on multi-task learning strategy and deep learning

A multi-task learning and deep learning technology, applied in the field of comprehensive energy load forecasting based on multi-task learning strategies and deep learning, can solve undiscovered problems, achieve the effects of fewer models, improved load forecasting accuracy, and good forecasting results

Pending Publication Date: 2021-12-21
STATE GRID TIANJIN ELECTRIC POWER +1
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] After searching, no publications of 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
  • Comprehensive energy load prediction method based on multi-task learning strategy and deep learning
  • Comprehensive energy load prediction method based on multi-task learning strategy and deep learning
  • Comprehensive energy load prediction method based on multi-task learning strategy and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0030] A comprehensive energy load forecasting method based on multi-task learning strategy and deep learning, comprising the following steps:

[0031] S1. Obtain the characteristics of the influencing factors considering the impact on the cooling, heating, and electric loads of the integrated energy system, and form a historical cooling, heating, and electrical load feature library and an influencing factor feature library;

[0032] The influencing factor characteristics in the step S1 include: meteorological factor characteristics and time factor characteristics closely related to cooling, heating and electrical loads.

[0033] The characteristics of the meteorological factors are analyzed through the Pearson correlation coefficient, that is, the Pearson correlation coefficients of the characteristics of the meteorological factors such as tempera...

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 relates to a comprehensive energy load prediction method based on a multi-task learning strategy and deep learning. The method comprises the following steps: S1, forming a historical cooling, heating and power load feature library and an influence factor feature library; S2, constructing an MMoE multi-task learning model; S3, constructing three LSTM neural network models, training the three LSTM neural network models by utilizing feature sharing and extraction results output by a plurality of expert sub-networks in the MMoE model in the step S2 and cold, hot and electric load tags, and finally obtaining an MMoE-LSTM model; and S4, obtaining a cooling, heating and electric load prediction result. According to the method, interference of weak correlation information on the subtasks can be avoided, and a better prediction effect is achieved.

Description

technical field [0001] The invention belongs to the technical field of comprehensive energy, and relates to a comprehensive energy load forecasting method, in particular to a comprehensive energy load forecasting method based on multi-task learning strategies and deep learning. Background technique [0002] With the development of my country's economy and society, the demand for energy continues to grow, and energy issues have become an important issue related to national security strategies and sustainable development capabilities. In the traditional energy supply system, functional systems such as cooling, heating, and electricity operate independently of each other, lack of coordination, low energy utilization rate, and poor reliability of energy supply. Therefore, the energy supply and consumption link is gradually developing towards an integrated energy system. The integrated energy system makes full use of the complementary effects of various energy forms, significantl...

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
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/06G06N3/04G06N3/08
CPCG06Q10/04G06Q10/06393G06Q50/06G06N3/08G06N3/044
Inventor 邓欣宇朱汉卿刘轶超刘扬李天梦
Owner STATE GRID TIANJIN ELECTRIC POWER
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