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

Bi-LSTM electric load prediction method based on deep learning

A forecasting method and deep learning technology, applied in neural learning methods, forecasting, instruments, etc., can solve the problems of low electric load forecasting efficiency, overfitting phenomenon, etc., to reduce overfitting phenomenon, improve adjustment freedom, improve The effect of efficiency

Inactive Publication Date: 2019-09-10
HOHAI UNIV CHANGZHOU
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a Bi-LSTM-based electric load forecasting method based on deep learning to solve the technical problems of low electric load forecasting efficiency and over-fitting phenomenon 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
  • Bi-LSTM electric load prediction method based on deep learning
  • Bi-LSTM electric load prediction method based on deep learning
  • Bi-LSTM electric load prediction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0032] Table 1 shows the daily electricity load and parameters of an office building in November:

[0033] Table 1

[0034]

[0035]

[0036]

[0037] In a specific example, the first M cycle parameters of the historical data are obtained, as shown in Table 1, the historical cycle parameters should not be less than 1, and the parameters include but are not limited to time, temperature, and weather conditions (clear 1, cloudy 0..5, In the embodiment of the present invention, the cycle parameters are illustrated by taking time, high temperature, low temperature, weather conditions, and load as examples.

[0038] Based on Table 1, if you want to get the forecasted load for 30 days in Dec...

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 Bi-LSTM electrical load prediction method based on deep learning, belongs to the technical field of electrical load prediction, and aims to solve the technical problems of low electrical load prediction efficiency and an overfitting phenomenon in the prior art and perform normalization preprocessing on an electrical load data sample. The method comprises: designing a multilayer Bi-LSTM deep neural network; inputting the preprocessed electrical load data into a neural network model for training; and performing reverse normalization processing on the prediction result.The multi-layer Bi-LSTM effectively increases the depth of the model, improves the adjustment freedom degree of electrical load parameters, carries out the extraction of a part of features of the inputted data, and improves the efficiency of a neural network model. In order to prevent overfitting of the training model caused by excessive layers of the network model, dropout is added into the model, and the overfitting phenomenon is reduced.

Description

technical field [0001] The invention belongs to the technical field of electric load forecasting, and in particular relates to a Bi-LSTM electric load forecasting method based on deep learning. Background technique [0002] The development of the power industry restricts the development of the national economy and society, and the power system also provides irreplaceable services for various users. While predicting the future electricity or power demand usage, power forecasting can reduce energy loss and avoid the situation of large horses and carts. Scientific power forecasting plays a major role in power system planning, operation and scheduling. When deciding on a new engine installation, unnecessary installed energy storage capacity can be avoided, which determines the capacity increase and reconstruction plan of the power grid, and determines the construction and development of the power grid. Power load forecasting can save energy, reduce costs, and reduce energy consu...

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): G06Q10/04G06Q50/06G06N3/04G06N3/08
CPCG06Q10/04G06Q50/06G06N3/08G06N3/044G06N3/045
Inventor 蔡昌春陶媛邓志祥刘昊林
Owner HOHAI UNIV CHANGZHOU
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