A Deep Learning Based Real-time Load Forecasting Method in Electricity Spot Market

This paper analyzes the potential influence in Chinese electricity market due to the reform and access of the electricity spot market. On this occasion, a deep learning based model for load forecasting is proposed to improve the market operator's precise scheduling level and assist power retail...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2019-03, Vol.1176 (6), p.62068
Main Authors: Zhang, Qipei, Lu, Jixiang, Yang, Zhihong, Tu, Mengfu
Format: Article
Language:English
Subjects:
Algorithms
Deep learning
Economic forecasting
Electrical loads
Electricity
Machine learning
Mathematical models
Meteorological data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper analyzes the potential influence in Chinese electricity market due to the reform and access of the electricity spot market. On this occasion, a deep learning based model for load forecasting is proposed to improve the market operator's precise scheduling level and assist power retailers in managing bid strategies. Long-Short Term Memory (LSTM) unit is used to modeling, which is one of the most popular techniques of deep learning. In addition, historical power load data and meteorological data of Suzhou and Lianyungang in China from January 2015 to December 2017 are used for the study to training and evaluate forecasting model. As a result, this paper shows the compare results with exiting machine algorithm for load forecasting.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1176/6/062068