Electrical Load Forecasting Based on LSTM Neural Networks

DOI

10.2991/acsr.k.191223.024How to use a DOI?

Keywords

electrical load forecasting, time series, recursive neural network, long short-term memory

Abstract

The accurate prediction of electrical load is vital to the safety of power grid and the efficiency of energy. The development history of electrical load forecasting is introduced briefly in this paper. Then the relationship between electricity, environment and economy is also analyzed. Ljubljana’s load data and environmental meteorological data of the previous time are applied to train LSTM networks to make prediction of the electrical load. The experimental results show that, in the case of abundant data with good quality, the LSTM network model can make quite acceptable short-term predictions of the power load based on previous energy consumption and environmental weather data.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lei Guo
AU  - Linyu Wang
AU  - Hao Chen
PY  - 2019
DA  - 2019/12/24
TI  - Electrical Load Forecasting Based on LSTM Neural Networks
BT  - Proceedings of the 2019 International Conference on Big Data, Electronics and Communication Engineering (BDECE 2019)
PB  - Atlantis Press
SP  - 107
EP  - 111
SN  - 2352-538X
UR  - https://doi.org/10.2991/acsr.k.191223.024
DO  - 10.2991/acsr.k.191223.024
ID  - Guo2019
ER  -