search for




 

Daily forecasting of energy demand using SARIMA and LSTM method to support decision making on V2G
Journal of the Korean Data & Information Science Society 2019;30:779-95
Published online July 31, 2019;  https://doi.org/10.7465/jkdi.2019.30.4.779
© 2019 Korean Data and Information Science Society.

Jeong Hyun Lee1 · Jae Sung Kim2 · Young Ho Ahn3 · Wan Sup Cho4

12Department of Bigdata, Chungbuk National University
3RETIGRID
4Department of MIS, Chungbuk National University
Correspondence to: Professor, Department of MIS, Chungbuk National University, 1 ChungDae-ro, Seowon-gu, Chungbuk 28644, Korea. E-mail: wscho@chungbuk.ac.kr

This research is supported by a reseach fund of university ICT center on Ministry of Science and ICT/IITP (IITP-2018-0-01396).
Received June 24, 2019; Revised July 10, 2019; Accepted July 11, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Domestic energy demand is currently at risk and is related to the gradual phase-out of nuclear power plants and the expansion of EV (electric vehicle) charging stations. And also, there will be additional demand due to political problems on the Korean Peninsula. The purpose of this study is to predict the energy peak load and their time zone of day when switching from main power to ESS (energy storage system) or energy trading. So, our goal is to get more reliable results through a short time period analysis based on 24-hours. And SARIMA (seasonal ARIMA) and long short term memory (LSTM) were used to perform this study. We hope this model of analysis can be used positively on real world related with V2G (vehicle to grid) or ESS in the near future.
Keywords : ESS, energy peak load, LSTM, SARIMA, V2G.