search for


Short term electricity demand forecasting in south korea with generalized additive models
Journal of the Korean Data & Information Science Society 2018;29:1299-307
Published online September 30, 2018
© 2018 Korean Data and Information Science Society.

Hyelyen Kim1· Jaehee Kim2

12Department of Statistics, Duksung Women's University
Correspondence to: Professor, Department of Statistics, Duksung Women's University, Seoul 01369, Korea. E-mail:
This research is supported by 2018 Duksung Women's University Research Fund.
Received July 17, 2018; Revised September 13, 2018; Accepted September 17, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Load forecasting is a key task for the effective operation and planning of power systems. This paper provides the Korean electricity load modeling and forecasting using SARMA (seasonal autoregressive moving average) models to explain an autoregressive lagged part and GAM (generalized additive model) to incorporate the explanatory variables. The selected exploratory variables are one-day-lagged loads, weather conditions, weekdays, and GDP as a global economic trend. The results demonstrate that our models are operationally efficient and achieve optimal prediction performance. The proposed model can explain the trend of Korean electricity demand and forecast the short-term demand.
Keywords : ARIMA, electricity demand forecasting, generalized additive model, load modeling, regression, smoothing methods, spline.