Double Seasonal ARIMA for Forecasting Electricity Demand of Kuaro Main Gate in East Kalimantan. Issue 1 (May 2020)

• Record Type: Journal Article
• Authors: Azka, M; Wiradinata, SA; Faisal, M; Suhartono,
• Is Part Of: IOP conference series. Volume 846:Issue 1(2020)
• Publication Date: 2020-05
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/846/1/012064
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: This study uses intraday electricity load demand data from Kuaro Main Gate data in East Kalimantan as the basis of an empirical comparison of Double Seasonal ARIMA models for prediction up to a day ahead. For the purpose of this study, a one-year hourly Kuaro Main Gate data load demand from 1 January 2018 to December 2018 measured in Megawatt (MW) is used. In multiple times of load demand data, in addition to intraday and intra week cycles, and intra year seasonal cycle is also apparent. We extend the Double Seasonal ARIMA methods in order to accommodate the Intra year seasonal cycle. The mean absolute percentage error (MAPE) is used as the measure of forecasting accuracy. A notable feature of the time series is the presence of both an intraweek and an intraday seasonal cycle. We also propose that a Double Seasonal ARIMA model with the one-step-ahead forecast as the most appropriate model for forecasting the two-seasonal cycles Kuaro Main Gate data load demand time series. We use the Statistical Analysis System package to analyze the data. Using the least-squares method to estimate the coefficients in a Double Seasonal ARIMA model, followed by model validation and model selection criteria, we propose the ARIMA (1, 1, 1)(0, 1, 1) 24 (0, 1, 1) 168 within-sample MAPE of 0.000992 as the best model for this study. Comparing the forecasting performances by using k-step ahead forecasts and one-step-ahead forecasts, we found that the MAPE for the one-step ahead out-sample forecasts from any horizon ranging from one week lead time to one month one week lead time are all less than 5%. Therefore we propose that a double seasonal ARIMA model with a one-step-ahead forecast must be considered in forecasting time series data with two seasonal cycles.