Daily electrical energy consumption: Periodicity, harmonic regression method and forecasting

Abstract

This study starts with a brief analysis of the global electricity market with special reference to the Turkish market. Next, the daily electricity consumption amounts in Turkey between 2012 and 2016 are examined by using statistical tools. Furthermore, the periodicity in the data is discovered. The periodicity, which has an impact not only in the electricity market but also in other sectors of the economy, is an important indicator for planning and policy-making. Periodicity is easier to observe depending on seasonal impacts. However, what is important is to detect hidden periodicity. The main contribution of this study is to detect the hidden periodicity with a rather novel approach in the electricity industry. The proposed periodicity test based on the periodogram ordinate has two major advantages. First, the periodograms are invariant to the model selection. Secondly, the distributions of the normalized periodograms and therefore critical values do not depend on the sample size. Moreover, the forecasting performance of the model for Turkish electricity consumption seems to be better compared to the standard time series model.