Hybrid dynamic harmonic regression with calendar variation for Turkey short-term electricity load forecasting

Abstract

Short-term electricity load forecasting plays a vital role in determining the energy supplied. It has daily, weekly, and yearly harmonics patterns. In Muslim countries, it is influenced by religious celebrations held on the Islamic Hijri calendar. This study aims to compare Dynamic Harmonic Regression forecasting and its hybrid version involving calendar variation effect. This study is designed in two scenarios. Scenario 1 shows that out-of-sample forecasting can capture both seasonal and calendar variation patterns, while Scenario 2 shows the performance while only seasonal patterns exist. The results show that the hybrid model outperforms the individual models in two scenarios.