Structural breaks, price and income elasticity and forecast of the monthly italian electricity demand

Insights about electricity demand dynamics is fundamental for investment capacity, optimal energy policies, and balanced electricity system. This paper presents an empirical analysis of the monthly Italian electricity demand since January 2001 to June 2012. In the first section we conduct a deep analysis of the structural breaks in the electricity demand finding that the series has two structural breaks in August 2002 and August 2004. In the second part of the paper we estimate the price elasticity of demand both for residential and industrial sector. As expected from the electricity economics literature, we find that the long run price and income elasticities are more price elastic than the short run both in the industrial and residential consumption. In the third and last section, we compare two different forecasting models: the Hidden Markov Models (HMM) and the Holt Winters (H-W) seasonal smoothing method. Considering the Mean Absolute Percentage Error (MAPE), the HMM approach seems to show a superiority in forecasting the monthly electricity demand compared to the H-W methodology in the horizon forecast.