Forecasting The Italian Day-Ahead Electricity Price Using Bootstrap Aggregation Method

Abstract

Electricity price forecasting has become a crucial element for both private and public decision-making. This importance has been growing since the wave of deregulation and liberalization of the energy sector on a global scale since the late 1990s. Given these facts, this paper is an attempt to establish and demonstrate a precision based applicable forecasting model for wholesale electricity prices with respect to the Italian power market on an hourly basis. Artificial intelligence models such as neural networks and bagged regression trees are utilized, although they are rarely used to forecast electricity prices. After model calibration, bagged regression trees with exogenous variables comprised the final model. The selected model outperformed neural network and bagged regression with a single price used in this paper, it also outperformed other statistical and non-statistical models used in other studies. We also confirm certain theoretical specifications of the model. As a policy tool, this model could be used by energy traders, transmission system operators and energy regulators for an enhanced decision-making process.