A review of short-term electricity price forecasting techniques in deregulated electricity markets

Short-term electricity price forecasting has become a crucial issue in the power markets, since it forms the basis of maximising profits for the market participants. This paper presents an extensive review of the established approaches to electricity price forecasting. It summarizes the influencing factors of price behaviour and proposes an extended taxonomy of price forecasting methods. Through the comparison of different approaches, such as Artificial Neural Networks (ANNs), Auto Regressive Integrated Moving Average Models (ARIMA) and Least Square Support Vector Machine (LSSVM), the hybrid methods that combine different models in order to offset the inherent weakness of individual models are highlighted with regard to the future trend of electricity price forecasting methodology.