Forecasting Spot Electricity Market Prices Using Time Series Models

This paper addresses the importance of electricity price forecasting in the deregulated electricity market. A simple multiple linear regression approach is proposed to predict next day's electricity prices. The developed models are tested using time-series data of the Nordic electricity market (Nord Pool) and a Canadian electricity market (Ontario) and satisfactory results are achieved. The obtained results of the Nord Pool market are found to be relatively more accurate than those of the Ontario market. This arises from the fact that the market of Ontario is very volatile and its market prices are hardly predictable. The results of the study have shown that the proposed models perform very well with the markets with rather low levels of volatility.