Energy price forecasting and bidding strategy in the Ontario power system market

This paper introduces a method for forecasting energy prices using artificial intelligence methods such as neural networks and fuzzy logic and a combination of the two. The forecasted price is then used to design an optimal bidding strategy for a generator according to his/her degree of risk aversion. A typical thermal plant is assumed to be located in the Ontario electricity system to apply this methodology for two types of participants: risk averse and risk seeker. Results for the Ontario electricity market are presented.