Fuzzy Q -- Learning for Uniform Price Wholesale Power Markets

The generators gain more profits through bidding strategies become an important in the open competitive market. In the incomplete information market, the generators are looking for a best bidding strategy according to the changing market structure and their own conditions are a significant. The reinforcement Q - learning combined with fuzzy control are considered to solve this problem. The day - ahead uniform price wholesale power market model is presented. The model is suitable for multi area power system and which simulated throughout IEEE 30 bus power system with six generators in three areas. The resulting simulations demonstrated the Fuzzy Q - learning (FQ - leaning) has convergent more rapidly than the conventional Q - learning and the supplier agents can choose the best bidding strategy according to the changing power market structure.