Implication of different pricing rules on generators' bidding behaviour

This paper presents an agent-based model to examine the employment of different pricing rules, namely the Uniform pricing rule and Pay-as-bid pricing rule. Using Q-learning in repetitive trading process, generator agents learn the market characteristics and seek to maximize their revenue by exploring bidding strategies. Supply quantity withholding and generators' collusion phenomenon have been observed in this study under certain market arrangements. The implication of different pricing rules on the total dispatch costs and generators' profit are discussed in this paper.