Optimal bidding strategies in electricity markets using reinforcement learning

In a deregulated electricity market, optimal bidding strategies are desired by market participants in order to maximize their individual profits. The optimal bidding strategy for a market participant is difficult to be determined by calculus based methods because of the uncertainties and dynamics of the electricity market. As one of a range of the learning techniques, learning automata are applied to this complex optimization problem in this paper. As a model-free method, it has great flexibility and distinct advantages in practice. The proposed method is illustrated by reference to the WSCC 9-bus test system. The simulation results show its feasibility and potential for on-line applications in the electricity market.