Reinforcement Learning Based Supplier-Agents for Electricity Markets

Bidding strategies play important roles in maximizing the profits of power suppliers in competitive electricity markets. Therefore, it will be an advantage for a supplier to search for optimal bidding strategies in the market. In this paper the problem of designing fuzzy reinforcement learning (FRL) supplier-agents that compete in forward electricity markets (e.g. Day-Ahead energy market) to maximize their revenues is studied. An IEEE 30-bus power system with 6 generators (supplier-agents) and three demand areas with stochastic loads are used for our simulation studies. This model is applicable to different types of commodity markets with numerous supply and demand agents