A Q-Learning Agent-based Model for the Analysis of the Power Market Dynamics

A. Tellidou and A. Bakirtzis (Greece)


Bidding strategy, multi-agent modelling, reinforcement learning


In the agent-based simulation discussed in this paper, we study the dynamics of the power market, when suppliers act following a Q-learning based bidding strategy. Power suppliers aim to satisfy two objectives: the maximization of their profit and their utilization rate. To meet with success their goals, they need to acquire a complex behavior by learning through a continuous exploiting and exploring process. Reinforcement learning theory provides a formal framework, along with a family of learning methods. In this paper we use Q-learning algorithm to analyze the behavior of power market participants under various market conditions. Q-learning offers suppliers the ability to evaluate their actions and to retain the most profitable of them. Four test cases with three supplier-agents are simulated and the outcomes under different demand values are discussed at the end of the paper. The Uniform Pricing system serves as the market clearing mechanism.

Important Links:

Go Back