Agent-Based Analysis of Monopoly Power in Electricity Markets

In this paper agent-based simulation is employed to study the energy market performance and, particularly, the exercise of monopoly power. The energy market is formulated as a stochastic game, where each stage game corresponds to an hourly energy auction. Each hourly energy auction is cleared using Locational Marginal Pricing. Generators are modeled as adaptive agents capable of learning through the interaction with their environment, following a Reinforcement Learning algorithm. The SA-Q-learning algorithm, a modified version of the popular Q-Learning, is used. Test results on a two-node power system with two competing generator-agents, demonstrate the exercise of monopoly power.