A Reinforcement Learning Method For Power Suppliers' Strategic Bidding with Insufficient Information

TL;DR

This paper introduces a novel model-free reinforcement learning algorithm based on Learning Automata for power suppliers to strategize bidding in markets with extremely limited external information, demonstrating its rationality and convergence.

Contribution

It proposes a new reinforcement learning method tailored for incomplete information markets and analyzes its theoretical properties within the Cournot market model.

Findings

The algorithm converges in case studies.

It effectively enables strategic bidding under information scarcity.

The method is rational and theoretically sound.

Abstract

Power suppliers can exercise market power to gain higher profit. However, this becomes difficult when external information is extremely rare. To get a promising performance in an extremely incomplete information market environment, a novel model-free reinforcement learning algorithm based on the Learning Automata (LA) is proposed in this paper. Besides, this paper analyses the rationality and convergence of the algorithm in case studies based on the Cournot market model.