AUTHOR=Zhang Feiye , Yang Qingyu , Li Donghe 

TITLE=A deep reinforcement learning-based bidding strategy for participants in a peer-to-peer energy trading scenario

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.1017438

DOI=10.3389/fenrg.2022.1017438

ISSN=2296-598X

ABSTRACT=Efficient energy trading strategy is proven to have vital role in reducing participants' payment in the energy trading process of power grid, which can greatly improve the operation efficiency of power grid and the willingness of participants to take part in the energy trading. Nevertheless, as the increasing number of participants taking part in the energy trading, the stability and efficiency of the energy trading system are exposed to extreme challenge. To address this issue, an actor-critic-based bidding strategy for energy trading participants is proposed in this paper. Specifically, we model the bidding strategy with sequential decision-making characteristic as a Markov decision process, which treats three elements, i.e., total supply, total demand and participants' individual supply or demand as the state and regards bidding price and volume as the action. In order to address the problem that existing value-based RL bidding strategy cannot be applied to the continuous action space environment, we propose an actor-critic architecture, which endows actor the ability of learning the action execution, and utilizes critic to evaluate the long-term rewards conditioned the current state-action pairs. Simulation results in energy trading scenarios with different number of participants indicate that the proposed method will obtain higher cumulative reward than the traditional greedy method.