Multi-Agent Deep Deterministic Policy Gradient Algorithm for Peer-to-Peer Energy Trading Considering Distribution Network Constraints

TL;DR

This paper introduces a multi-agent deep reinforcement learning algorithm to optimize peer-to-peer energy trading among prosumers, effectively considering uncertainties and distribution network constraints to minimize costs.

Contribution

It develops a novel multi-agent deep deterministic policy gradient method incorporating network tariffs to ensure constraint satisfaction without prior agent information.

Findings

Algorithm effectively minimizes energy costs in simulations.

Robustness demonstrated with real-world data.

Constraints are successfully integrated into the learning process.

Abstract

In this paper, we investigate an energy cost minimization problem for prosumers participating in peer-to-peer energy trading. Due to (i) uncertainties caused by renewable energy generation and consumption, (ii) difficulties in developing an accurate and efficient energy trading model, and (iii) the need to satisfy distribution network constraints, it is challenging for prosumers to obtain optimal energy trading decisions that minimize their individual energy costs. To address the challenge, we first formulate the above problem as a Markov decision process and propose a multi-agent deep deterministic policy gradient algorithm to learn optimal energy trading decisions. To satisfy the distribution network constraints, we propose distribution network tariffs which we incorporate in the algorithm as incentives to incentivize energy trading decisions that help to satisfy the constraints and penalize the decisions that violate them. The proposed algorithm is model-free and allows the agents to learn the optimal energy trading decisions without having prior information about other agents in the network. Simulation results based on real-world datasets show the effectiveness and robustness of the proposed algorithm.