Imperial College London
Portrait Picture

Professor Yujian Ye

Faculty of Engineering, Department of Electrical and Electronic Engineering

Honorary Lecturer
 
 
 
//

Contact

 

yujian.ye11

 
 
//

Location

 

1105Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Ye:2021:10.1109/tsg.2021.3103917,
author = {Ye, Y and Tang, Y and Wang, H and Zhang, X-P and Strbac, G},
doi = {10.1109/tsg.2021.3103917},
journal = {IEEE Transactions on Smart Grid},
pages = {1--1},
title = {A Scalable Privacy-Preserving Multi-agent Deep Reinforcement Learning Approach for Large-Scale Peer-to-Peer Transactive Energy Trading},
url = {http://dx.doi.org/10.1109/tsg.2021.3103917},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Peer-to-peer (P2P) transactive energy trading has emerged as a promising paradigm towards maximizing the flexibility value of prosumers’ distributed energy resources (DERs). Despite reinforcement learning constitutes a well-suited model-free and data-driven methodological framework to optimize prosumers’ energy management decisions, its application to the large-scale coordinated management and P2P trading among multiple prosumers within an energy community is still challenging, due to the scalability, non-stationarity and privacy limitations of state-of-the-art multi-agent deep reinforcement learning (MADRL) approaches. This paper proposes a novel P2P transactive trading scheme based on the multi-actor-attention-critic (MAAC) algorithm, which addresses the above challenges individually. This method is complemented by a P2P trading platform that incentivizes prosumers to engage in local energy trading while also penalizes each prosumer’s addition to rebound peaks. %The proposed method is applied to the coordination of prosumers operating multiple and diverse DERs, including photovoltaic (PV) generators, energy storage (ES) units and two types of shiftable loads. Case studies involving a real-world, large-scale scenario with 300 residential prosumers demonstrate that the proposed method significantly outperforms the state-of-the-art MADRL methods in reducing the community’s cost and peak demand.
AU  - Ye,Y
AU  - Tang,Y
AU  - Wang,H
AU  - Zhang,X-P
AU  - Strbac,G
DO  - 10.1109/tsg.2021.3103917
EP  - 1
PY  - 2021///
SN  - 1949-3053
SP  - 1
TI  - A Scalable Privacy-Preserving Multi-agent Deep Reinforcement Learning Approach for Large-Scale Peer-to-Peer Transactive Energy Trading
T2  - IEEE Transactions on Smart Grid
UR  - http://dx.doi.org/10.1109/tsg.2021.3103917
ER  -
Download