Reinforcement learning and its applications in modern power and energy systems: A review

D Cao, W Hu, J Zhao, G Zhang, B Zhang… - Journal of modern …, 2020 - ieeexplore.ieee.org
With the growing integration of distributed energy resources (DERs), flexible loads, and
other emerging technologies, there are increasing complexities and uncertainties for …

Multi-agent reinforcement learning for active voltage control on power distribution networks

J Wang, W Xu, Y Gu, W Song… - Advances in Neural …, 2021 - proceedings.neurips.cc
This paper presents a problem in power networks that creates an exciting and yet
challenging real-world scenario for application of multi-agent reinforcement learning …

Safe off-policy deep reinforcement learning algorithm for volt-var control in power distribution systems

W Wang, N Yu, Y Gao, J Shi - IEEE Transactions on Smart Grid, 2019 - ieeexplore.ieee.org
Volt-VAR control is critical to kee** distribution network voltages within allowable range,
minimizing losses, and reducing wear and tear of voltage regulating devices. To deal with …

Data-driven multi-agent deep reinforcement learning for distribution system decentralized voltage control with high penetration of PVs

D Cao, J Zhao, W Hu, F Ding, Q Huang… - … on Smart Grid, 2021 - ieeexplore.ieee.org
This paper proposes a novel model-free/data-driven centralized training and decentralized
execution multi-agent deep reinforcement learning (MADRL) framework for distribution …

Deep reinforcement learning enabled physical-model-free two-timescale voltage control method for active distribution systems

D Cao, J Zhao, W Hu, N Yu, F Ding… - … on Smart Grid, 2021 - ieeexplore.ieee.org
Active distribution networks are being challenged by frequent and rapid voltage violations
due to renewable energy integration. Conventional model-based voltage control methods …

Attention enabled multi-agent DRL for decentralized volt-VAR control of active distribution system using PV inverters and SVCs

D Cao, J Zhao, W Hu, F Ding… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
This paper proposes attention enabled multi-agent deep reinforcement learning (MADRL)
framework for active distribution network decentralized Volt-VAR control. Using the …

Learning to operate distribution networks with safe deep reinforcement learning

H Li, H He - IEEE Transactions on Smart Grid, 2022 - ieeexplore.ieee.org
In this paper, we propose a safe deep reinforcement learning (SDRL) based method to solve
the problem of optimal operation of distribution networks (OODN). We formulate OODN as a …

Peer-to-peer transactive energy trading of a reconfigurable multi-energy network

Y Zou, Y Xu, X Feng, HD Nguyen - IEEE Transactions on Smart …, 2022 - ieeexplore.ieee.org
This paper proposes a bi-level peer-to-peer (P2P) multi-energy trading framework for a
coupled distribution network (DN) and district heating network (DHN). At the lower level …

A risk-averse adaptive stochastic optimization method for transactive energy management of a multi-energy microgrid

Y Zou, Y Xu, C Zhang - IEEE Transactions on Sustainable …, 2023 - ieeexplore.ieee.org
This paper proposes a new energy management method for a multi-energy microgrid
(MEMG) which supplies both electrical and thermal energies. Based on the transactive …

Data-driven optimal energy management for a wind-solar-diesel-battery-reverse osmosis hybrid energy system using a deep reinforcement learning approach

G Zhang, W Hu, D Cao, W Liu, R Huang… - Energy conversion and …, 2021 - Elsevier
Significant dependence on fossil fuels and freshwater shortage are common problems in
remote and arid regions. In this context, the operation of a wind-solar-diesel-battery-reverse …