H Li, T Lv, X Zhang - 2018 IEEE Globecom Workshops (GC …, 2018 - ieeexplore.ieee.org
… PolicyGradient (DDPG) into the dynamic powercontrol … , we investigate the optimal power control strategy in EH-UDN … the optimization framework of the powercontrol scheme. In …
A Fathollahi, B Andresen - e-Prime-Advances in Electrical Engineering …, 2024 - Elsevier
… power system stabilizers (PSSs) are typically employed. These facilities generate auxiliary control … deep deterministic policygradient (DDPG) based on a synergetic control approach to …
… In this paper, we present two novel approaches based on deep deterministic policygradient … policygradient” and “sharing deep deterministic policygradient”, for the multi-agent power …
BV Mbuwir, L Vanmunster, K Thoelen, G Deconinck - Energy and AI, 2021 - Elsevier
… execution, computation of the reward is not required - since we will focus on a policy gradient RL algorithm. Thus, knowledge of i E t r e q and i T t d e p is not required during policy …
… and the corresponding optimal reactive powercontrol (aka, policy) is parameterized in the … power loss over a number of historical and simulated training pairs, using the policygradient …
JH Woo, L Wu, JB Park, JH Roh - Ieee Access, 2020 - ieeexplore.ieee.org
… Since TD3, which policygradient methods used, is well known as a model to avoid the curse of dimensionality, although their units are not the same, TD3 algorithm does not need a …
… This section introduces the powercontrol method based on the deep deterministic policy gradient (DDPG) algorithm, which is used to achieve the powercontrol objectives of the WPGS. …
R Lincoln, S Galloway, B Stephen… - … Transactions on Power …, 2011 - ieeexplore.ieee.org
… of policygradient reinforcement learning methods, using artificial neural networks for policy function … The methods are compared using an AC optimal power flow based power exchange …
… (4)) to a continuous action space is problematic, as the greedy policy requires global optimization during policy improvement. The deterministic policygradient (DPG) is more …