期刊
RENEWABLE ENERGY
卷 181, 期 -, 页码 445-456出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.renene.2021.09.023
关键词
Wind farm control; Coordinated control; Reinforcement learning; Fatigue; Wake; Auto-encoder
The paper introduces a multi-agent deep reinforcement learning method called FALCON for coordinated control of wind farms, which addresses the trade-off between energy and fatigue damage by jointly controlling the pitch and yaw of all turbines. FALCON achieves scale by using multiple reinforcement learning agents and efficiently capturing the global state-space, leading to better performance compared to baseline PID controllers and learning-based distributed control in a real-world wind farm case study.
Turbines in a wind farm dynamically influence each other through wakes. Therefore trade-offs exist between energy output of upstream turbines and the health of downstream turbines. Using both model based predictive control (MPC) and machine learning techniques, existing works have explored the energy-fatigue trade-off either in a single turbine or only with few turbines due to issues of scalability and complexity. To address this gap, this paper proposes a multi-agent deep reinforcement learning based coordinated control for wind farms, called FALCON. FALCON addresses the multi-objective optimization problem of maximizing energy while minimizing fatigue damage by jointly controlling pitch and yaw of all turbines. FALCON achieves scale by using multiple reinforcement learning agents; capturing the global state-space efficiently using an auto-encoder; and pruning the action-space using domain knowledge. FALCON is evaluated through a real-world wind-farm case study with 21 turbines; and performs better than the default baseline PID controller and a learning-based distributed control. (c) 2021 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据