Proof-of-concept of a reinforcement learning framework for wind farm energy capture maximization in time-varying wind

被引:21
|
作者
Stanfel, P. [1 ]
Johnson, K. [1 ]
Bay, C. J. [2 ]
King, J. [2 ]
机构
[1] Colorado Sch Mines, Dept Elect Engn, Golden, CO 80401 USA
[2] Natl Renewable Energy Lab, NWTC, Golden, CO 80401 USA
关键词
WAKE; PREDICTION;
D O I
10.1063/5.0043091
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In this paper, we present a proof-of-concept distributed reinforcement learning framework for wind farm energy capture maximization. The algorithm we propose uses Q-Learning in a wake-delayed wind farm environment and considers time-varying, though not yet fully turbulent, wind inflow conditions. These algorithm modifications are used to create the Gradient Approximation with Reinforcement Learning and Incremental Comparison (GARLIC) framework for optimizing wind farm energy capture in time-varying conditions, which is then compared to the FLOw Redirection and Induction in Steady State (FLORIS) static lookup table wind farm controller baseline.
引用
收藏
页数:14
相关论文
共 34 条
  • [1] Optimal control of a wind farm in time-varying wind using deep reinforcement learning
    Kim, Taewan
    Kim, Changwook
    Song, Jeonghwan
    You, Donghyun
    [J]. ENERGY, 2024, 303
  • [2] A Distributed Reinforcement Learning Yaw Control Approach for Wind Farm Energy Capture Maximization
    Stanfel, Paul
    Johnson, Kathryn
    Bay, Christopher J.
    King, Jennifer
    [J]. 2020 AMERICAN CONTROL CONFERENCE (ACC), 2020, : 4065 - 4070
  • [3] Rate Maximization with Reinforcement Learning for Time-Varying Energy Harvesting Broadcast Channels
    Kim, Heasung
    Shin, Wonjae
    Yang, Heecheol
    Lee, Nayoung
    Lee, Jungwoo
    [J]. 2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2019,
  • [4] Visualizing the Maximum Energy Zone of Wind Turbines Operating at Time-Varying Wind Speeds
    Chioncel, Cristian Paul
    Spunei, Elisabeta
    Tirian, Gelu-Ovidiu
    [J]. SUSTAINABILITY, 2024, 16 (07)
  • [5] Frequency Regulation at a Wind Farm Using Time-Varying Inertia and Droop Controls
    Wu, Yuan-Kang
    Yang, Wu-Han
    Hu, Yi-Liang
    Dung Phan Quoc
    [J]. 2018 IEEE/IAS 54TH INDUSTRIAL AND COMMERCIAL POWER SYSTEMS TECHNICAL CONFERENCE (I&CPS), 2018,
  • [6] Frequency Regulation at a Wind Farm Using Time-Varying Inertia and Droop Controls
    Wu, Yuan-Kang
    Yang, Wu-Han
    Hu, Yi-Liang
    Phan Quoc Dzung
    [J]. IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2019, 55 (01) : 213 - 224
  • [7] PROOF-OF-CONCEPT COMBINED SHROUDED WIND TURBINE AND COMPRESSED AIR ENERGY STORAGE SYSTEM
    Langness, Chenaniah
    Kolsky, Daniel
    Busch, Tyler
    Davidson, Colin
    Depcik, Christopher
    [J]. PROCEEDINGS OF THE ASME INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, 2013, VOL 6A, 2014,
  • [8] Modeling Wind Speed and Time-varying Turbulence in Geographically Dispersed Wind Energy Markets in China
    Payne, J. E.
    Carroll, B.
    [J]. ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2009, 31 (19) : 1759 - 1769
  • [9] Time-varying signal parameters for assessment of disturbances in wind energy systems
    Lobos, Tadusz
    Schegner, Peter
    Sikorski, Tomasz
    [J]. PRZEGLAD ELEKTROTECHNICZNY, 2010, 86 (01): : 47 - 49
  • [10] A low-fidelity dynamic wind farm model for simulating time-varying wind conditions and floating platform motion
    Kheirabadi, Ali C.
    Nagamune, Ryozo
    [J]. OCEAN ENGINEERING, 2021, 234