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

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.

[1]  Li Jia,et al.  A short-term hybrid wind power prediction model based on singular spectrum analysis and temporal convolutional networks , 2020 .

[2]  Kathryn E. Johnson,et al.  Simulation comparison of wake mitigation control strategies for a two‐turbine case , 2015 .

[3]  Zhe Zhang,et al.  Reinforcement-Learning-Based Intelligent Maximum Power Point Tracking Control for Wind Energy Conversion Systems , 2015, IEEE Transactions on Industrial Electronics.

[4]  Jizhen Liu,et al.  A dynamic clustering model of wind farm based on the operation data , 2015 .

[5]  Yongqian Liu,et al.  Clustering methods of wind turbines and its application in short-term wind power forecasts , 2014 .

[6]  Jason R. Marden,et al.  A Model-Free Approach to Wind Farm Control Using Game Theoretic Methods , 2013, IEEE Transactions on Control Systems Technology.

[7]  Jason R. Marden,et al.  Wind plant power optimization through yaw control using a parametric model for wake effects—a CFD simulation study , 2016 .

[8]  Carlos Ocampo-Martinez,et al.  A wind farm control strategy for power reserve maximization , 2019, Renewable Energy.

[9]  Brady Ryan,et al.  Initial results from a field campaign of wake steering applied at a commercial wind farm – Part 1 , 2019, Wind Energy Science.

[10]  Yongqian Liu,et al.  Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting , 2016 .

[11]  Masoud Rashidinejad,et al.  Robust short-term prediction of wind turbine power based on combined neural networks , 2020 .

[12]  Marc Calaf,et al.  Clustering sparse sensor placement identification and deep learning based forecasting for wind turbine wakes , 2021 .

[13]  E. Simley,et al.  Power increases using wind direction spatial filtering for wind farm control: Evaluation using FLORIS, modified for dynamic settings , 2021 .

[14]  Lotfi Krichen,et al.  Power Control of DFIG-Based Wind Farm for System Frequency Support , 2018, 2018 15th International Multi-Conference on Systems, Signals & Devices (SSD).

[15]  Ervin Bossanyi.  Combining induction control and wake steering for wind farm energy and fatigue loads optimisation , 2018 .

[16]  Jinfu Liu,et al.  The analysis of turbulence intensity based on wind speed data in onshore wind farms , 2018, Renewable Energy.

[17]  Yu Huang,et al.  Improved clustering and deep learning based short-term wind energy forecasting in large-scale wind farms , 2020 .

[18]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[19]  Yingtao Jiang,et al.  A novel deep learning approach for short-term wind power forecasting based on infinite feature selection and recurrent neural network , 2018, Journal of Renewable and Sustainable Energy.

[20]  Kincho H. Law,et al.  Bayesian Ascent: A Data-Driven Optimization Scheme for Real-Time Control With Application to Wind Farm Power Maximization , 2016, IEEE Transactions on Control Systems Technology.

[21]  R. B. Cal,et al.  Data-driven modeling of the wake behind a wind turbine array , 2020 .

[22]  P. Fleming,et al.  Evaluation of the potential for wake steering for U.S. land-based wind power plants , 2021, Journal of Renewable and Sustainable Energy.

[23]  Michail G. Lagoudakis,et al.  Coordinated Reinforcement Learning , 2002, ICML.

[24]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..