3.8 Review

Wind farm control technologies: from classical control to reinforcement learning

Related references

Note: Only part of the references are listed.
Article Automation & Control Systems

Surrogate-Assisted Cooperation Control of Network-Connected Doubly Fed Induction Generator Wind Farm With Maximized Reactive Power Capacity

Zhen Dong et al.

Summary: This article focuses on cooperative active power control of DFIG-based wind farm, utilizing a surrogate model to fit the accurate model for online optimization, which improves the extraction efficiency of reactive power capacity.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Green & Sustainable Science & Technology

Joint optimization of wind farm layout considering optimal control

Kaixuan Chen et al.

Summary: The wake effect is a major cause of energy losses in offshore wind farms, and turbine placement and cooperative control can influence wake interactions and overall power production. A novel two-stage WF layout optimization model is developed in this study, considering cooperative WF control. The proposed joint optimization can achieve higher energy yields compared to traditional separate layout optimization.

RENEWABLE ENERGY (2022)

Article Automation & Control Systems

Composite Experience Replay-Based Deep Reinforcement Learning With Application in Wind Farm Control

Hongyang Dong et al.

Summary: In this study, a deep reinforcement learning-based control approach with enhanced learning efficiency and effectiveness is proposed to optimize the total power production of wind farms. By introducing a novel composite experience replay strategy and modified importance-sampling weights, the method successfully handles the challenges posed by strong wake effects among wind turbines and the stochastic features of environments, achieving higher rewards with less training costs compared to conventional deep RL-based control approaches.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2022)

Article Automation & Control Systems

Wind-Farm Power Tracking Via Preview-Based Robust Reinforcement Learning

Hongyang Dong et al.

Summary: This article presents a novel preview-based robust deep reinforcement learning method for wind-farm power tracking problem, which can handle tasks subject to uncertain environmental conditions and strong aerodynamic interactions among wind turbines. The control problem is transformed into a zero-sum game to quantify the influence of unknown wind conditions and future reference signals.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Automation & Control Systems

Wind Farm Power Generation Control Via Double-Network-Based Deep Reinforcement Learning

Jingjie Xie et al.

Summary: This article proposes a model-free deep reinforcement learning (DRL) method for wind farm control, aiming to maximize the total power generation. By combining induction control and yaw control, a novel double-network (DN)-based DRL approach is designed. The simulation results show that this method can significantly increase power generation for wind farms with different layouts.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Green & Sustainable Science & Technology

Large-scale wind farm control using distributed economic model predictive scheme

Xiaobing Kong et al.

Summary: A distributed economic model predictive control strategy is proposed for large-scale wind farms, integrating power tracking and economic optimization into one optimal control framework, ensuring accurate tracking of reference power and global economic optimality.

RENEWABLE ENERGY (2022)

Article Automation & Control Systems

Reinforcement Learning-Based Structural Control of Floating Wind Turbines

Jincheng Zhang et al.

Summary: This article investigates the structural control of floating wind turbines using active tuned mass damper, and employs a reinforcement learning-based control approach for the first time. The study derives optimal control laws based on nonlinear structural dynamics using an adaptive dynamic programming algorithm and designs the neural network structure using the large-scale machine learning platform Tensorflow. The simulation results demonstrate the effectiveness of the proposed control approach in reducing pitch displacement and show clear advantages over traditional H-infinity controllers, especially in extreme conditions.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2022)

Article Automation & Control Systems

ADP-Based Spacecraft Attitude Control Under Actuator Misalignment and Pointing Constraints

Haoyang Yang et al.

Summary: This article proposes a constrained optimal attitude control scheme, considering two practical problems: actuator misalignment and forbidden pointing constraints. The design makes use of the adaptive dynamic programming framework and a special reward function to overcome the difficulty in actuator misalignment. With the Lyapunov stability theory, the optimality of the method and the ultimate boundedness of state error are guaranteed.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

Article Robotics

Socially Compliant Robot Navigation in Crowded Environment by Human Behavior Resemblance Using Deep Reinforcement Learning

Sunil Srivatsav Samsani et al.

Summary: Social robots face challenges in safely navigating in complex environments due to unpredictable human behavior. By modeling danger zones based on real-time human actions, robots can learn to safely navigate in a socially compliant manner.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Green & Sustainable Science & Technology

A novel deep reinforcement learning enabled sparsity promoting adaptive control method to improve the stability of power systems with wind energy penetration

Guozhou Zhang et al.

Summary: This paper proposes a novel sparsity promoting adaptive control method for online self-tuning of PSS parameter settings, utilizing the combination of DDPG algorithm and sensitivity analysis theory. After training, the method enables PSS to achieve better performance in damping oscillation and robustness against changes in wind energy.

RENEWABLE ENERGY (2021)

Article Energy & Fuels

Spatiotemporal wind field prediction based on physics-informed deep learning and LIDAR measurements

Jincheng Zhang et al.

Summary: By combining LIDAR measurements and flow physics, this study developed a method to predict the spatiotemporal wind field, achieving promising results in various scenarios with only sparse LIDAR measurements. The approach utilized a deep neural network incorporating the Navier-Stokes equations, allowing for accurate predictions of wind patterns not present in the training dataset.

APPLIED ENERGY (2021)

Article Automation & Control Systems

Deep Neural Learning Based Distributed Predictive Control for Offshore Wind Farm Using High-Fidelity LES Data

Xiuxing Yin et al.

Summary: This article discusses the application of deep neural learning for predictive control in offshore wind farms using high-fidelity large eddy simulations data. It introduces a hybrid CNN-LSTM model which shows high prediction accuracy and a distributed model predictive control method that significantly increases power generation efficiency compared to decentralized control. The computational time of the distributed MPC is fast enough to be used as a real-time control solution for wind farm operations.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2021)

Article Engineering, Electrical & Electronic

Scheduled Operation of Wind Farm with Battery System Using Deep Reinforcement Learning

Mamoru Futakuchi et al.

Summary: This paper investigates the scheduled operation method of wind farms using a battery energy storage system and forecast data of wind power generation output. A new method based on deep reinforcement learning is proposed, and a comparison of different methods in reducing ramp events is conducted. The effectiveness of reducing the storage capacity of BESS is also calculated.

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING (2021)

Article Engineering, Electrical & Electronic

Data driven learning model predictive control of offshore wind farms

Xiuxing Yin et al.

Summary: This paper introduces a data-driven control approach for maximizing the total power generation of offshore wind farm using the recently developed learning model predictive control (LMPC) algorithm. The strategy focuses on reducing wake interactions among wind turbines to increase power production, showing a 15% improvement over traditional MPC methods.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2021)

Article Energy & Fuels

Intelligent wind farm control via deep reinforcement learning and high-fidelity simulations

Hongyang Dong et al.

Summary: This study proposes a wind farm control scheme based on deep reinforcement learning, which uses a reward regularization module and composite learning controller to optimize power generation and yaw tracking. The scheme demonstrates robustness and adaptability in handling uncertain wind conditions.

APPLIED ENERGY (2021)

Article Green & Sustainable Science & Technology

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

P. Stanfel et al.

Summary: This paper presents a proof-of-concept distributed reinforcement learning framework for maximizing wind farm energy capture, utilizing Q-learning in a wake-delayed wind farm environment with time-varying wind conditions. The proposed algorithm modifications create the GARLIC framework for optimizing wind farm energy capture in time-varying conditions, which is compared to the static lookup table wind farm controller baseline FLORIS.

JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY (2021)

Proceedings Paper Energy & Fuels

Exploring the application of reinforcement learning to wind farm control

Henry Korb et al.

Summary: In this study, Reinforcement Learning is applied for wind farm control for the first time, optimizing the total power production by tuning existing control parameters and extending to multiple turbines. New control strategies based on generator torque control were attempted, with the tuned helix approach showing an average increase in total power output.

WAKE CONFERENCE 2021 (2021)

Proceedings Paper Energy & Fuels

Analysis of offshore wind spectra and coherence under neutral stability condition using the two LES models PALM and SOWFA

X. Ning et al.

Summary: The study compared the Parallelized Large-Eddy Model (PALM) and the Simulator for Wind Farm Applications (SOWFA) in simulating marine boundary layer flows under neutral stability condition, focusing on the wind spectra and coherence. Both models showed good agreement with empirical spectral model near the surface, but demonstrated lower turbulence intensity in the low frequency range above the surface layer. Additionally, they provided consistent estimates of coherence with different horizontal and vertical separations, aligning well with existing coherence models at specified heights.

EERA DEEPWIND'2021 (2021)

Article Green & Sustainable Science & Technology

Design and analysis of a wake model for spatially heterogeneous flow

Alayna Farrell et al.

Summary: Methods of turbine wake modeling are being developed to account for spatially variant atmospheric conditions within wind farms. The FLORIS model has been adapted to incorporate spatial heterogeneity in flow-field characterization, resulting in improved accuracy of power prediction. Comparative studies demonstrate a decrease in mean absolute error for wind farm power output predictions, suggesting potential benefits of the proposed modeling techniques under varying site-specific conditions.

WIND ENERGY SCIENCE (2021)

Article Engineering, Electrical & Electronic

A data-driven approach for designing STATCOM additional damping controller for wind farms

Guozhou Zhang et al.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2020)

Article Green & Sustainable Science & Technology

Data-driven multi-objective predictive control of offshore wind farm based on evolutionary optimization

Xiuxing Yin et al.

RENEWABLE ENERGY (2020)

Article Green & Sustainable Science & Technology

Contextual Bayesian optimization with trust region (CBOTR) and its application to cooperative wind farm control in region 2

Jinkyoo Park

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS (2020)

Article Engineering, Electrical & Electronic

A deep reinforcement learning method for managing wind farm uncertainties through energy storage system control and external reserve purchasing

J. J. Yang et al.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2020)

Article Green & Sustainable Science & Technology

Closed-loop model-based wind farm control using FLORIS under time-varying inflow conditions

Bart M. Doekemeijer et al.

RENEWABLE ENERGY (2020)

Review Automation & Control Systems

Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications

Thanh Thi Nguyen et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

Proceedings Paper Green & Sustainable Science & Technology

Effects of induction and wake steering control on power and drivetrain responses for 10 MW floating wind turbines in a wind farm

Dirk Willem van Binsbergen et al.

SCIENCE OF MAKING TORQUE FROM WIND (TORQUE 2020), PTS 1-5 (2020)

Proceedings Paper Green & Sustainable Science & Technology

Numerical Validation of Wind Plant Control Strategies

Sugoi Gomez-Iradi et al.

SCIENCE OF MAKING TORQUE FROM WIND (TORQUE 2020), PTS 1-5 (2020)

Proceedings Paper Automation & Control Systems

Model-Free Optimization Scheme for Efficiency Improvement of Wind Farm Using Decentralized Reinforcement Learning

Zhiwei Xu et al.

IFAC PAPERSONLINE (2020)

Review Energy & Fuels

A novel review on optimization techniques used in wind farm modelling

Karthik Balasubramanian et al.

RENEWABLE ENERGY FOCUS (2020)

Article Green & Sustainable Science & Technology

Global trends in the performance of large wind farms based on high-fidelity simulations

Soren Juhl Andersen et al.

WIND ENERGY SCIENCE (2020)

Article Energy & Fuels

A novel dynamic wind farm wake model based on deep learning

Jincheng Zhang et al.

APPLIED ENERGY (2020)

Article Automation & Control Systems

Cooperative Wind Farm Control With Deep Reinforcement Learning and Knowledge-Assisted Learning

Huan Zhao et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Article Geosciences, Multidisciplinary

Overview of the PALM model system 6.0

Bjoern Maronga et al.

GEOSCIENTIFIC MODEL DEVELOPMENT (2020)

Article Automation & Control Systems

Parameterized Batch Reinforcement Learning for Longitudinal Control of Autonomous Land Vehicles

Zhenhua Huang et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2019)

Article Engineering, Electrical & Electronic

Data-Driven Load Frequency Control for Stochastic Power Systems: A Deep Reinforcement Learning Method With Continuous Action Search

Ziming Yan et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2019)

Article Green & Sustainable Science & Technology

Wind farm power optimization via yaw angle control: A wind tunnel study

Majid Bastankhah et al.

JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY (2019)

Article Green & Sustainable Science & Technology

Effects of axial induction control on wind farm energy production - A field test

Daan van der Hoek et al.

RENEWABLE ENERGY (2019)

Article Green & Sustainable Science & Technology

Wind farm distributed PSO-based control for constrained power generation maximization

Nicolo Gionfra et al.

RENEWABLE ENERGY (2019)

Article Green & Sustainable Science & Technology

A constrained wind farm controller providing secondary frequency regulation: An LES study

S. Boersma et al.

RENEWABLE ENERGY (2019)

Review Behavioral Sciences

Reinforcement Learning, Fast and Slow

Matthew Botvinick et al.

TRENDS IN COGNITIVE SCIENCES (2019)

Review Engineering, Civil

A quantitative review of wind farm control with the objective of wind farm power maximization

Ali C. Kheirabadi et al.

JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS (2019)

Article Engineering, Electrical & Electronic

Distributed optimal wind farm control for fatigue load minimization: A consensus approach

Stefanos Baros et al.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2019)

Article Green & Sustainable Science & Technology

An active power control approach for wake-induced load alleviation in a fully developed wind farm boundary layer

Mehdi Vali et al.

WIND ENERGY SCIENCE (2019)

Article Automation & Control Systems

Model-based vs data-driven adaptive control: An overview

Mouhacine Benosman

INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING (2018)

Article Green & Sustainable Science & Technology

Optimization of wind turbines siting in a wind farm using genetic algorithm based local search

Ali M. Abdelsalam et al.

RENEWABLE ENERGY (2018)

Article Green & Sustainable Science & Technology

Decomposition based multi-objective evolutionary algorithm for windfarm layout optimization

Partha P. Biswas et al.

RENEWABLE ENERGY (2018)

Article Engineering, Electrical & Electronic

Decentralized Model-Free Wind Farm Control via Discrete Adaptive Filtering Methods

Shan Zhong et al.

IEEE TRANSACTIONS ON SMART GRID (2018)

Article Green & Sustainable Science & Technology

A control-oriented dynamic wind farm model: WFSim

Sjoerd Boersma et al.

WIND ENERGY SCIENCE (2018)

Article Energy & Fuels

Combined Active and Reactive Power Control of Wind Farms Based on Model Predictive Control

Haoran Zhao et al.

IEEE TRANSACTIONS ON ENERGY CONVERSION (2017)

Article Multidisciplinary Sciences

Mastering the game of Go without human knowledge

David Silver et al.

NATURE (2017)

Proceedings Paper Automation & Control Systems

Distributed Extremum Seeking Control for Wind Farm Power Maximization

Judith Ebegbulem et al.

IFAC PAPERSONLINE (2017)

Proceedings Paper Energy & Fuels

Verification and Calibration of a Reduced Order Wind Farm Model by Wind Tunnel Experiments

J. Schreiber et al.

WAKE CONFERENCE 2017 (2017)

Article Energy & Fuels

Wind farm hub height optimization

Ahmadreza Vasel-Be-Hagh et al.

APPLIED ENERGY (2017)

Article Thermodynamics

Optimization of offshore wind farm layout in restricted zones

Peng Hou et al.

ENERGY (2016)

Article Automation & Control Systems

Bayesian Ascent: A Data-Driven Optimization Scheme for Real-Time Control With Application to Wind Farm Power Maximization

Jinkyoo Park et al.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2016)

Article Multidisciplinary Sciences

Mastering the game of Go with deep neural networks and tree search

David Silver et al.

NATURE (2016)

Article Thermodynamics

Cooperative wind turbine control for maximizing wind farm power using sequential convex programming

Jinkyoo Park et al.

ENERGY CONVERSION AND MANAGEMENT (2015)

Article Thermodynamics

Multi-objective genetic algorithm based innovative wind farm layout optimization method

Ying Chen et al.

ENERGY CONVERSION AND MANAGEMENT (2015)

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)

Article Green & Sustainable Science & Technology

Solving the wind farm layout optimization problem using random search algorithm

Ju Feng et al.

RENEWABLE ENERGY (2015)

Article Engineering, Electrical & Electronic

Power System Stability Control for a Wind Farm Based on Adaptive Dynamic Programming

Yufei Tang et al.

IEEE TRANSACTIONS ON SMART GRID (2015)

Article Green & Sustainable Science & Technology

Optimized Placement of Wind Turbines in Large-Scale Offshore Wind Farm Using Particle Swarm Optimization Algorithm

Peng Hou et al.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2015)

Article Energy & Fuels

Survey of wind farm control-power and fatigue optimization

Torben Knudsen et al.

WIND ENERGY (2015)

Article Computer Science, Artificial Intelligence

Wind turbine selection for wind farm layout using multi-objective evolutionary algorithms

Francisco G. Montoya et al.

EXPERT SYSTEMS WITH APPLICATIONS (2014)

Article Automation & Control Systems

A Model-Free Approach to Wind Farm Control Using Game Theoretic Methods

Jason R. Marden et al.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2013)

Article Green & Sustainable Science & Technology

A fast and effective local search algorithm for optimizing the placement of wind turbines

Markus Wagner et al.

RENEWABLE ENERGY (2013)

Article Green & Sustainable Science & Technology

Wind farm layout optimization using particle filtering approach

Yunus Eroglu et al.

RENEWABLE ENERGY (2013)

Article Engineering, Mechanical

An Extended Pattern Search Approach to Wind Farm Layout Optimization

Bryony L. Du Pont et al.

JOURNAL OF MECHANICAL DESIGN (2012)

Article Green & Sustainable Science & Technology

Wake effect in wind farm performance: Steady-state and dynamic behavior

F. Gonzalez-Longatt et al.

RENEWABLE ENERGY (2012)

Review Green & Sustainable Science & Technology

Wind farm micro-siting by Gaussian particle swarm optimization with local search strategy

Chunqiu Wan et al.

RENEWABLE ENERGY (2012)

Article Green & Sustainable Science & Technology

Design of wind farm layout using ant colony algorithm

Yunus Eroglu et al.

RENEWABLE ENERGY (2012)

Article Green & Sustainable Science & Technology

Unrestricted wind farm layout optimization (UWFLO): Investigating key factors influencing the maximum power generation

Souma Chowdhury et al.

RENEWABLE ENERGY (2012)

Article Green & Sustainable Science & Technology

Optimization of wind farm turbines layout using an evolutive algorithm

Javier Serrano Gonzalez et al.

RENEWABLE ENERGY (2010)

Article Energy & Fuels

Modelling and Measuring Flow and Wind Turbine Wakes in Large Wind Farms Offshore

R. J. Barthelmie et al.

WIND ENERGY (2009)

Article Computer Science, Artificial Intelligence

An evolutive algorithm for wind farm optimal design

Jose Castro Mora et al.

NEUROCOMPUTING (2007)

Article Green & Sustainable Science & Technology

Placement of wind turbines using genetic algorithms

SA Grady et al.

RENEWABLE ENERGY (2005)

Review Automation & Control Systems

Constrained model predictive control: Stability and optimality

DQ Mayne et al.

AUTOMATICA (2000)