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

This paper describes a data-driven approach for real-time control of a physical system. Specifically, this paper focuses on the cooperative wind farm control where the objective is to maximize the total wind farm power production by using control actions as an input and measured power as an output. For real time, data-driven wind farm control, it is imperative that the optimization algorithm is able to improve a target wind farm power production by executing as small number of trial actions as possible using the wind farm power monitoring data. To achieve this goal, we develop a Bayesian ascent (BA) algorithm by incorporating into the Bayesian optimization framework a strategy that regulates the search domain, as used in the trust region method. The BA algorithm is composed of two iterative phases, namely, learning and optimization phases. In the learning phase, the BA algorithm approximates the target function using Gaussian process regression to fit the measured input and output of the target system. In the optimization phase, the BA algorithm determines the next sampling point to learn more about the target function (exploration) as well as to improve the target value (exploitation). Specifically, the sampling strategy is designed to ensure that the input is selected within a trust region to improve the target value monotonically by gradually changing the input for a target system. The results from simulation studies using an analytical wind farm power function and experimental studies using scaled wind turbines show that the BA algorithm can achieve an almost monotonic increase in the target value.

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

[2]  Andreas Krause,et al.  Contextual Gaussian Process Bandit Optimization , 2011, NIPS.

[3]  Trevor Darrell,et al.  Active Learning with Gaussian Processes for Object Categorization , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[4]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[5]  Jorge J. Moré,et al.  Testing Unconstrained Optimization Software , 1981, TOMS.

[6]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[7]  Hemant Tyagi,et al.  Continuum Armed Bandit Problem of Few Variables in High Dimensions , 2013, WAOA.

[8]  Chunghun Kim,et al.  A model-free method for wind power plant control with variable wind , 2014, 2014 IEEE PES General Meeting | Conference & Exposition.

[9]  Daria Madjidian,et al.  A Stationary Turbine Interaction Model for Control of Wind Farms , 2011 .

[10]  Jan-Willem van Wingerden,et al.  SOWFA Super-Controller: A High-Fidelity Tool for Evaluating Wind Plant Control Approaches , 2013 .

[11]  J. W. van Wingerden,et al.  Maximum power‐point tracking control for wind farms , 2015 .

[12]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[13]  J. Jonkman,et al.  Definition of a 5-MW Reference Wind Turbine for Offshore System Development , 2009 .

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

[15]  Nikolaos V. Sahinidis,et al.  Derivative-free optimization: a review of algorithms and comparison of software implementations , 2013, J. Glob. Optim..

[16]  Michael A. Osborne.  Bayesian Gaussian processes for sequential prediction, optimisation and quadrature , 2010 .

[17]  Hong Wan,et al.  Stochastic Trust-Region Response-Surface Method (STRONG) - A New Response-Surface Framework for Simulation Optimization , 2013, INFORMS J. Comput..

[18]  D. Dennis,et al.  A statistical method for global optimization , 1992, [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics.

[19]  N. Jensen.  A note on wind generator interaction , 1983 .

[20]  Mato Baotic,et al.  Quasi-stationary optimal control for wind farm with closely spaced turbines , 2012, 2012 Proceedings of the 35th International Convention MIPRO.

[21]  Muyiwa S. Adaramola,et al.  Experimental investigation of wake effects on wind turbine performance , 2011 .

[22]  Steven L. Scott,et al.  A modern Bayesian look at the multi-armed bandit , 2010 .

[23]  Davide Medici,et al.  Experimental studies of wind turbine wakes : power optimisation and meandering , 2005 .

[24]  Kathryn E. Johnson,et al.  Wind farm control: Addressing the aerodynamic interaction among wind turbines , 2009, 2009 American Control Conference.

[25]  Andrew Swift,et al.  Characterizing power performance and wake of a wind turbine under yaw and blade pitch , 2016 .

[26]  Christine A. Shoemaker,et al.  ORBIT: Optimization by Radial Basis Function Interpolation in Trust-Regions , 2008, SIAM J. Sci. Comput..

[27]  D. Dennis,et al.  SDO : A Statistical Method for Global Optimization , 1997 .

[28]  Ervin Bossanyi,et al.  Wind Energy Handbook , 2001 .

[29]  M. Bierlaire,et al.  Boosters: A Derivative-Free Algorithm Based on Radial Basis Functions , 2009 .

[30]  M. Powell.  Developments of NEWUOA for minimization without derivatives , 2008 .

[31]  N. Jenkins,et al.  Wind Energy Handbook: Burton/Wind Energy Handbook , 2011 .

[32]  Leslie Pack Kaelbling,et al.  Algorithms for multi-armed bandit problems , 2014, ArXiv.

[33]  Doina Precup,et al.  Algorithms for multi-armed bandit problems , 2014, ArXiv.

[34]  M. J. D. Powell,et al.  UOBYQA: unconstrained optimization by quadratic approximation , 2002, Math. Program..

[35]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[36]  Michael I. Jordan,et al.  Learning with Mixtures of Trees , 2001, J. Mach. Learn. Res..

[37]  Csaba Szepesvári,et al.  –armed Bandits , 2022 .

[38]  Kincho H. Law,et al.  Cooperative wind turbine control for maximizing wind farm power using sequential convex programming , 2015 .

[39]  Nando de Freitas,et al.  A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning , 2010, ArXiv.

[40]  Jan-Åke Dahlberg,et al.  Potential improvement of wind turbine array efficiency by active wake control (AWC) , 2003 .