Optimizing wind farms layouts for maximum energy production using probabilistic inference: Benchmarking reveals superior computational efficiency and scalability

Successful development of wind farms relies on the optimal siting of wind turbines to maximize the power capacity under stochastic wind conditions and wake losses caused by neighboring turbines. This paper presents a novel method to quickly generate approximate optimal layouts to support infrastructure design decisions. We model the quadratic integer formulation of the discretized layout design problem with an undirected graph that succinctly captures the spatial dependencies of the design parameters caused by wake interactions. On the undirected graph, we apply probabilistic inference using sequential tree-reweighted message passing to approximate turbine siting. We assess the effectiveness of our method by benchmarking against a state-of-the-art branch and cut algorithm under varying wind regime complexities and wind farm discretization resolutions. For low resolutions, probabilistic inference can produce optimal or nearly optimal turbine layouts that are within 3% of the power capacity of the optimal layouts achieved by state-of-the-art formulations, at a fraction of the computational cost. As the discretization resolution (and thus the problem size) increases, probabilistic inference produces optimal layouts with up to 9% more power capacity than the best state-of-the-art solutions at a much lower computational cost.

[1]  B. Koren,et al.  Review of computational fluid dynamics for wind turbine wake aerodynamics , 2011 .

[2]  Xiaowei Zhao,et al.  Quantification of parameter uncertainty in wind farm wake modeling , 2020 .

[3]  M. Y. Hussaini,et al.  Placement of wind turbines using genetic algorithms , 2005 .

[4]  Yair Weiss,et al.  Approximate Inference and Protein-Folding , 2002, NIPS.

[5]  E. S. Politis,et al.  Modelling and Measuring Flow and Wind Turbine Wakes in Large Wind Farms Offshore , 2009, Renewable Energy.

[6]  Jie Zhang,et al.  Optimizing the arrangement and the selection of turbines for wind farms subject to varying wind conditions , 2013 .

[7]  Achille Messac,et al.  Characterizing and mitigating the wind resource-based uncertainty in farm performance , 2012 .

[8]  J. Christopher Beck,et al.  Constrained multi-objective wind farm layout optimization: Novel constraint handling approach based on constraint programming , 2018, Renewable Energy.

[9]  Zhe Chen,et al.  Optimization of offshore wind farm layout in restricted zones , 2016 .

[10]  Hongxing Yang,et al.  Validations of three-dimensional wake models with the wind field measurements in complex terrain , 2019 .

[11]  Kincho H. Law,et al.  Layout optimization for maximizing wind farm power production using sequential convex programming , 2015 .

[12]  Cristina H. Amon,et al.  Continuous adjoint formulation for wind farm layout optimization: A 2D implementation , 2018, Applied Energy.

[13]  David Sontag,et al.  Efficiently Searching for Frustrated Cycles in MAP Inference , 2012, UAI.

[14]  M. Payán,et al.  Overall design optimization of wind farms , 2011 .

[15]  Rafic Younes,et al.  Review of performance optimization techniques applied to wind turbines , 2015 .

[16]  Martin J. Wainwright,et al.  MAP estimation via agreement on trees: message-passing and linear programming , 2005, IEEE Transactions on Information Theory.

[17]  Cristina H. Amon,et al.  Optimal design of wind farms in complex terrains using computational fluid dynamics and adjoint methods , 2020 .

[18]  Cristina H. Amon,et al.  Toward efficient optimization of wind farm layouts: Utilizing exact gradient information , 2016 .

[19]  Andrew Ning,et al.  Massive simplification of the wind farm layout optimization problem , 2019, Wind Energy Science.

[20]  Rosalind Archer,et al.  Wind Turbine Interference in a Wind Farm Layout Optimization Mixed Integer Linear Programming Model , 2011 .

[21]  Daniel P. Huttenlocher,et al.  Efficient Belief Propagation for Early Vision , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[22]  Gunner Chr. Larsen,et al.  A Simple Wake Calculation Procedure , 1988 .

[23]  Rebecca J. Barthelmie,et al.  Analytical modelling of wind speed deficit in large offshore wind farms , 2006 .

[24]  Hester Bijl,et al.  Large Eddy Simulation of wind farm aerodynamics : a review , 2014 .

[25]  Tommi S. Jaakkola,et al.  Approximate inference in graphical models using lp relaxations , 2010 .

[26]  Cristina H. Amon,et al.  Chapter 28: Robust Wind Farm Layout Optimization , 2017 .

[27]  Cristina H. Amon,et al.  Gradient-based multidisciplinary design of wind farms with continuous-variable formulations , 2017 .

[28]  Cristina H. Amon,et al.  A mechanistic semi-empirical wake interaction model for wind farm layout optimization , 2015 .

[29]  J. Sørensen,et al.  Wind turbine wake aerodynamics , 2003 .

[30]  Jim Y. J. Kuo,et al.  Wind Farm Yaw Optimization via Random Search Algorithm , 2020, Energies.

[31]  Luciano Castillo,et al.  Unrestricted wind farm layout optimization (UWFLO): Investigating key factors influencing the maximum power generation , 2012 .

[32]  Ernesto Benini,et al.  Evaluation of the different aerodynamic databases for vertical axis wind turbine simulations , 2014 .

[33]  G. Gualtieri Comparative analysis and improvement of grid-based wind farm layout optimization , 2020 .

[34]  Josef Kittler,et al.  Contextual classification of multispectral pixel data , 1984, Image Vis. Comput..

[35]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[36]  Carlo Poloni,et al.  Optimization of wind turbine positioning in large windfarms by means of a genetic algorithm , 1994 .

[37]  David A. Romero,et al.  Analysis and Modifications of Turbulence Models for Wind Turbine Wake Simulations in Atmospheric Boundary Layers , 2018 .

[38]  Javier Serrano González,et al.  Optimization of wind farm turbines layout using an evolutive algorithm , 2010 .

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

[40]  Zhe Chen,et al.  Optimized Placement of Wind Turbines in Large-Scale Offshore Wind Farm Using Particle Swarm Optimization Algorithm , 2015, IEEE Transactions on Sustainable Energy.

[41]  KolmogorovVladimir Convergent Tree-Reweighted Message Passing for Energy Minimization , 2006 .

[42]  Javier Serrano González,et al.  A review and recent developments in the optimal wind-turbine micro-siting problem , 2014 .

[43]  Enrico G. A. Antonini CFD-based Methodology for Wind Farm Layout Optimization , 2018 .

[44]  Enrico G. A. Antonini,et al.  Atmospheric pressure gradients and Coriolis forces provide geophysical limits to power density of large wind farms , 2021 .

[45]  Cristina H. Amon,et al.  The impact of land use constraints in multi-objective energy-noise wind farm layout optimization , 2016 .

[46]  Ryan P. Adams,et al.  Revisiting uncertainty in graph cut solutions , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[47]  Peter Graf,et al.  Adjoint Optimization of Wind Farm Layouts for Systems Engineering Analysis , 2016 .

[48]  Vladimir Kolmogorov Tree-Reweighted Message Passing , 2014, Tractability.

[49]  Jonathan Cagan,et al.  An Extended Pattern Search Approach to Wind Farm Layout Optimization , 2010, DAC 2010.

[50]  Pushmeet Kohli,et al.  Measuring uncertainty in graph cut solutions , 2008, Comput. Vis. Image Underst..

[51]  Ivan Mustakerov,et al.  Wind turbines type and number choice using combinatorial optimization , 2010 .

[52]  Zhe Chen,et al.  Combined optimization for offshore wind turbine micro siting , 2017 .

[53]  P. Forooghi,et al.  Quantifying structural uncertainties in Reynolds-averaged Navier–Stokes simulations of wind turbine wakes , 2021 .

[54]  Vladimir Kolmogorov,et al.  Convergent Tree-Reweighted Message Passing for Energy Minimization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[55]  Cristina H. Amon,et al.  Improving CFD wind farm simulations incorporating wind direction uncertainty , 2019, Renewable Energy.

[56]  J. C. Smith,et al.  Wind Farm Optimization , 2005 .

[57]  Ryan N. King,et al.  Optimization of wind plant layouts using an adjoint approach , 2017 .

[58]  Nanning Zheng,et al.  Stereo Matching Using Belief Propagation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[59]  F. Porté-Agel,et al.  A new analytical model for wind-turbine wakes , 2013 .

[60]  Tomaso Poggio,et al.  Probabilistic Solution of Ill-Posed Problems in Computational Vision , 1987 .

[61]  Jens Nørkær Sørensen,et al.  A new wake model and comparison of eight algorithms for layout optimization of wind farms in complex terrain , 2020, Applied Energy.

[62]  Hou-Sheng Huang,et al.  Distributed Genetic Algorithm for Optimization of Wind Farm Annual Profits , 2007, 2007 International Conference on Intelligent Systems Applications to Power Systems.

[63]  Mohammad Yusri Hassan,et al.  Wake effect modeling: A review of wind farm layout optimization using Jensen׳s model , 2016 .

[64]  Xing Zhang,et al.  Wind farm micro-siting by Gaussian particle swarm optimization with local search strategy , 2012 .

[65]  J. Christopher Beck,et al.  Wind farm layout optimization on complex terrains – Integrating a CFD wake model with mixed-integer programming , 2016 .

[66]  Alireza Emami,et al.  New approach on optimization in placement of wind turbines within wind farm by genetic algorithms , 2010 .

[67]  Cristina H. Amon,et al.  A new mathematical programming approach to optimize wind farm layouts , 2014 .

[68]  Vladimir Kolmogorov,et al.  Minimizing Nonsubmodular Functions with Graph Cuts-A Review , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[69]  Ernesto Benini,et al.  Innovative Discrete-Vortex Model for Dynamic Stall Simulations , 2015 .

[70]  E. Pyrgioti,et al.  Optimal placement of wind turbines in a wind park using Monte Carlo simulation , 2008 .

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

[72]  Tommi S. Jaakkola,et al.  Tightening LP Relaxations for MAP using Message Passing , 2008, UAI.

[73]  Cristina H. Amon,et al.  Multi-Objective Wind Farm Layout Optimization Considering Energy Generation and Noise Propagation With NSGA-II , 2014 .

[74]  Richard Szeliski,et al.  A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[75]  Juan J. Alonso,et al.  Polynomial chaos to efficiently compute the annual energy production in wind farm layout optimization , 2018, Wind Energy Science.

[76]  Krystel K. Castillo-Villar,et al.  A Review of Methodological Approaches for the Design and Optimization of Wind Farms , 2014 .