An adaptive switch strategy for acquisition functions in Bayesian optimization of wind farm layout

TL;DR

This work tackles WFLO where wake effects degrade energy production and high-fidelity CFD evaluations are expensive. It introduces a Bayesian optimization framework that adaptively switches acquisition functions between MSP (exploitation-focused) and MES (information-theoretic exploration), with constrained-LHS initialization and a Kriging surrogate to efficiently navigate irregular design spaces. The approach is validated on Ackley benchmarks and applied to WFLO with Gaussian wakes and CFD simulations, showing substantial reductions in expensive evaluations while achieving near-optimal AEP and outperforming traditional heuristics. The results suggest that this adaptive switch strategy enables practical, high-fidelity WFLO, with potential for further gains via multi-fidelity and dimensionality-reduction techniques.

Abstract

Wind farm layout optimization (WFLO), which seeks to maximizing annual energy production by strategically adjusting wind turbines' location, is essential for the development of large-scale wind farms. While low-fidelity methods dominate WFLO studies, high-fidelity methods are less commonly applied due to their significant computational costs. This paper introduces a Bayesian optimization framework that leverages a novel adaptive acquisition function switching strategy to enhance the efficiency and effectiveness of WFLO using high-fidelity modeling methods. The proposed switch acquisition functions strategy alternates between MSP and MES acquisition functions, dynamically balancing exploration and exploitation. By iteratively retraining the Kriging model with intermediate optimal layouts, the framework progressively refines its predictions to accelerate convergence to optimal solutions. The performance of the switch-acquisition-function-based Bayesian optimization framework is first validated using 4- and 10-dimensional Ackley benchmark functions, where it demonstrates superior optimization efficiency compared to using MSP or MES alone. The framework is then applied to WFLO problems using Gaussian wake models for three varying wind farm cases. Results show that the switch-acquisition-function-based Bayesian optimization framework outperforms traditional heuristic algorithms, achieving near-optimal annual energy output with significantly fewer calculations. Finally, the framework is extended to high-fidelity WFLO by coupling it with CFD simulations, where turbine rotors are modeled as actuator disks. The novel switch-acquisition-function-based Bayesian optimization enables more effective exploration to achieve higher annual energy production in WFLO, advancing the design of more effective wind farm layouts.

Figures (13)

• Figure 1: The workflow of Bayesian optimization using the proposed adaptive switching strategy between MSP and MES AFs.
• Figure 2: The response surface of the 2 dimensional Ackley function
• Figure 3: The violin plots of the optimized results obtained by using switch-AF, MSP and MES for ($a$) the 4D Ackley function and ($b$) the 10D Ackley function.
• Figure 4: The development of the optimized results obtained by using switch-AF, MSP and MES for ($a$) the 4D Ackley function and ($b$) the 10D Ackley function.
• Figure 5: $(a)$ Boundary for Case I, $(b)$ boundary for Case II, $(c)$ boundary for Case III.