A Trust-Region Parallel Bayesian Optimization Method for Simulation-Driven Antenna Design

Zhou, Jinzhu; Yang, Zhanbiao; Yu, Shengbao; Kang, Le; Li, Haitao; Wang, Mei; Zhang, Zhiya

doi:10.1109/tap.2020.3044393

Cited by 42 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An infinite version could possibly be entertained via spectral methods, e.g., based on Gauthier and Bay (2012). In such a case, the use of a trust-region (TR) can limit the size of the search space drastically, which has been shown to be quite beneficial in high-dimension (Regis, 2016;Eriksson et al, 2019;Diouane et al, 2021;Zhou et al, 2021;Daulton et al, 2021), perhaps at the cost of a less global search (possibly compensated for with restarts or parallel TR). To further avoid the attraction of the boundary of the TR,…”

Section: High-dimensional Acquisition Function Optimizationmentioning

confidence: 99%

A survey on high-dimensional Gaussian process modeling with application to Bayesian optimization

Binois¹,

Wycoff²

2021

Preprint

View full text Add to dashboard Cite

Extending the efficiency of Bayesian optimization (BO) to larger number of parameters has received a lot of attention over the years. Even more so has Gaussian process regression modeling in such contexts, on which most BO methods are based. A variety of structural assumptions have been tested to tame high dimension, ranging from variable selection and additive decomposition to low dimensional embeddings and beyond. Most of these approaches in turn require modifications of the acquisition function optimization strategy as well. Here we review the defining assumptions, and discuss the benefits and drawbacks of these approaches in practice.

show abstract

Section: High-dimensional Acquisition Function Optimizationmentioning

confidence: 99%

A survey on high-dimensional Gaussian process modeling with application to Bayesian optimization

Binois¹,

Wycoff²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Design of modern antenna systems faces numerous challenges, partially related to the increase of performance requirements, which may be attributed to emerging application areas such as internet of things 7 , 8 , 5G wireless communications 9 , 10 , medical imaging 11 , remote sensing 12 , as well as wearable 13 or implantable devices 14 . Furthermore, the designers have to address the demands for additional functionalities, including multi-band 15 or MIMO operation 16 , circular polarization 17 , polarization/pattern diversity 18 , and band-notch operation 19 .…”

Section: Introductionmentioning

confidence: 99%

Reduced-cost two-level surrogate antenna modeling using domain confinement and response features

Pietrenko‐Dabrowska

Kozieł

Ullah

2022

Sci Rep

View full text Add to dashboard Cite

Electromagnetic (EM) simulation tools have become indispensable in the design of contemporary antennas. Still, the major setback of EM-driven design is the associated computational overhead. This is because a single full-wave simulation may take from dozens of seconds up to several hours, thus, the cost of solving design tasks that involve multiple EM analyses may turn unmanageable. This is where faster system representations (surrogates) come into play. Replacing expensive EM-based evaluations by cheap yet accurate metamodels seems to be an attractive solution. Still, in antenna design, application of surrogate models is hindered by the curse of dimensionality. A practical workaround has been offered by the recently reported reference-design-free constrained modeling techniques that restrict the metamodel domain to the parameter space region encompassing high-quality designs. Therein, the domain is established using only a handful of EM-simulations. This paper proposes a novel modeling technique, which incorporates the response feature technology into the constrained modeling framework. Our methodology allows for rendering accurate surrogates using exceptionally small training data sets, at the expense of reducing the generality of the modeling procedure to antennas that exhibit consistent shape of input characteristics. The proposed technique can be employed in other fields that employ costly simulation models (e.g., mechanical or aerospace engineering).

show abstract

“…In the evolution of the SADEA series, the main innovations locate in the model management method and the search operators. Considering the surrogate modeling method, to the best of our knowledge, not only the SADEA series but Gaussian process (GP) machine learning is also used by most online state-of-the-art surrogate model-assisted antenna optimization methods [14], [15], [16], [17]. For the often highly multimodal antenna design landscape [10], a strong machine learning method is essential.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Method for Antenna Design Based on a Self-Adaptive Bayesian Neural Network-Assisted Global Optimization Technique

Liu

Ur-Rehman

et al. 2022

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

Gaussian process (GP) is a very popular machine learning method for online surrogate model-assisted antenna design optimization. Despite many successes, two improvements are important for GP-based antenna global optimization methods, including (1) the convergence speed (i.e., the number of necessary electromagnetic simulations to obtain a high-performance design), and (2) the GP model training cost when there are several tens of design variables and/or specifications. In both aspects, state-of-the-art GP-based methods show practical but not desirable performance. Therefore, a new method, called self-adaptive Bayesian neural network surrogate model-assisted differential evolution for antenna optimization (SB-SADEA), is presented in this paper. The key innovations include: (1) The introduction of the Bayesian neural network (BNN)-based antenna surrogate modeling method into this research area, replacing GP modeling, and (2) a bespoke self-adaptive lower confidence bound method for antenna design landscape making use of the BNN-based antenna surrogate model. The performance of SB-SADEA is demonstrated by two challenging design cases, showing considerable improvement in terms of both convergence speed and machine learning cost compared to state-of-the-art GP-based antenna global optimization methods.

show abstract

A Trust-Region Parallel Bayesian Optimization Method for Simulation-Driven Antenna Design

Cited by 42 publications

References 47 publications

A survey on high-dimensional Gaussian process modeling with application to Bayesian optimization

A survey on high-dimensional Gaussian process modeling with application to Bayesian optimization

Reduced-cost two-level surrogate antenna modeling using domain confinement and response features

An Efficient Method for Antenna Design Based on a Self-Adaptive Bayesian Neural Network-Assisted Global Optimization Technique

Contact Info

Product

Resources

About