Intelligent Optimization of Antenna Parameters Using Machine Learning Algorithms
Year: 2026
Type: article
Abstract: Parameter optimization of antennas is an extremely resource-intensive task in contemporary wireless systems design, especially considering the increasing complexity of antenna geometry and tightening constraints in terms of performance at millimeter-wave and terahertz frequencies. In this paper, we consider a systematic study of the application of machine learning algorithms in antenna parameter optimization with a particular focus on surrogate modeling and regression-based ensemble approaches. Our approach involves development of a closed-loop methodology based on generation of electromagnetic simulation data, feature engineering, model selection, and iterative training of a machine learning-based optimizer. We evaluate three algorithm families: tree-based ensembles, neural network surrogates, and kernel methods as possible candidates for predicting antenna metrics based on its geometry. The analysis of optimization process reveals that ensemble algorithms, such as random forest regressor, have very promising prospects for significantly lowering the number of simulations needed during optimization while preserving design accuracy within given parameter spaces. The comparison of algorithms is carried out by means of evaluating their performance according to several criteria: convergence rate, efficiency of data use, robustness to variations in parameters.
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Keywords: antenna parameter optimization, surrogate models, random forest regression, neural network surrogate model, kernel methods, decision tree ensembles, feature engineering, closed-loop optimization, millimeter-wave antennas, terahertz antennas, antenna geometry, convergence rate, parameter variation robustness
Open Access status: green
OpenAlex ID: W7235212803
