A Robust Surrogate-Assisted Framework for Simultaneous Multi-Parameter Optimization in Microstrip Antenna Design
Conventional optimization still poses a significant challenge when it comes to producing the designs required for modern communication technologies. Previous studies have mainly focused on effectiveness and computational efficiency, but have not sufficiently addressed robustness, an essential factor in surrogate-assisted optimization for Microstrip Antenna (MSA) design. Unlike existing surrogate-assisted optimization approaches, this study explicitly incorporates robustness analysis, statistical validation, and sensitivity-driven interpretability into a unified multi-parameter optimization framework. This framework is referred to as a Robustness-Driven Surrogate Optimization Framework (RDSOF). A regression-based Machine Learning (ML) approach using Extreme Gradient Boosting (XGBoost) is employed to model the relationship among 11 geometric input parameters and key antenna performance metrics, including the input reflection coefficient (S₁₁), Bandwidth (BW), and Voltage Standing Wave Ratio (VSWR). The model is trained on a simulation-generated dataset comprising 1,920 samples generated from diverse geometric configurations. The surrogate model is evaluated inside the optimization loop under four optimization scenarios. Following this, robustness and sensitivity analyses are conducted to assess the reliability and influence of the design parameters. The outcomes indicate that the Differential Evolution (DE) approach achieves superior Electromagnetic (EM) performance, particularly in minimizing S₁₁. However, Particle Swarm Optimization (PSO) demonstrates greater stability, as shown by the relatively small difference in fitness standard deviation among its default and tuned configurations. Overall, the proposed RDSOF demonstrates capability in balancing exploration and exploitation while emphasizing robustness and computational efficiency for Rectangular Microstrip Antenna (RMSA) design.