Improving the performance of the metaheuristic optimization algorithm SAR by leveraging the fine-tuning process

This article introduces the Enhanced Search and Rescue Algorithm (ESAR), an optimization method that advances the standard Search and Rescue Algorithm (SAR) by balancing accuracy, success rate, and convergence time. Our study fine-tuned four crucial SAR parameters—population size, maximum iterations, maximum unsuccessful searches, and social effects. Using Design of Experiments (DOE) techniques and Response Surface Methodology (RSM), we assessed the impact of these parameters on performance metrics such as deviation from optimum, convergence time, and success rate. The models' validity was confirmed through Analysis of Variance (ANOVA), and an optimal parameter set was determined using the desirability function. Compared to the standard SAR, ESAR showed significant improvements in solution quality and stability, though convergence time increased slightly. The enhancements demonstrate a substantial performance increase in SAR algorithm efficiency.