Spider Wasp Optimization Algorithm

This study aims to improve the performance of the Spider Wasp Optimization (SWO) algorithm, a swarm intelligence algorithm recently introduced in the literature, on various test functions with fixed and variable dimensions. Optimization can be defined as making a system as efficient as possible with minimal cost within certain constraints. Numerous optimization algorithms have been designed in the literature and used to obtain the best solutions for specific problems. The most critical aspects in solving these problems include correctly modeling the problem, determining the problem’s parameters and constraints, and finally selecting an appropriate meta-heuristic algorithm to solve the objective function. Not every algorithm is suitable for every problem structure. Some algorithms perform better on fixed-dimension test functions, while others in solving variable-dimension test functions. In this study, the performance of the SWO algorithm was evaluated on 10 test functions previously used in the literature, consisting of three fixed-dimension functions (Schaffer, Himmelblau and Kowalik Functions) and seven variable-dimension functions, including one unimodal function (Elliptic Function) and six multimodal functions (Non-Continuous Rastrigin, Alpine, Levy, Weierstrass, Michalewicz, and Dixon & Price Functions). The solution values obtained for each of the selected functions were compared with the solutions obtained using the Harris Hawks Optimizer (HHO), the Charged System Search (CSS), and the Backtracking Search Optimization Algorithm (BSA).