Balancing Exploration and Exploitation Through a Sequential Hybrid of Roach Infestation and Mayfly Algorithms for Constrained Engineering Design Optimization

Abstract

Maintaining an effective balance between exploration and exploitation is essential during optimization processes, from mathematical functions to more complex problems such as constrained engineering design optimization, particularly when addressing highly nonlinear issues with numerous local optima and strict feasibility requirements. This manuscript introduces a sequential hybrid metaheuristic that integrates the global search virtues of the roach infestation optimization (RIO) framework with the local refinement strengths of the mayfly algorithm (MA) to boost search efficiency in constrained optimization problems. This strategy leverages the best of both algorithms, thereby increasing population diversity, accelerating convergence, and improving solution quality while maintaining feasible solutions within the engineering constraints. Performance was evaluated using various classic engineering design benchmark problems widely used in the optimization literature. Experimental results evaluated solution quality and population diversity, comparing the proposed method with the original RIO and MA algorithms and with other known metaheuristic approaches. In the statistical validation, distribution‐free statistical tests were performed to evaluate the importance of the generated outcomes. Our observations indicate that the introduced sequential hybrid scheme attains an enhanced coordination of global and local search, enabling the system to mitigate early stagnation and improve optimization performance in restricted search spaces. This provides a highly viable and dependable alternative for engineering optimization layouts and establishes a foundation for future adaptive and fuzzy logic‐based hybrid optimization approaches.