Boosting multi-objective aquila optimizer with opposition-based learning for large-scale time–cost trade-off problems

Abstract

This study presents an enhanced version of the Aquila optimizer (AO), known as the opposition-based aquila optimizer (OBAO), which incorporates opposition-based learning (OBL) to enhance performance. By considering both current solutions and their opposites, OBL expands the search space, increasing the chances of avoiding local optima and identifying superior solutions. Additionally, OBL replaces the expanded and narrowed exploitation methods of the original AO, reducing computational complexity and enhancing the efficiency of the proposed model. The proposed OBAO is applied to a large-scale time–cost trade-off problems (TCTP) with 630 activities, demonstrating its capability to efficiently achieve optimal or near-optimal solutions. Comparative assessments against advanced optimization algorithms, including teaching learning-based optimization (TLBO), genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), and plain AO indicate that OBAO achieves better solutions in terms of number of objective function evaluations (NFE) and hypervolume (HV) indicator. The findings suggest that OBAO is a promising alternative for optimizing large-scale construction projects in construction management field.