An intelligent multi-objective decision framework for Time–Cost–Quality optimization in construction scheduling using AHP and OBL–NSGA-III

Abstract

Construction scheduling requires simultaneous optimization of project time, cost, and quality; however, most existing time–cost trade-off (TCTO) models inadequately incorporate construction quality as a quantitative optimization objective. This study proposes an intelligent hybrid decision framework that integrates the Analytic Hierarchy Process (AHP) with an Opposition-Based Learning-enhanced Non-dominated Sorting Genetic Algorithm III (OBL–NSGA-III) to solve the time–cost–quality trade-off (TCQT) problem. AHP is employed to derive activity importance and quality indicator weights from expert judgments for constructing a Project Quality Index (PQI), while OBL–NSGA-III improves population diversity and convergence to generate high-quality Pareto-optimal solutions. The framework is validated using a real residential building project consisting of thirteen activities with multiple execution modes. The proposed model produced 23 Pareto-optimal scheduling alternatives, enabling decision-makers to select solutions that best satisfy project priorities. Comparative evaluation against NSGA-III, MOPSO, MOACO, OB-MODE, and LHS-based NSGA-III demonstrated superior convergence, solution diversity, hypervolume, and the generation of unique non-dominated solutions. Sensitivity analysis further confirmed the robustness of the selected schedules under varying stakeholder preferences. The proposed framework provides an effective and transparent decision-support tool for construction scheduling and establishes a flexible foundation for future extensions involving uncertainty, resource constraints, sustainability objectives, and digital construction technologies.