The rapid growth of populations and industrial activities has intensified the need to optimize resource management and reduce environmental impacts. A promising pathway toward sustainable development is the gradual replacement of fossil fuel vehicles with electric vehicles (EVs). However, managing EV operations, particularly regarding depot siting and vehicle routing, is a complex challenge that requires balancing economic, environmental, and social objectives. This research proposes a model for designing an intelligent and sustainable transportation system for waste collection using EV fleets. The model simultaneously determines optimal depot locations from a set of candidates and identifies efficient vehicle routes. Its dual objectives are to minimize total costs, including depot set-up, operation, and travel costs, and to minimize maximum travel time, ensuring equitable workload distribution among drivers. Beyond reducing costs and emissions, the model incorporates social equity considerations in balancing driver travel times. EV limitations, such as restricted range, are explicitly addressed. To solve small-scale instances, the ϵ-constraint method was applied, while medium- and large-scale instances were tackled with two multi-objective metaheuristics: the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Multi-Objective Particle Swarm Optimization (MOPSO). The results demonstrate the model’s sensitivity to system parameters such as vehicle capacity and demand rates. Statistical comparative analysis revealed that both algorithms successfully optimized the primary objective functions without significant differences. However, they exhibited distinct performance metric strengths; NSGA-II demonstrated statistically significant advantages in computational efficiency, solution quantity, and uniform distribution, while MOPSO excelled in convergence quality and closeness to the true Pareto front. Furthermore, the practical applicability of the proposed model is validated through a real-world case study of a municipal solid waste management network in Southern Tehran. This research contributes a comprehensive framework for optimizing EV-based waste collection systems, offering a meaningful step toward sustainable and intelligent urban transportation. The findings provide a theoretical framework and strategic insights for transportation managers and policymakers seeking effective strategies for environmentally responsible and socially equitable waste collection.
Feyzli et al. (Mon,) studied this question.