Rapid urbanization and the growing demand for personal mobility have intensified traffic congestion, energy consumption, and environmental stress in metropolitan regions. Shared electric mobility offers a viable pathway toward sustainable urban transportation. However, large-scale adoption remains constrained by interrelated challenges, including fleet sizing, routing decisions, battery limitations, and the availability of charging infrastructure. Addressing these complexities requires advanced optimization approaches capable of managing nonlinear system dynamics, uncertain travel demand, and time-varying energy states. This paper presents a hybrid optimization framework that integrates Ant Colony Optimization, Bacterial Swarm Optimization, and Deep Reinforcement Learning (ACO–BSO–DRL) to jointly address fleet sizing, routing, and energy management in shared electric vehicle systems. Urban transportation networks are modeled as constrained graphs that capture the evolution of battery state of charge, charging and battery replacement decisions, and service deadline requirements. ACO supports efficient global route exploration, BSO enhances local solution refinement, and DRL adaptively updates decision policies and algorithm parameters in response to evolving system conditions. The framework is evaluated through extensive simulation studies based on realistic urban scenarios in Hyderabad and Bengaluru, India. A comparative analysis of standalone metaheuristic and learning-based methods demonstrates consistent reductions in required fleet size, improved energy utilization efficiency, and faster, more stable convergence. Multi-run statistical evaluation under randomized initial conditions further confirms the robustness and repeatability of the proposed approach. Overall, the results demonstrate that intelligent hybrid optimization has significant potential to enhance the efficiency and sustainability of shared electric mobility systems by reducing unnecessary vehicle deployment, minimizing battery replacements, and improving charging coordination. This work aligns with Sustainable Development Goals (SDG) 11 (Sustainable Cities and Communities), SDG 12 (Responsible Consumption and Production), and SDG 13 (Climate Action) by promoting energy-efficient, low-emission, and resilient urban transportation. Future extensions may incorporate real-time traffic data, renewable energy-powered charging infrastructure, and multi-modal mobility integration to enhance practical applicability.
Vijay Raviprabhakaran (Thu,) studied this question.