Design management for smart urban traffic: an IoV-Based multi-agent AI framework for adaptive signal control

Abstract

This study develops an adaptive multi-agent traffic-management framework that responds to real-time urban traffic conditions using Internet of Vehicles (IoV) traffic-state information and artificial intelligence. Remote-sensing information is discussed as a contextual extension of the broader framework rather than as an experimentally validated input in the present evaluation. A Sustainable Multi-Agent Traffic Management Strategy (SMATMS) is implemented using a Galactic Swarm Optimized Deep Q-Network (GSO-DQN). The empirical evaluation uses traffic-state variables available in the Urban Traffic Light Control Dataset and considers two- and six-intersection multi-agent reinforcement-learning scenarios. GSO is positioned as an outer optimization layer that supports exploration of learning/control parameter configurations, while DQN performs sequential signal-control decisions. The reported aggregate comparisons show favorable observed mean performance for GSO-DQN relative to MADDPG and MARDDPG in reward, delay, queue length, travel time, and pedestrian waiting across the two evaluated scenarios. Because the archived results are aggregate summaries rather than a repeated-seed inferential dataset, the revised manuscript treats these differences descriptively and does not claim formal statistical significance. The framework provides an adaptive AI-based approach for coordinated traffic-signal control and supports traffic-efficiency-related sustainability objectives in the evaluated multi-intersection settings. Claims concerning metropolitan-scale scalability, direct emission reduction, and operational remote-sensing fusion are explicitly limited and identified as priorities for future validation.