Edge‑Native Federated Multi‑Agent Traffic Signal Control with Smart Poles and Digital Twins: A VEINS–Simu5G Study
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Urban traffic congestion leads to prolonged delays, elevated emissions, and diminished safety across arterial networks. This paper proposes an edge‑native framework for intersection control that combines smart‑pole edge computing with federated multi‑agent reinforcement learning. Lightweight agents at each intersection learn locally from on‑pole sensors while a privacy‑preserving federated procedure periodically aggregates model updates across the network. The communication layer integrates IEEE 802.11p for low‑latency local V2X exchange and MQTT 5.0 for monitoring and model coordination. Evaluation is conducted in a digital‑twin‑in‑the‑loop environment that couples VEINS (OMNeT++–SUMO) with Simu5G to account for 802.11p and NR‑V2X link behavior. Emissions are estimated using SUMO’s HBEFA‑based model. Compared with fixed‑time, actuated, and non‑federated MARL baselines, the proposed approach shows the potential to reduce network‑wide average delay and queue length while simultaneously lowering CO₂ and NOx. The paper details the architecture, the learning and communication design, and a reproducible protocol for scenario construction, metrics, and statistical testing.
Abstract
Urban traffic congestion leads to prolonged delays, elevated emissions, and diminished safety across arterial networks. This paper proposes an edge‑native framework for intersection control that combines smart‑pole edge computing with federated multi‑agent reinforcement learning. Lightweight agents at each intersection learn locally from on‑pole sensors while a privacy‑preserving federated procedure periodically aggregates model updates across the network. The communication layer integrates IEEE 802.11p for low‑latency local V2X exchange and MQTT 5.0 for monitoring and model coordination. Evaluation is conducted in a digital‑twin‑in‑the‑loop environment that couples VEINS (OMNeT++–SUMO) with Simu5G to account for 802.11p and NR‑V2X link behavior. Emissions are estimated using SUMO’s HBEFA‑based model. Compared with fixed‑time, actuated, and non‑federated MARL baselines, the proposed approach shows the potential to reduce network‑wide average delay and queue length while simultaneously lowering CO₂ and NOx. The paper details the architecture, the learning and communication design, and a reproducible protocol for scenario construction, metrics, and statistical testing.