Resilient Multi-Agent State Estimation for Smart City Traffic: A Systems Engineering Approach to Emission Mitigation

Uninterrupted traffic flow monitoring is essential for optimal resource allocation and minimizing vehicular emissions in smart cities. However, centralized traffic management architectures are highly vulnerable to single points of failure. When structural sensor malfunctions occur, the resulting network unobservability paralyzes dynamic signalization, triggering cascading traffic congestion, extended idling times, and severe greenhouse gas emissions. This cyber-ecological vulnerability motivates the need for a resilient, decentralized approach. The authors propose the Hybrid Multi-Agent State Estimation (H-MASE) protocol, a fully decentralized decision-support framework designed from an applied systems reliability engineering perspective. The goal is to maintain accurate traffic state estimation even under severe hardware failures, thereby ensuring ecological resilience and optimal resource utilization.

Numerical simulations demonstrate that the H-MASE protocol yields a highly resilient optimality gap even under catastrophic hardware failures. Specifically, the Root Mean Square Error (RMSE) is merely 0.81 vehicles per estimated state. This performance is maintained across various failure scenarios, including the loss of multiple sensors. The distributed consensus mechanism ensures that the global estimate remains accurate despite local faults, preventing the cascading congestion and emission increases that would occur in centralized systems. The autonomous anomaly detection successfully isolates severe structural faults without triggering false alarms under bounded disturbances.