Stability and deadlock avoidance in distributed systems for traffic control

This paper describes a distributed method for traffic control and addresses the crucial problem of stability from both a formal and a practical perspective. Within a continuous-time and continuous-space approximation, a mathematical analysis first demonstrates the inherent stability of priority-based local decision making. Then, a more realistic model takes into account a network's finite connectivity and the time-discrete nature of events. This paper shows how deadlock-avoidance algorithms can be effectively included in a distributed system. Experimental results obtained by a realistic railway model prove that the inclusion of deadlock avoidance can provide early detection of critical situations, thus making it possible to schedule appropriate decisions or to drive a routing mechanism to enhance traffic flow.