The Impact of Traffic Information Age on Congestion Mitigation

Abstract

In a dynamic network environment, the applicability of traffic engineering techniques requires fresh traffic measurements, fast routing solvers and frequent network reconfigurations. However, the ages of traffic measurements exhibit significant variation due to asynchronization and random communication delays between routers and controllers. Besides, frequent reconfigurations may incur routing instability, and hence impair network utilization. We devise a controller-assisted distributed routing scheme with recursive link weight reconfigurations, accounting for the impact of measurement ages and routing instability. In particular, the controller estimates the current traffic conditions using an autoregressive model to account for the uncertainty of the age of measurements. A fast load-sensitive link weight update algorithm swiftly computes a new set of OSPF weights by using the estimated link loads. To reduce complexity, a myopic policy is used to determine link weight reconfiguration, which takes into consideration congestion, measurement ages, and possible instability. Since distributed routing offers stronger robustness against link failures compared to centralized routing, the proposed adaptive routing approach offers desirable robustness and further benefits from the controller assistance via iterative search of better OSPF weights.