CAM01-5: Low-Jitter Scheduling Algorithms for Deadline-Aware Packet Switches

Abstract

We study low jitter-scheduler design for deadline-aware input-queued (IQ) packet switches. We consider scheduling of traffic streams associated with service profiles, which reflect the inter-packet deadlines between packets constituting the stream. To make the NP-hard problem of scheduling with strict deadlines tractable, we use soft deadlines as a modeling tool, and study the scheduling problem with soft deadlines in a dynamic programming (DP) framework. We establish the optimality of a myopic scheduling policy for the canonical 2times2 crossbar switch. For bigger switches, we develop low-complexity approximations to the myopic policy (which is near-optimal), one based on the notion of neighborhood search, and two others based on convex relaxations of an integer programming problem. We demonstrate the efficacy of the proposed policies via simulations, employing good put as a performance metric. A key feature of the proposed policies is that they do not require knowledge of traffic statistics (rate, periodicity etc.), rendering them robust and amenable to implementation.