Centrality-Based Deployment of Queue Policies in Acyclic Multipath Routing Networks

Abstract

Excessive queueing delays constitute a significant impediment to latency-sensitive network applications. Although effective deployment of Active Queue Management (AQM) strategies has been proposed as a necessary solution, deployment remains sparse. This paper studies AQM deployment in a specific class of networks where routers/switches have a topological hierarchy, form acyclic paths, and adopt multipath routing. Our approach rests on the well-established premise that AQM deployment impacts packet-forwarding dynamics in networks carrying TCP flows, thus establishing a direct link between stability and network performance. We use fluid models for TCP and queue dynamics in the network, along with a simple threshold-based queue policy to outline a closed-loop model for the network. Stability analyses reveal that while the network is vulnerable to instability as the average round-trip time (RTT) of the TCP flows increases, it tolerates a much larger RTT without losing stability when the threshold-based AQM is deployed in an appropriate router. We then define a Katz centrality-based metric to choose the most appropriate router for AQM deployment, and argue that doing so ensures the greatest stabilising effect. Finally, packet-level simulations corroborate that the proposed deployment strategy ensures low-latency operation of the network.