Minimizing Flow Completion Times using Adaptive Routing over Inter-Datacenter Wide Area Networks

TL;DR

This paper presents an adaptive routing method for inter-datacenter networks that significantly reduces bandwidth usage and flow completion times by dynamically assigning paths based on network conditions.

Contribution

It introduces an alternative adaptive routing approach that decreases bandwidth consumption by at least 50% and flow completion times by at least 40%, improving over traditional bandwidth-utilization-based methods.

Findings

Bandwidth usage reduced by up to 50%

Flow completion times decreased by up to 40%

Effective across various scheduling policies and flow sizes

Abstract

Inter-datacenter networks connect dozens of geographically dispersed datacenters and carry traffic flows with highly variable sizes and different classes. Adaptive flow routing can improve efficiency and performance by assigning paths to new flows according to network status and flow properties. A popular approach widely used for traffic engineering is based on current bandwidth utilization of links. We propose an alternative that reduces bandwidth usage by up to at least 50% and flow completion times by up to at least 40% across various scheduling policies and flow size distributions.