Improved queue-size scaling for input-queued switches via graph factorization

Abstract

This paper studies the scaling of the expected total queue size in an $n\times n$ input-queued switch, as a function of both the load $ρ$ and the system scale $n$. We provide a new class of scheduling policies under which the expected total queue size scales as $O\left( n(1-ρ)^{-4/3} \log \left(\max\{\frac{1}{1-ρ}, n\}\right)\right)$, over all $n$ and $ρ<1$, when the arrival rates are uniform. This improves over the previously best-known scalings in two regimes: $O\left(n^{1.5}(1-ρ)^{-1} \log \frac{1}{1-ρ}\right)$ when $Ω(n^{-1.5}) \le 1-ρ\le O(n^{-1})$ and $O\left(\frac{n\log n}{(1-ρ)^2}\right)$ when $1-ρ\geq Ω(n^{-1})$. A key ingredient in our method is a tight characterization of the largest $k$-factor of a random bipartite multigraph, which may be of independent interest.

42 pages, 4 figures