01671nas a2200169   4500000000100000000000100001008004100002260001200043100002400055700001700079700001900096700001800115245007100133856004100204490000700245520124900252       2021                            d  c03/20211 aTadeusz Czachórski1 aErol Gelenbe1 aGodlove Kuaban1 aDariusz Marek00aTime-Dependent Performance of a Multi-Hop Software Defined Network  uhttps://www.mdpi.com/journal/applsci0 v113 a<p>It has been recently observed that Software Defined Networks (SDN) can change the<br />
paths of different connections in the network at a relatively frequent pace to improve the overall<br />
network performance, including delay and packet loss, or to respond to other needs such as security.<br />
These changes mean that a network that SDN controls will seldom operate in steady state; rather,<br />
the network may often be in transient mode, especially when the network is heavily loaded and<br />
path changes are critically important. Hence, we propose a transient analysis of such networks to<br />
better understand how frequent changes in paths and the switches’ workloads may affect multi-hop<br />
networks’ performance. Since conventional queueing models are difficult to solve for transient<br />
behaviour and simulations take excessive computation time due to the need for statistical accuracy,<br />
we use a diffusion approximation to study a multi-hop network controlled by SDN. The results show<br />
that network optimization should consider the transient effects of SDN and that transients need to be<br />
included in the design of algorithms for SDN controllers that optimize network performance.</p>