End to end delay modeling of heterogeneous traffic flows in software defined 5G networks

In ultra-dense 5th Generation (5G) wireless networks, we believe that foreground User Datagram Protocol (UDP) traffic flow is ‘squeezed’ by Transmission Control Protocol (TCP) background because of increasing queue waiting time and extra transmission delay for each timeout in TCP congestion control mechanism. Therefore, traffic Heterogeneity which is defined by the rate between number of UDP over TCP traffic flows for each forwarding device, has become more significant. According to the 3rd Generation Partnership Project (3GPP) Release 13, conventional Long Term Evolution - Self Organize Networks (LTE-SON) does not consider Heterogeneity rate of traffic flows while balancing load between neighbor eNodeBs (eNBs). In order to reduce end to end delay (e2eDelay) of foreground TCP traffic flow, an optimal path should be selected by considering both load Intensity and traffic Heterogeneity level of eNBs. To do this, we propose a Software-Defined Networks (SDN)-based softwarization approach brought by 5G networks with three fold contributions: virtualization of topology graph (G), e2eDelay optimization which is run in terms of both load Intensity (ρ_j(t)) and Heterogeneity rate(H_j(t)), and novel Queuing Theory based OpenFlow (OF) switch model. Moreover, due to being bottleneck, centralized SDN-Controller is proposed to accelerated with novel three heuristics including shortest path and e2eDelay optimization algorithms running in parallel manner. More specifically, this process is combined into a novel closed-form expression of e2eDelay(T_i(t)) in two main parts: Data plane effect and Control plane effect. As a result, proposed SDN-based e2eDelay model serves foreground TCP traffic flow upto 74% and 98% less e2eDelay than LTE-SON and conventional LTE.