Scalable guaranteed-bandwidth multicast service in software defined ISP networks

Abstract

New applications where anyone can broadcast video are becoming very popular on smartphones. With the advent of high definition video, ISP providers may take the opportunity to propose new high quality broadcast services to their clients. Because of its centralized control plane, Software Defined Networking (SDN) seems an ideal way to deploy such a service in a flexible and bandwidth-efficient way. But deploying large scale multicast services on SDN requires smart group membership management and a bandwidth reservation mechanism to support QoS guarantees that should neither waste bandwidth nor impact too severely best effort traffic. In this paper, we propose a Network Function Virtualization based solution for Software Defined ISP networks to implement scalable multicast group management. Then, we propose the Lazy Load balancing Multicast (L2BM) routing algorithm for sharing the network capacity in a friendly way between guaranteed-bandwidth multicast traffic and besteffort traffic. Our implementation of the framework made on Floodlight controllers and Open vSwitches is used to study the performance of L2BM.

NFV-Based Scalable Guaranteed-Bandwidth Multicast Service for Software Defined ISP Networks

“…Therefore, we execute 500 runs of the workload and study the bandwidth demands acceptance ratio metric as shown in Figure 7d. The x-axis shows different values (1,2,5,9,12,25, 50 and 80 Mbps) of bandwidth demands corresponding to multicast join requests whereas the y-axis shows the acceptance ratio obtained for each demand. For this workload, L2BM-0.1 accepts 2-3% more requests than DST-LU whatever bandwidth demands values of join requests.…”

“…If another path of the same length to v already exists, the algorithm updates Path[v] with the one having the lowest maximum edge utilization of the two (lines 20-23). Otherwise, node v is added in the queue Q and Path and len are updated for v (lines [24][25][26][27]. If U new is above θ (lines 29-32), node u is added in prune queue P and θ next is set to the minimum edge utilization value among all the pruned edges.…”

“…This paper is an extended version of the work published in [25] in which we originally proposed the L2BM algorithm. In particular, it includes a more complete evaluation of L2BM with a simulator, considering congested traffic scenarios to model flash-crowd and peak hours traffic in Software Defined ISP networks.…”

Resilient Multiuser Session Control in Softwarized Fog-Supported Internet of Moving Thing Systems

“…When a link in a multicast tree path associated with a group exhibits congestion, the algorithm statistically distributes packets with low priority between a set of alternative and lower quality paths. Soni et al [22] also proposed a multicast SDN-based service for multimedia traffic, whose main objective is to provide QoS (bandwidth) and scalability in the softwarized networks of Internet Service Providers. This service seeks to avoid the exponential growth of the number of messages in the IGMP protocol due to the increase in the scale of the ISP’s network, by using a virtual network function that delegates the management of the multicast groups for nodes closest to the edge of the network.…”

“…The works in [21,22] use mechanisms to monitor network dynamics, allowing them to react in the adaptation of the SDN Control Plane in a resilient way. However, none of these works (other than ReMUSiC) implements a holistic, resilient IoMT multiuser mobile session view capable of providing resilient content transport with guaranteed quality in IoMT scenarios, even in the face of network dynamics.…”