Multicast solutions for streaming applications

Abstract

I propose an application layer multicast framework, Scalable Overlay Multicast (SOM), which is tailored to large-scale, limited-bandwidth streaming applications. The mechanism exploits AS (Autonomous System) information extracted from BGP (Border Gateway Protocol) routing table snapshots. A centralized server immediately identifies clusters on a basis of AS and build a inter-cluster data distribution tree. Within a cluster, a delivery tree is made in a distributed way based on round-trip-time estimates. By a hybrid tree building mechanism, stable data delivery paths on overlay networks can be determined quickly and efficiently. By simulation, our framework shows very quick convergence characteristics and efficient network usage. Besides, a novel multicast routing protocol is proposed for one-to-many communication in ad hoc networks. ACMRP(Adaptive Core Multicast Routing Protocol) is on demand core-based multicast routing protocol that is based on a multicast mesh. In ACMRP, a core is not well-known and it adapts to the current network topology and group membership. The enhanced adaptivity minimizes the core dependency and, accordingly, improves performance and robustness of ACMRP. A multicast mesh is created and maintained by the periodic flooding of the adaptive core. Since the flooding traffic is evenly maintained and a mesh provides rich connectivity among group members, ACMRP can achieve efficiency, scalability, and effectiveness. I evaluate scalability and performance of ACMRP via simulation.