On Issues of Multi-path Routing in Overlay - Networks Using Optimization Algorithms

Routing policies used in the Internet can be restrictive, limiting communication between source-destination pairs to one path, when often better alternatives exist. To avoid route flapping, recovery mechanisms may be dampened, making adaptation slow. Overlays have been widely proposed to mitigate the issues of path and performance failures in the Internet by routing through an indirect-path via overlay peer(s). Choosing alternate-paths in overlay networks is a challenging issue. Guaranteeing both availability and performance guarantees on alternate paths requires aggressive active probing of all overlay paths, which limits scalability when the number of overlay-paths becomes large. If path correlations could be determined, multi-media applications can benefit greatly if their traffic could be sent over multiple uncorrelated paths. Statistical approaches have been previously proposed for establishing path correlation for multi-path routing; In this paper we test the efficacy of such approaches in Internet scale overlay networks using real-world datasets.