Collaboratively Scheduling to Decrease Inter-AS Traffic in P2P Live Streaming

In the existing data fetching algorithms for P2P streaming systems, the peers usually fetch data independently, leading to huge inter-AS traffic (AS: autonomous system). This paper proposes CoFetch, a collaborative fetching algorithm for P2P live streaming systems to decrease inter-AS traffic. In CoFetch, to avoid that all peers fetch the same data from inter-AS connection, instead of aggressively fetching data depending on the peers´ own desires, the peers divide requests into multiple steps. In each step, peers mainly and locally share data fetched in previous steps by other collaborating peers and request subset data from inter-AS connections. The analytical results show that, inter-AS traffic in CoFetch is independent of the number of peers in AS but the number of collaborating peers in AS. Furthermore, in each overlay, when we limit the number of collaborating peers in one AS from 5 to 20, the inter-AS traffic is about 1.7-3 times of the streaming rate, regardless of the number of peers.