In this paper, we propose a method to enhance the download efficiency of BitTorrent protocol with the notion of structures in the set of pieces generated from a shared file and the swarm of peers downloading the same shared file. More specifically, as for the set of pieces, we introduce the notion of super-pieces called clusters, which is aimed to enlarge the granularity of the management of request-and-reply of pieces, and as for the swarm of peers, we organize a clique consisting of several peers with similar upload capacity, to improve the smoothness of the flow of pieces associated with a cluster. As is shown in the simulation results, the proposed extensions significantly reduce the download time of the first 75% of the downloaders, and thereby improve the performance of P2P-assisted video streaming such as Akamai NetSession and BitTorrent DNA.

In this paper, we propose an adaptive chunk scheduling for mesh-based peer-to-peer live streaming system, a hybrid class of push and pull chunk delivery approach. The proposed rule-based push-pull scheduler simultaneously pull video chunk from lower latency peers to fill up missing chunks and push video chunk adaptively for rapid chunk delivery. We performed comparative simulation study against rarest first push-pull and status-wise push-pull to prove the efficiency of our proposed algorithm. Mesh-push is made possible by effectively exploiting the information through buffer map exchange. The findings of performance evaluation have suggested a better video continuity and achieved lower source to end delay.

In this paper, we consider a problem of assigning n independent tasks onto m identical processors in such a way that the overall execution time of the tasks will be minimized. Unlike conventional task assignment problem, we assume that the execution time of each task is not fixed in advance, and merely upper and lower bounds of the execution time are given at the compile time. In the following, we first provide a theoretical analysis of several conventional scheduling policies in terms of the worst case slowdown compared with the outcome of an optimal off-line scheduling policy. It is shown that the best known algorithm in the literature achieves a worst case performance ratio of 1 + 1/f(n) where f(n) = O(n2/3) for any fixed m, which approaches to one by increasing n to the infinity. We then propose a new scheme that achieves better worst case ratio of 1 + 1/g(n) where g(n) = Θ (n/log n) for any fixed m, which approaches to one more quickly than previous schemes.