In the peer-to-peer based video-on-demand systems, when the number of users online reaches a certain scale, It will greatly influence the bandwidth and the speed of response server when the number of online users reaches a certain scale. At the same time, there are so many video resources and sometimes the base number of users can not fully meet the number of P2P users that a lot of video resources need to be dealt with by the server, and increase the load on the server, bring the buffer phenomenon as well. To solve this problem, the article refereed to the idea “cloud computing” to design a kind of cross-platform cache server group based on Hadoop synchronization operation storage and solved the problem that store temporary files using cache server. Compared the simulation results with the traditional method of using load balancing and multiple buffer servers we found that the performance of Hadoop framework was improved significantly in feasibility and efficiency when dealing with large data. Finally the prospects of application of cloud computing in VoD/P2P were prospected.
You are here: Home / IEEE 2011 PROJECTS / Research on Cloud Computing Application in the Peer-to-Peer Based Video-on-Demand Systems