Improved Parallel Downloading Algorithm for Large File Distribution

Abstract

As a lot of large files such as video files are being delivered via the Internet, and copies are often stored in distributed servers in order to reduce the load on the original servers. To decrease the response time and improve the fault-tolerance of network service, we can select several mirror servers and fetch different parts of the same file from the servers in parallel. However, existing parallel downloading algorithms do not take the availability of the server into consideration in the process of selecting the mirror servers. In this paper, we propose a new parallel downloading algorithm which takes the bandwidth and availability into consideration when selecting the mirror servers. Simulation Results show that, by considering the availability of server in the server selection process, the proposed algorithm can significantly improve the efficiency of parallel downloading for large file distribution.