A Novel Clustering Tree-based Video lookup Strategy for Supporting VCR-like Operations in MANETs
Abstract: Mobile Peer-to-Peer
(MP2P) technologies can efficiently support large-scale deployment for video streaming
services over mobile ad-hoc networks (MANETs) such as video-on-demand (VoD).
Because streaming interactivity for VoD service causes frequent video lookup,
the video lookup performance of MP2P-based VoD systems is significant for
system quality of service (QoS) and user quality of experience (QoE). In this
paper, we propose a novel Clustering Tree-based Video Lookup strategy for
supporting VCR-like operations in MANETs (CTVL). CTVL builds the binary tree
composed of chunks with high popularity by investigation of playback and
switchover frequency of users for video chunks. Based on the built binary tree,
CTVL designs a construction method of node community to group nodes into
different communities in terms of cached chunks and defines the logical links
between communities, which reduces maintenance cost of community structure and
achieves high system scalability. CTVL also designs a video chunk lookup
strategy, which makes use of the logical links between communities to achieve
fast video chunk lookup. Extensive tests show how CTVL achieves much better
performance results in comparison with other state of the art solutions.
Author: Shijie Jia, Ye Guo,
Youzhong Ma, Chunlin Kuang, Guofang Kuang
Journal Code: jptkomputergg170104