A Novel Clustering Tree-based Video lookup Strategy for Supporting VCR-like Operations in MANETs

Abstract

Mobile Peer-to-Peer (MP2P) network is a promising avenue for large-scale deployment of Video-on-Demand (VoD) applications over mobile ad-hoc networks (MANETs). In P2P VoD systems, fast search for resources is key determinants for improving the Quality of Service (QoS) due to the low delay of seeking resources caused by streaming interactivity. In this paper, we propose a novel Clustering Tree-based Video Lookup strategy for supporting VCR-like operations in MANETs (CTVL) CTVL selects the chunks with the high popularity as "overlay router" chunks to build the "virtual connection" with other chunks in terms of the popularities and external connection of video chunks. CTVL designs a new clustering strategy to group nodes in P2P networks and a maintenance mechanism of cluster structure, which achieves the high system scalability and fast resource search performance. Thorough simulation results also show how CTVL achieves higher average lookup success rate, lower maintenance cost, lower average end-to-end delay and lower packet loss ratio (PLR) in comparison with other state of the art solutions.