Superchunk-Based Efficient Search in P2P-VoD System

• Published in: IEEE transactions on multimedia Vol. 13; no. 2; pp. 376 - 387
• Main Authors: Wang, Danqi, Yeo, Chai Kiat
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.04.2011; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Applied sciences; Artificial intelligence; Availability; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Content discovery; Data processing. List processing. Character string processing; Delay; Dynamical systems; Dynamics; Exact sciences and technology; Indexes; Memory organisation. Data processing; Motion pictures; Multimedia; Networks; Pattern recognition. Digital image processing. Computational geometry; Peer to peer computing; peer-to-peer; Peers; Searching; Simulation; Software; Streaming media; Trees; Video on demand; Availability; Backbone; Peer to peer; Video on demand; Logarithmic function; Cache memory; Tapping; Video signal; Search time; Data transmission; Information retrieval; AVL tree; Distributed system; Real time; peer-to-peer; Gossiping(all to all); Knowledge discovery; video-on-demand; Movies; Jumping; Information exchange; Content discovery; Content analysis
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2011.2106485

In this paper, we seek to provide reliable and fast content discovery in peer-to-peer (P2P) video-on-demand (VoD) system to enable user interactivity under peer dynamics. We first identify two characteristics of content discovery in P2P-VoD: real-time constraints and limited local cache. Tapping on these properties, we propose a hybrid content discovery mechanism: SUpeRchunk- based eFficient search Network (SURFNet). SURFNet divides movies into superchunks and chunks. Stable peers that are likely to have longer lifespans in the system are used to construct an AVL tree to provide superchunk-level data availability information. Peers storing the same superchunk are grouped into a holder-chain, which is then attached to a node in the AVL tree. This structured overlay is further extended by a gossip-based unstructured network for chunk-level information exchange and data transmission. Since the AVL tree consists of only stable peers, it provides a reliable backbone even in highly dynamic environment. Our analysis and simulation results show that SURFNet supports nearly-constant and logarithmic search time for seeking within a video and jumping to a different video, respectively.