DocumentCode
2351664
Title
Analysis of the BitTorrent Protocol Modified with Multicast
Author
Costa-Montenegro, Enrique ; López-Bravo, Cristina ; Rodríguez-Hernández, Pedro S. ; Barragáns-Martínez, Ana Belén
Author_Institution
Dept. de Enxenaria Telematica, Univ. de Vigo, Vigo, Spain
fYear
2012
fDate
12-14 Nov. 2012
Firstpage
132
Lastpage
139
Abstract
Peer to Peer (P2P) computer networks rely on direct connections between participants instead of conventional centralized resources. These networks are useful for many purposes, but the killer application nowadays is file sharing. BitTorrent is a very popular protocol for this matter. In this paper, we use a multi-agent model of a BitTorrent network. In it, each BitTorrent client is an agent that interacts with other agents and reacts autonomously, following the same decision algorithms as a real client. Their goals are downloading contents in the shortest possible time and sharing them with other agents. The use of this multi-agent model allows us to introduce modifications to the protocol. We have modified this model to use multicast. A multicast transmission consists in sending information in a network to multiple destinations simultaneously, using a more efficient strategy: to send the message on each link of the network only once and to create copies when the links to the destinations are divided. We have evaluated how BitTorrent performs using multicast and compared to its normal behavior.
Keywords
multi-agent systems; multicast communication; peer-to-peer computing; protocols; BitTorrent client; BitTorrent protocol analysis; P2P computer networks; decision algorithms; multiagent model; multicast transmission; peer-to-peer computer networks; Bandwidth; IP networks; Multiagent systems; Peer to peer computing; Protocols; Receivers; Unicast; Analysis; BitTorrent; Multicast; P2P;
fLanguage
English
Publisher
ieee
Conference_Titel
P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC), 2012 Seventh International Conference on
Conference_Location
Victoria, BC
Print_ISBN
978-1-4673-2991-0
Type
conf
DOI
10.1109/3PGCIC.2012.11
Filename
6362960
Link To Document