DocumentCode :
3539818
Title :
ISP friendly peer selection in bittorrent
Author :
Fernando, Tyrone ; Keppetiyagama, Chamath
Author_Institution :
Sch. of Comput., Univ. of Colombo, Colombo, Sri Lanka
fYear :
2013
fDate :
11-15 Dec. 2013
Firstpage :
160
Lastpage :
167
Abstract :
Peer-to-peer (P2P) applications provides services such as content sharing, video-on-demand, voice-over-IP which are very popular among Internet users and it accounts for a significant amount of global internet traffic. Use of overlay networks pose significant new challenges to Internet Service Providers (ISP). In order to reduce operational costs ISP are throttling or blocking P2P traffic which is unfavourable for a majority of internet users. In this paper, we design and evaluate an approach of reducing these costs when using BitTorrent P2P applications. Our approach involves of using knowledge of network paths that can be gathered in trackers and using it to bias the peer selection without any modification to any client software. Using the results of an evaluation of nearly 300 users in PlanetLab testbed the proposed approach will reduce cross-ISP traffic by 44% while improving in download speed (40%) and upload speed (39%).
Keywords :
Internet; cost reduction; peer-to-peer computing; BitTorrent P2P applications; ISP friendly peer selection; Internet service providers; Internet users; P2P applications; P2P traffic; PlanetLab testbed; content sharing; cross-ISP traffic reduction; download speed; network path; operational cost reduction; peer selection; peer-to-peer applications; upload speed; video-on-demand; voice-over-IP; Bandwidth; IP networks; Internet; Peer-to-peer computing; Protocols; Routing; Software; BitTorrent; Peer-to-peer; neighbour selection; performance; traffic locality;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advances in ICT for Emerging Regions (ICTer), 2013 International Conference on
Conference_Location :
Colombo
Print_ISBN :
978-1-4799-1275-9
Type :
conf
DOI :
10.1109/ICTer.2013.6761172
Filename :
6761172
Link To Document :
بازگشت