DocumentCode :
3246441
Title :
Hierarchical and Breathing Peer-to-Peer SIP System
Author :
Lifeng Le ; Geng-Sheng Kuo
Author_Institution :
Beijing Univ. of Posts & Telecommun., Beijing
fYear :
2007
fDate :
24-28 June 2007
Firstpage :
1887
Lastpage :
1892
Abstract :
The combination of the SIP-based service and peer-to-peer (P2P) can improve the performance of traditional client-server SIP system. However, current P2P SIP systems have many disadvantages. For example, node heterogeneity (e.g., bandwidth, CPU, storage and uptime) has not been considered enough which affects the scalability and service availability of P2P overlay; session setup latency is higher than that of traditional SIP system; and high cost is paid to maintain DHT overlays during a long idle uptime. In order to overcome these disadvantages, this paper proposes a novel hierarchical and breathing P2P SIP system. Its hierarchical overlay is composed of more than two suboverlays with different physical capability and system availability. Based on the hierarchical overlay, we propose a Node Virtualization Model that enables a node to share physical capability of powerful nodes in higher-level suboverlays. Suboverlays adopt breathing overlay model that enables a node to quit P2P overlay temporarily after a long idle uptime and rejoin P2P overlay when new SIP services are initiated on it. Based on the performance analysis and simulation results, our proposed system achieves better scalability and resource availability as well as shorter session setup latency, less bandwidth for DHT maintenance traffic and larger storage capacity than current P2P SIP systems.
Keywords :
client-server systems; peer-to-peer computing; resource allocation; signalling protocols; telecommunication traffic; DHT overlays; SIP-based service; breathing peer-to-peer SIP system; client-server SIP system; maintenance traffic; node virtualization model; resource availability; session setup latency; Analytical models; Availability; Bandwidth; Costs; Delay; Peer to peer computing; Performance analysis; Power system modeling; Scalability; Traffic control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications, 2007. ICC '07. IEEE International Conference on
Conference_Location :
Glasgow
Print_ISBN :
1-4244-0353-7
Type :
conf
DOI :
10.1109/ICC.2007.314
Filename :
4288985
Link To Document :
بازگشت