TY - JOUR
T1 - A Stochastic Analytical Modelling Framework on ISP-P2P Collaborations in Multi-domain Environments
AU - Zhang, Xu
AU - Wang, Ning
AU - Cao, Yue
AU - Peng, Linyu
AU - Meng, Haining
PY - 2018/9
Y1 - 2018/9
N2 - Cooperation between peer-to-peer (P2P) overlays and underlying networks has been proposed as an effective approach to improve the efficiency of both the applications and the underlying networks. However, fundamental characteristics with respect to ISP business relationships and inter-ISP routing information are not sufficiently investigated in the context of collaborative ISP-P2P paradigms in multi-domain environments. In this paper, we focus on such issues and develop an analytical modelling framework for analysing optimized inter-domain peer selection schemes concerning ISP policies, with the main purpose of mitigating cross-ISP traffic and enhancing service quality of end users. In addition, we introduce an advanced hybrid scheme for peer selections based on the proposed analytical theory framework, in accordance with practical network scenarios, wherein cooperative and non-cooperative behaviours coexisting. Numerical results show that the proposed scheme incorporating ISP policies is able to achieve desirable network efficiency as well as great service quality for P2P users. Our analytical modelling framework can be used as a guide for analysing and evaluating future network-aware P2P peer selection paradigms in general multi-domain scenarios.
AB - Cooperation between peer-to-peer (P2P) overlays and underlying networks has been proposed as an effective approach to improve the efficiency of both the applications and the underlying networks. However, fundamental characteristics with respect to ISP business relationships and inter-ISP routing information are not sufficiently investigated in the context of collaborative ISP-P2P paradigms in multi-domain environments. In this paper, we focus on such issues and develop an analytical modelling framework for analysing optimized inter-domain peer selection schemes concerning ISP policies, with the main purpose of mitigating cross-ISP traffic and enhancing service quality of end users. In addition, we introduce an advanced hybrid scheme for peer selections based on the proposed analytical theory framework, in accordance with practical network scenarios, wherein cooperative and non-cooperative behaviours coexisting. Numerical results show that the proposed scheme incorporating ISP policies is able to achieve desirable network efficiency as well as great service quality for P2P users. Our analytical modelling framework can be used as a guide for analysing and evaluating future network-aware P2P peer selection paradigms in general multi-domain scenarios.
KW - P2P systems
KW - peer selection algorithms
KW - analytical modelling
KW - Markov chain
U2 - 10.1109/JSYST.2017.2725914
DO - 10.1109/JSYST.2017.2725914
M3 - Article
VL - 12
SP - 2320
EP - 2331
JO - IEEE Systems Journal
JF - IEEE Systems Journal
SN - 1932-8184
IS - 3
ER -