A Stochastic Analytical Modeling Framework on ISP–P2P Collaborations in Multidomain Environments

Xu Zhang, Ning Wang, Yue Cao, Linyu Peng, Haining Meng

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


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 Internet service providers (ISP) business relationships and inter-ISP routing information are not sufficiently investigated in the context of collaborative ISP–P2P paradigms in multidomain environments. In this paper, we focus on such issues and develop an analytical modeling framework for analyzing optimized interdomain 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 noncooperative behaviors 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 modeling framework can be used as a guide for analyzing and evaluating future network-aware P2P peer selection paradigms in general multidomain scenarios.

Original languageEnglish
JournalIEEE Systems Journal
Publication statusAccepted/In press - 2017 Aug 3


  • Analytical modeling
  • Analytical models
  • Business
  • Collaboration
  • Internet
  • Markov chain
  • peer selection algorithms
  • peer-to-peer (P2P) systems
  • Peer-to-peer computing
  • Routing
  • Stochastic processes

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering


Dive into the research topics of 'A Stochastic Analytical Modeling Framework on ISP–P2P Collaborations in Multidomain Environments'. Together they form a unique fingerprint.

Cite this