Phoenix: Towards an Accurate, Practical and Decentralized Network Coordinate System

  • Authors:
  • Yang Chen;Xiao Wang;Xiaoxiao Song;Eng Keong Lua;Cong Shi;Xiaohan Zhao;Beixing Deng;Xing Li

  • Affiliations:
  • Tsinghua National Laboratory for Information Science and Technology,Department of Electronic Engineering, Tsinghua University, Beijing, China 100084;Tsinghua National Laboratory for Information Science and Technology,Department of Electronic Engineering, Tsinghua University, Beijing, China 100084;Tsinghua National Laboratory for Information Science and Technology,Department of Electronic Engineering, Tsinghua University, Beijing, China 100084;College of Engineering, Carnegie Mellon University, Pittsburgh, PA 15213;College of Computing, Georgia Institute of Technology, Atlanta, GA 30332;Tsinghua National Laboratory for Information Science and Technology,Department of Electronic Engineering, Tsinghua University, Beijing, China 100084;Tsinghua National Laboratory for Information Science and Technology,Department of Electronic Engineering, Tsinghua University, Beijing, China 100084;Tsinghua National Laboratory for Information Science and Technology,Department of Electronic Engineering, Tsinghua University, Beijing, China 100084

  • Venue:
  • NETWORKING '09 Proceedings of the 8th International IFIP-TC 6 Networking Conference
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Network coordinate (NC) system allows efficient Internet distance prediction with scalable measurements. Most of the NC systems are based on embedding hosts into a low dimensional Euclidean space. Unfortunately, the accuracy of predicted distances is largely hurt by the persistent occurrence of Triangle Inequality Violation (TIV) in measured Internet distances. IDES is a dot product based NC system which can tolerate the constraints of TIVs. However, it cannot guarantee the predicted distance non-negative and its prediction accuracy is close to the Euclidean distance based NC systems. In this paper, we propose Phoenix, an accurate, practical and decentralized NC system. It adopts a weighted model adjustment to achieve better prediction accuracy while it ensures the predicted distances to be positive and usable. Our extensive Internet trace based simulation shows that Phoenix can achieve higher prediction accuracy than other representative NC systems. Furthermore, Phoenix has fast convergence and robustness over measurement anomalies.