Research on an available bandwidth measurement model based on regression model

  • Authors:

  • Fengjun Shang

  • Affiliations:

  • College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China

  • Venue:
  • LSMS'07 Proceedings of the Life system modeling and simulation 2007 international conference on Bio-Inspired computational intelligence and applications
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Inferring the available bandwidth is of great importance for various network applications. In this paper, an available bandwidth measurement model is introduced based on regression model that can be used to high-speed IP network. The core of model has four parts as follows: 1) introducing the least absolute deviation method to compute regression coefficient. 2) deducing between delay and time interval. The advantages of the model are the lower cost and overhead, higher accurate result, independent clock synchronization. 3) deducing relation between sampling probability and background traffic. 4) introducing linear programming method to deal with the least absolute formula. The model is valid by simulation verification.