Hardware implementation of configurable bandwidth estimation module in high speed networks

  • Authors:

  • Yang-Keun Ahn;Young-Choong Park;Kwang-Soon Choi;Kwang-Mo Jung;Seong-Dong Kim

  • Affiliations:

  • Ubiquitous Computing Research Center, Korea Electronics Technology Institute, Yatap-Dong, Bundang-Gu, Sungnam-Si, Kyunggi-Do, Korea;Ubiquitous Computing Research Center, Korea Electronics Technology Institute, Yatap-Dong, Bundang-Gu, Sungnam-Si, Kyunggi-Do, Korea;Ubiquitous Computing Research Center, Korea Electronics Technology Institute, Yatap-Dong, Bundang-Gu, Sungnam-Si, Kyunggi-Do, Korea;Ubiquitous Computing Research Center, Korea Electronics Technology Institute, Yatap-Dong, Bundang-Gu, Sungnam-Si, Kyunggi-Do, Korea;Ubiquitous Computing Research Center, Korea Electronics Technology Institute, Yatap-Dong, Bundang-Gu, Sungnam-Si, Kyunggi-Do, Korea

  • Venue:
  • ACOS'07 Proceedings of the 6th Conference on WSEAS International Conference on Applied Computer Science - Volume 6
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

The purpose of self-sizing networks is to provide efficient utilization of network resources while ensuring appropriate Quality of Service (QoS) for each class of traffic. Bandwidth estimation, which estimates the amount of a traffic bandwidth, is useful to allocate proper bandwidth in order to meet a QoS requirement. This paper concerns an hardware implementation of a Configurable Bandwidth Estimation Module(CBEM) on a reconfigurable field-programmable gate array(FPGA) board. CBEM can be configured in one of the two forecasting based rate estimation mechanisms; Moving Average (MA) mechanism and Exponential Smoothing (ES) mechanism. We performed simulation and test to evaluate CBEM in various network conditions. The results show CBEM is practically feasible to be implemented in self-sizing high speed networks.