|
Published Articles >> Table of Contents >> Abstract
12th Asian Test Symposium (ATS'03)
p. 340
Measurement-Based Modeling with Adaptive Sampling
Junfeng Wang, University of Electric Science and Technology of China
Jianhua Yang, Chinese Academy of Sciences
Gaogang Xie, Chinese Academy of Sciences
Mingtian Zhou, University of Electric Science and Technology of China
Zhongcheng Li, Chinese Academy of Sciences
Full Article Text:
  
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ATS.2003.1250834
Send link to a friend
| Abstract |
|
To develop an accurate parametric model for network character is much difficult. We propose an Fitting-based Adaptive Sampling Methodology (FASM) trying to model some network metrics non-parametrically. The contributions of the paper are twofold: (1) Adopting Piecewise Linear Function Approximation scheme to provide more accurate approximation of the true metric model. (2) The statistical metric derived from the non-parametric model provides much more stable, lower variance and accurate estimation than other popular methodologies under the same sampling size. Experiments based on two measurement traces show that FASM
dramatically reduces the number of samples while retaining the same approximating residual error than others.
|
 Additional Information
|
Citation:
Junfeng Wang, Jianhua Yang, Gaogang Xie, Mingtian Zhou, Zhongcheng Li,
"Measurement-Based Modeling with Adaptive Sampling,"
ats,
p. 340,
12th Asian Test Symposium (ATS'03),
2003
|
|
