Title :
Analysing traffic flows through sampling: A comparative study
Author :
Jo?o Marco C. Silva;Paulo Carvalho;Solange Rito Lima
Author_Institution :
Centro Algoritmi, Universidade do Minho, Braga, Portugal
fDate :
7/1/2015 12:00:00 AM
Abstract :
Understanding network workload through the characterization of network flows, being essential for assisting network management tasks, can benefit largely from traffic sampling as long as an accurate snapshot of network behavior is captured. This paper is devoted to evaluate the real applicability of using sampling to support flow analysis. Considering both classical and emerging sampling techniques, a comparative performance study is carried out to assess the accuracy of estimating flow parameters through sampling. After identifying the main building blocks of sampled-based measurements, a sampling framework has been implemented to provide a versatile and fair platform for carrying out the testing and comparison process. Through an encompassing coverage of representative sampling techniques, the present study aims to provide useful insights regarding the use of sampling in traffic flow analysis.
Keywords :
"Systematics","Estimation","Kernel","Computer architecture","Adaptive systems","Taxonomy","Computers"
Conference_Titel :
Computers and Communication (ISCC), 2015 IEEE Symposium on
DOI :
10.1109/ISCC.2015.7405538