Research on influence of sampling methodologies on the metrics of identifying elephant flows by using sample and hold algorithm

Abstract

Identifying elephant flows is very important in developing effective and efficient traffic engineering schemes. In addition, obtaining the statistics of these flows is also very useful for network operation and management. In this paper, we propose and implement using sample and hold algorithm to realize elephant flows identification. Besides, we analysis the sampling mechanisms that used in sample and hold method, which include random sampling, period sampling and stratified sampling, and discuss the influence of those sampling methods on measurement accuracy of identifying elephant flows. The theoretical analysis and the simulation result indicates that under the condition of existing some tolerable measurement error about the length of flows, sample and hold algorithm can identify elephant flows accurately, which reduce the storage space and improve the processing speed efficiently. Further more the measurement accuracy of three different sampling methods is not obvious.