摘要
This paper proposes anew variation of systematic sampling, called Self-Adaptive Systematic Double Sampling(SSDS). This algorithm can fully consider the self-similar and heavy-tailed distribution characteristics of network traffic and estimate Hurst parameter correctly.The experiments on real Internet traces indicate,compared with traditional sampling methods,the new method advances the accuracy and practicability of the sampling measuring system obviously,and can achieve simplicity,adaptability and controllability of resource consumption.
This paper proposes a new variation of systematic sampling, called Self-Adaptive Systematic Double Sampling(SSDS). This algorithm can fully consider the self-similar and heavy-tailed distribution characteristics of network traffic and estimate Hurst parameter correctly. The experiments on real Internet traces indicate, compared with traditional sampling methods, the new method advances the accuracy and practicability of the sampling measuring system obviously, and can achieve simplicity, adaptability and controllability of resource consumption.
