As an important parameter to describe the sudden nature of network traffic, Hurst index typically conducts behaviors of both self-similarity and long-range dependence. With the evolution of network traffic over time, ...As an important parameter to describe the sudden nature of network traffic, Hurst index typically conducts behaviors of both self-similarity and long-range dependence. With the evolution of network traffic over time, more and more data are generated. Hurst index estimation value changes with it, which is strictly consistent with the asymptotic property of long-range dependence. This paper presents an approach towards dynamic asymptotic estimation for Hurst index. Based on the calculations in terms of the incremental part of time series, the algorithm enjoys a considerable reduction in computational complexity. Moreover, the local sudden nature of network traffic can be readily captured by a series of real-time Hurst index estimation values dynamically. The effectiveness and tractability of the proposed approach are demonstrated through the traffic data from OPNET simulations as well as real network, respectively.展开更多
文摘As an important parameter to describe the sudden nature of network traffic, Hurst index typically conducts behaviors of both self-similarity and long-range dependence. With the evolution of network traffic over time, more and more data are generated. Hurst index estimation value changes with it, which is strictly consistent with the asymptotic property of long-range dependence. This paper presents an approach towards dynamic asymptotic estimation for Hurst index. Based on the calculations in terms of the incremental part of time series, the algorithm enjoys a considerable reduction in computational complexity. Moreover, the local sudden nature of network traffic can be readily captured by a series of real-time Hurst index estimation values dynamically. The effectiveness and tractability of the proposed approach are demonstrated through the traffic data from OPNET simulations as well as real network, respectively.
