Generation of teletraffic of generalized Cauchy type

Generation of long-range-dependent (LRD) traffic is crucial for networking, e.g. simulating the Internet. In this respect, it is necessary to generate an LRD traffic series according to a given correlation structure that may well reflect the statistics of real traffic. Recent research on traffic modeling exhibits that the LRD traffic is well modeled by the generalized Cauchy (GC) process indexed by two parameters that separately characterize the self-similarity (SS), which is a local property described by the fractal dimension D, and long-range dependence (LRD), which is a global property measured by the Hurst parameter H. This paper gives a computational method to generate the LRD traffic based on the correlation form of the GC process in both the unifractal and multifractal cases. It may nevertheless be used as a way to flexibly simulate the realizations that reflect the fractal phenomena of traffic for both short-term lags and long-term ones.