A novel wavelet-based approach to enhance the performance of mobile-business systems

We propose a novel wavelet-based approach (WBA) that accurately decides if the Internet traffic is currently SRD (short-range dependence) or LRD (long-range dependence) on the fly. As a result, it helps a real-time dynamic cache size tuner such as the MACSC (Model for Adaptive Cache Size Control) maintain the given cache hit ratio under all Internet traffic conditions. The WBA mechanism utilizes the following unique characteristics of wavelet coefficients (WC) for stationary signals f(x): i) WC values by discrete wavelet transform (DWT), irrespective to if f(x) is SRD or LRD, are always SRD; ii) if f(x) is LRD then the WC variances scale divergently with the dilation factor; and iii) WC variances of SRD signals, however, converge to a constant. The DWT process is D_j,k = 〈f(x), ω_j,k〉,w or 2^-j/2 ∫_-∞^+∞ f(x)ω(2^-j x - k)dx formally, where D_j,k are the WC values, ω_j,k the mother wavelet, j the dilation factor/scale, and k the translation factor.