Network Traffic Prediction Based on Multifractal MLD Model

Abstract

In this paper, a multifractal approach to the classification of unknown self affine signals is presented as an improvement over traditional traffic signal. The fundamental advantages of using multifractal measures include normalization and a very high compression ratio of a signature of the traffic, thereby leading to faster implementations, and the abiliiy to add new traffic classes without redesigning the traffic classifier. Mixed logical dynamical (MLD) modeling appears as an effective and realistic approach in modeling and control of hybrid systems. In this paper, the MLD framework is used for modeling of a multi-server system as a switched nonlinear system. Control of data flow in multiple servers is considered as a case study for predictive control of MLD systems. It is a good model for network traffic control and research as shown in the simulation.