Network Traffic Prediction Based on Multifractal MLD Model
In this paper, a multifractal approach to the classification of unknown selfaffine 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 nonlinearsystem. 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.
Li Hong Yan Tie Wang Lanlan
School of Electric Infromation Engineering Dongbei Petroleum University Daqing, China President Assistant Dongbei Petroleum University Daqing, China School of Electric Infromation Engineering Daqing Petroleum University Daqing, China
国际会议
2010国际混沌、分形理论与应用研讨会(IWCFTA 2010)
昆明
英文
466-470
2010-10-29（万方平台首次上网日期，不代表论文的发表时间）