演講題目：Mining Network Traffic Data
主講人：Professor Ljiljana Trajkovic
時間：105年7月6日(星期三10：00 - 12：00)
地點：商1F01
Abstract:
Understanding modern communication networks involves collection and analysis of data collected from deployed networks. Data mining and statistical analysis of network data are often employed to determine traffic loads, analyze patterns of users' behavior, and predict future network traffic. Collected traffic data are also used to characterize and model network traffic, analyze Internet topologies, and predict network anomalies.
In this talk, we analyze traffic data collected from four deployed networks: the Vancouver Lower Mainland Gigabit Ethernet network (BCNET), a cellular wireless network used by public safety agencies (E-Comm), a satellite network used by Internet service providers (ChinaSat), and the Internet. We first describe the BCNET traffic measurement site and equipment. We then analyze network log data collected from E-Comm, a public safety trunked radio network that utilizes circuit-switched cellular wireless technology. We examine statistical distributions and autocorrelation functions of call inter-arrival and call holding times during busy hours. Our findings indicate that traditional Erlang models used for voice traffic are not suitable for evaluating the performance of trunked radio networks. We also describe collection of traffic data, characterization of traffic loads, and distribution of packet sizes in ChinaSat, a hybrid satellite-terrestrial system. We investigate long-range dependence as the traffic patterns vary, propose a traffic model for the TCP connections, and use data from billing records to predict future traffic loads. Finally, we examine Internet datasets from the Route Views and RIPE projects and illustrate historical trends in the development of the Internet. The Internet traffic data are also used to classify and detect network anomalies by employing various machine learning techniques.
