Social network behaviour inferred from O-D Pair traffic

Social network behaviour inferred from O-D Pair traffic

Because traffic is predominantly formed by communication between users or between users and servers which communicate with users, network traffic inherently exhibits social networking behaviour; the extent of interaction between entities – as identified by their IP addresses – can be extracted from the data and analysed in a multiplicity of ways. In this paper, Anonymized Internet Trace Datasets obtained from the Center for Applied Internet Data Analysis (CAIDA) have been used to identify and estimate characteristics of the underlying social network from the overall traffic. The analysis methods used here fall into two groups, the first being based on frequency analysis and second method being based on the use of traffic matrices, with the latter analysis method being further sub-divided into groups based on the traffic mean, variance and co-variance. The frequency analysis of origin, destination and O-D Pair statistics exhibit heavy tailed behaviour. Because the large number of IP addresses contained in the CAIDA Datasets, only the most predominate IP Addresses are used when estimating all three sub-divided groups of traffic matrices. Principal Component Analysis and related methods are applied to identify key features of each type of traffic matrix. A new system called Antraff has been developed by the authors to carry out all the analysis procedures.