Measuring and modelling the group membership in the Internet.pdfVIP

Measuring and Modelling the Group Membership in the Internet 1 3 4 2 2 Jun-Hong Cui , Michalis Faloutsos , Dario Maggiorini , Mario Gerla , Khaled Boussetta Emails: jcui@, michalis@, dario@dico.unimi.it, gerla@, boukha@ 1 Computer Science Engineering Department, University of Connecticut, Storrs, CT 06029 2 Computer Science Department, University of California, Los Angeles, CA 90095 3 Computer Science Engineering, University of California, Riverside, CA 92521 4 Computer Science Department, University of Milan, via Comelico 39, I-20135, Milano, Italy ABSTRACT research can greatly benefit from realistic models and a systematic In this paper, we measure and model the distribution of multicast evaluation methodology ([7] [25] [10] [21] [8] [23] [22] [26] [30] group members. Multicast research has traditionally been plagued [14]). Despite the significant breakthroughs in modelling the traf- by a lack of real data and an absence of a systematic simulation fic and the topology of the Internet, there has been little progress methodology. Although temporal group properties have received in multicast modelling. As a result, the design and evaluation of some attention, the location of group members has not been mea- multicast protocols is based on commonly accepted but often un- sured and modelled. However, the placement of members can have proven assumptions. For example, the majority of simulation stud- significant impact on the design and evaluati