Iterative research method applied to the design and evaluation of a dynamic multicast routing scheme

摘要

Following the iterative research cycle process, this chapter elaborates a methodology and documents the steps followed for the design of a dynamic multicast routing algorithm, referred to as Greedy Compact Multicast Routing. Starting from the design of the dynamic multicast routing algorithm, we then evaluate by simulation on large-scale topologies its performance and compare them with the Abraham compact multicast routing scheme and two other reference schemes, namely the Shortest Path Tree (SPT) and the Steiner Tree (ST) algorithm. Performance evaluation and comparison include i) the stretch of the multicast routing paths also referred to as multicast distribution tree (MDT), ii) the memory space required to store the resulting routing table entries, and iii) the total communication or messaging cost, i.e., the number of messages exchanged to build the MDT. However, such performance evaluation is a necessary but not a sufficient condition to meet in order to expect deployment of multicast routing. Indeed, if one can determine that traffic exchanges are spatially and temporally concentrated, this would provide elements indicating the relevance for the introduction of such scheme in the Internet. Otherwise (if traffic exchanges are spatially and temporally diverse, i.e., highly distributed), then very few of them would benefit from a (shared) point-to-multipoint routing paths and multicast routing scheme would be less useful. For this purpose, we have conducted a multicast tree inference study. In turn, data and results obtained from these studies provides more realistic scenarios for emulation experiments against the currently deployed approach combining MBGP and PIMdeployed in IPTV or mVPN context.