A recent trend in routing research is to avoid inefficiencies in network-level routing by allowing hosts to choose routes themselves using either source routing or overlay routing. Such end-to-end route selection schemes are selfish by nature, because routing decisions are no longer based on system-wide criteria, but are instead designed to optimize host-based or overlay-based metrics. A series of theoretical results showing that selfish routing can result in sub-optimal performance have cast doubts on this approach.
In this talk, I will present our study on the performance of selfish routing in Internet-like environments, focusing on intra-domain scenarios. Using realistic topologies and traffic demands, I will show that in contrast to theoretical worst cases, selfish routing achieves close to optimal average latency in such environments. However, such performance benefit comes at the expense of significantly increased congestion on certain links. Moreover, the adaptive nature of selfish overlays can significantly reduce the effectiveness of traffic engineering by making network traffic less predictable. I will conclude my talk with a brief overview of other networking research I have done, and a summary of my future research interests.