Popularity-based Congestion Control in Named Data Networking

Named Data Networking (NDN) has some transport characteristics different from those of TCP/IP because it is pull-based, in-path caching, hop-by-hop, and multi-path. For these reasons, it is necessary to adapt a distinguished congestion control mechanism to the NDN environment. Congestion control algorithms based on traditional RTT measurements will not work correctly since the data source may change due to in-network caching during communication flow. In this paper, we propose a novel approach for developing a congestion control scheme in NDN by predicting content popularity. Performance evaluation demonstrates the effectiveness of the proposed congestion control scheme using the ns3-based NDN simulator (ndnSIM).