An Improved Hop-by-hop Interest Shaper for Congestion Control in Named Data Networking

摘要

Hop-by-hop interest shaping has been proposed as a viable congestion control mechanism in Named Data Networking (NDN). Interest shaping exploits the strict receiver-driven traffic pattern and the symmetric bidirectional forwarding in NDN to control the returning data rate. In this paper, we point out that both interests and contents contribute to congestion and their interdependence must be considered in any interest shaping algorithm. We first analyze this issue mathematically by formulating it as an optimization problem to obtain the optimal shaping rate. Then a practical interest shaping algorithm is proposed to achieve high link utilization without congestive data loss. We further note that flow differentiation in NDN is complicated and design our scheme independently of traffic flows. We demonstrate our hop-by-hop interest shaper in conjunction with simple Additive-Increase-Multiplicative-Decrease (AIMD) clients using the ns3-based NDN simulator (ndnSIM). Our results show that the proposed shaping algorithm can effectively control congestion and achieve near-optimal throughput.