A Practical Congestion Control Scheme for Named Data Networking

Abstract

Traditional congestion control mechanisms are designed for end-toend connections and do not fit the Named Data Networking (NDN) architecture, in which content can be retrieved from multiple sources and through multiple paths. To fully exploit the NDN architecture, a congestion control scheme must consider the effects of in-network caching, multipath forwarding, and multicast data delivery. Moreover, the solution must not assume known link bandwidths or Data packet sizes, as these assumptions may not hold for overlay links, wireless links, or applications with varying Data packet sizes. In this paper we propose PCON: a practical congestion control scheme to address the above issues. PCON detects congestion based on the CoDel AQM (by measuring packet queuing time), then signals it towards consumers by explicitly marking certain packets, so that downstream routers can divert traffic to alternative paths and consumers can reduce their Interest sending rates. Our simulations show that PCON's forwarding adaptation reaches a higher total throughput than existing work while maintaining similar RTT fairness. Moreover, PCON can adapt to the changing capacity of IP tunnels and wireless links, conditions that other hop-by-hop schemes do not consider.

PFECC: a precise feedback-based explicit congestion control algorithm in named data networking

“…It uses the AIMD window adjustment mechanism at the receiver. PCON [12] detects link congestion by the sojourn time of Data packet in the queue, and explicitly feeds back to the receiver. The receiver controls the sending rate of its Interest packets by using the AIMD-like algorithm, but there is an unnecessary rate drop at the intermediate node.…”

LQCC: A Link Quality-based Congestion Control Scheme in Named Data Networks

“…Implicit-Feedback Congestion Control Solutions: Schneider et al [15] propose a practical congestion control scheme. This scheme measures packet queuing time to detect congestion, then marks certain packets to signal them to the consumer.…”

An Analysis of NDN Congestion Control Challenges

“…The algorithm that selects suitable paths is named Forwarding Strategy (FS). Many forwarding strategies have been defined and, in this study, we use and compare the Best Route strategy (BR) [6], Dynamic Request Forwarding strategy (DRF) [7], the Fast Pipeline Filling strategy (FPF) [3] and the Practical Congestion cONtrol strategy (PCON) [4]. FPF and PCON are particular forwarding strategies that propose to solve the congestion problem.…”

“…Finally, the third kind of solutions is a hybrid approach that combine the previous solutions. In [4], PCON is designed: the end-to-end part is based on a congestion window at the consumer side whereas the hop-by-hop part is a forwarding strategy on each NDN nodes. We respectively name them PCON-CS and PCON-FS in this paper.…”

“…Therefore the community have propose several solutions that fall into three types: end-to-end solutions that follow the footsteps of TCP, hop-by-hop ones that act as Internet loadbalancer or queue manager (AQM), and some hybrid solutions that combine both approaches. In this paper, we propose to assess and to analyze one representative solution of each type: Interest Control Protocol (ICP) [2] for the end-to-end approach, Fast Pipeline Filling (FPF) [3] for the hop-by-hop approach and Practical Congestion cONtrol scheme (PCON) [4] for the hybrid approach.…”