A Game Theoretic Framework for Congestion Control in Named Data Networking

Abstract

As an essential building block of the Named Data Networking (NDN) architecture, congestion mechanism has been the focus of much attention. The unique features of NDN architecture bring forward distinct requirements for congestion control from its Internet Protocol (IP) counterpart. In this paper, we present a game theoretic framework for flow rate control in NDN based on the concept of Nash bargaining solution from cooperative game theory, and propose a distributed, flow-aware and hop-by-hop congestion control mechanism on a solid analytical basis. In addition, we developed a possible implementation in ndnSIM and performed various experiments with different settings to study the behavior of our scheme. We have seen that the proposed congestion control mechanism performs as designed, and significantly enhances the network performance.

DOI: http://dx.doi.org/10.5755/j01.itc.46.4.15680