Path associativity centralized explicit congestion control (PACEC) for SDN

Abstract

This paper proposes a new algorithm called Path Associativity Centralized Explicit Congestion Control (PACEC). PACEC works on a Software Defined Networking (SDN) framework. In PACEC, a congestion control decision is based on global information network conditions. PACEC uses global information network to identify network resources along the path from the source to the destination and provides this information to end systems. This solution allows more efficient network capacity because the decision is based on real-time information about the path network states. Based on the information, PACEC gives the controller to view the available path capacity and make congestion control decisions. In this paper, we describe and discuss the results of the PACEC evaluation using emulator mininet with Ryu controller. The results show that PACEC has the ability to provide necessary information for the traffic source and makes the right congestion control decisions and to avoid full queue problem. This shows that PACEC has the possibility to provide better performance than other explicit congestion control protocols.