A fuzzy Active Queue Management mechanism for Internet congestion control

Abstract

Internet “Congestion” occurs when the aggregate demand for a resource (e.g. link bandwidth) exceeds the available capacity of the resource. Resulting effects from such congestion include long delays in data delivery, wasted resources due to lost or dropped packets, and even possible congestion collapse, in which all communication ceases in the entire network. “Congestion control” mechanism, implemented trough “queue management” algorithms, is the key factor to solve this problem keeping networks efficient and reliable from the user's viewpoint. In this paper by using a two input single output fuzzy logic controller we propose a high performance fuzzy adaptive Active Queue Management (AQM) mechanism based on Random Early Detection (RED) algorithm. Using the computer simulation, several trials were performed. All simulation results show that the proposed fuzzy AQM mechanism has better performance than traditional mechanisms.