Fuzzy logic controller of Random Early Detection based on average queue length and packet loss rate

The utilisation of fuzzy logic (FL) has shown to be useful in designing new active queue management (AQM) methods that can be used to alleviate congestions in wired and wireless networks. In this paper, we propose a FL controller technique based on the traditional random early detection (RED) algorithm to discover the congested router buffer as soon as the congestion occurs in the network. The proposed technique relies on the average queue length and the packet loss rate as input linguistic variables and produces a single output linguistic variable, i.e. the packet dropping probability. We compare the proposed method with the classic RED algorithm in terms of different performance metrics, including packets dropping probability, average queue length, throughput, average queueing delay, and packet loss rate. The simulation results obtained from this comparison revealed that our FL method outperforms RED with reference to average queue length, throughput, packet loss rate and packet dropping probability function. In addition, our method provides average queueing delay results similar to that of RED. Finally, the performance measures results of the proposed method is not impacted with the traffic load states (high or low), whereas, REDpsilas results get impacted when the traffic load becomes high.