Implementation and Evaluation of the Blue Active Queue Management Algorithm

This work documents the implementation of the BLUE Active Queue Management algorithm for the Linux Operating System and its evaluation by measurements. The issues of Active Queue Management (AQM), and the search for the most adequate AQM algorithms are important in these days because of the changing traffic dynamics – mostly congestion – on the Internet, and the rising quality expectations held by the customers. One of the oldest and the most known AQM scheme is RED (Random Early Detection), but there are other proposed algorithms also. The BLUE algorithm is one of these, and tries to be superior in heavily congested situations by using a different approach, which decouples the queue management from the queue length. The conclusion is that while BLUE outperforms RED in scalability and low setup resource demand, but if not available, RED can be also hand-tuned to achieve similar or close results.