FQL-RED: an adaptive scalable schema for active queue management

摘要

In a potentially congested network, random early detection (RED) active queue management (AQM) provedneffective in improving throughput and average queuing delay. The main disadvantage of RED is its sensitivenparameters that are impossible to estimate perfectly and adjust manually because of the dynamic nature ofnthe network. For this reason, RED performs differently during different phases of a scenario and there is nonguarantee that it will have optimal performance. Giving adaptability to RED has been the subject of broadnresearch studies ever since RED was proposed. After a substantial study of AQM schemes and presentingna novel categorization for so-called modern approaches utilizing artificial intelligence tools to improvenAQM, this paper proposes an algorithm enhancing RED as an add-on patch that makes minimal changes tonthe original RED. Being built on the basis of AQM schemes like ARED and Fuzzy-RED, this algorithmninherits adaptability and is able to adjust RED inaccurate parameters regarding network traffic status, tryingnto optimize throughput and average queuing delay in a scenario. This algorithm is a Q-learning methodnenhanced with a fuzzy inference system to provide RED with self-adaptation and improved performance asna result. Given the name of FQL-RED, this algorithm outperformed RED, ARED, and Fuzzy-RED, as thenOPNET simulations show. Copyright © 2010 John Wiley & Sons, Ltd.