FAOM: A Novel Active Queue Management with Fuzzy Logic for TCP-Based Interactive Communications

摘要

Given the fact that the current Internet is getting more difficult in handling those interactive traffics which are rapidly increasing, new techniques are required. In this paper, a new Active Queue Management (AQM) algorithm for interactive communications that uses fuzzy logic is proposed. We analyse the relationship between the end-to-end performance and switch nodes' operation state in packet-switched networks. Based on this analysis, guidelines for performing control actions at gateways are given. A new AQM algorithm, Fuzzy Adaptive Optimized Marking (FAOM), is also introduced. We then compare FAOM with RED (Random Early Detection) by simulation using NS-2 to show that FAOM does improve the end-to-end performance for real-time interactive communications.