Self-Organization in a Particle Swarm Optimized Fuzzy Logic Congestion Detection Mechanism for IP Networks

The fuzzy logic congestion detection (flcd) algorithm is a recent proposal for congestiondetection in ip networks which combines the good characteristics of both traditional activequeue management (aqm) algorithms and fuzzy logic based aqm algorithms. themembership functions (iiifs) of the flcd algorithm are designed using a multi-objectiveparticle swarm optimization (mopso) algorithm, in order to achieve optimal performanceon all the major performance metrics of ip congestion control. the flcd algorithm achievesbetter performance when compared to the basic fuzzy logic aqm and random explicitmarking (rem) algorithms. since the optimization process is undertaken offline and is basedon a single optimization script, the performance of the flcd algorithm may not be optimalunder different network conditions, due to the fact that the ip environment is characterizedby dynamic traffic patterns. this paper proposes two online self-learning and organizationstructures that enable the flcd algorithm to learn the system conditions and adjust thefuzzy rule base in accordance with prevailing conditions. the self-organized flcd algorithmis compared with the unorganized flcd, the basic fuzzy logic aqm and the adaptiverandom early detection (red) algorithms using simulations with dynamic traffic patterns.performance results show that the self-organized flcd algorithm is more robust than theother algorithms. compared to the unorganized flcd, the new scheme improves the udptraffic delay for short round trip times and also reduces packet loss rates. in terms of jitter,fairness and link utilization, it exhibits a similar performance to the unorganized flcd algorithm.