Adaptive neuro-fuzzy controller trained by genetic-particle swarm for active queue management in internet congestion

Routers are vital during network congestion. All routers have input and output packet buffers. V<span lang="EN-US">Various congestion control strategies been suggested. Some controller-based proportional-integral derivative (PIDs) recently offered as active queue management (AQM) solutions to alleviate the deterioration of transmission protocol (TCP) system performance. However, time delay is large, data retention decreases, oscillation occurs, suggesting that present PID-controller unable fulfill quality service (QoS) criteria. research developed on new technologies such neural networks fuzzy logic. This paper proposes adaptive neuro-fuzzy inference (ANFIS) like PID controller for AQM. model employs genetic algorithms (GAs) particle swarm optimization (PSO) learn optimize all variables ANFIS controller. Simulations were used investigate effects using based single sign-on (SSO), (ANFIS PI, with GA-PSO) controllers length an AQM router, respectively. Then we compared findings see which approach should be utilized manage routers. In simulations, has superior stability, convergence, resilience, loss ratio, goodput, lowest rising time, overshoot, settling time.</span>