Premium
Swarm intelligence based robust active queue management design for congestion control in TCP network
Author(s) -
Ali Hazem I.,
Khalid Karam Samir
Publication year - 2016
Publication title -
ieej transactions on electrical and electronic engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 30
eISSN - 1931-4981
pISSN - 1931-4973
DOI - 10.1002/tee.22220
Subject(s) - active queue management , pid controller , robustness (evolution) , particle swarm optimization , control theory (sociology) , computer science , network congestion , network packet , ant colony optimization algorithms , control engineering , robust control , quality of service , queue , engineering , control system , control (management) , computer network , algorithm , temperature control , biochemistry , chemistry , electrical engineering , artificial intelligence , gene
Active queue management (AQM) is an effective solution for the congestion control problem. It can achieve high quality of service (QoS) by reducing the packet dropping probability and network utilization. Three robust control algorithms are proposed in this paper in order to design robust AQM schemes: conventionalH ∞controller, robust particle swarm optimization (PSO)‐based PID (proportional–integral–derivative) (PSOPID) controller, and robust ant‐colony optimization (ACO)‐based PID (ACOPID) controller. PSO and ACO methods are used to tune the PID controller parameters subject toH ∞constraints to achieve the required robustness of the network. Robust PSOPID and ACOPID controllers can achieve desirable time‐response specifications with a simple design procedure and low‐order controller in comparison to the conventionalH ∞controller. Wide ranges of system parameters change are used to show the robustness of the designed controllers. The ability of the designed controllers to meet the specified performance is demonstrated using MATLAB 7. 11, (R2010b): The MathWorks, Inc.3 Apple Hill Drive Natick, MA USA. On the other hand, to verify the effectiveness of the designed controller, nonlinear simulation is performed using the NS2 package. Finally, it is shown by comparison that the proposed robust ACOPID can achieve more desirable performance than the PSOPID controller and the controllers that have been proposed in previous works. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.