An analytical design of GAPIDNN algorithm for AQM

Author

Ping Hou

Author_Institution

Sch. of Manage., Nanjing Univ. of Posts & Telecommun., Nanjing, China

fYear

2013

fDate

20-22 Dec. 2013

Firstpage

83

Lastpage

86

Abstract

A PID Neural Network algotithm with genetic algorithm, called GAPIDNN, is designed and applied in active queue management (AQM). The genetic algorithm is used to turn the PID Neural Network weight. NS simulation results show that the GAPIDNN algorithm has better control performance than PIDNN. GAPIDNN algorithm shows higher robustness and link utilization under changing network enviroment and large delay.

Keywords

control system synthesis; delays; genetic algorithms; neurocontrollers; queueing theory; stability; telecommunication congestion control; telecommunication network management; three-term control; AQM; GAPIDNN algorithm design; PID neural network algorithm; PID neural network weight; PIDNN controller; active queue management; control performance; genetic algorithm; network congestion control; network delay; robustness; Algorithm design and analysis; Biological neural networks; Educational institutions; Genetic algorithms; Neurons; Robustness; AQM; PID Neural Network; genetic algorithm; network congestion control;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronic Sciences, Electric Engineering and Computer (MEC), Proceedings 2013 International Conference on

Conference_Location

Shengyang

Print_ISBN

978-1-4799-2564-3

Type

conf

DOI

10.1109/MEC.2013.6885053

Filename

6885053