Title :
Fuzzy/neural congestion control for integrated voice and data DS-CDMA/FRMA cellular networks
Author :
Chang, Chung-Ju ; Chen, Bo-Wei ; Liu, Terng-Yuan ; Ren, Fang-Ching
Author_Institution :
Dept. of Commun. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
The paper proposes congestion control using fuzzy/neural techniques for integrated voice and data direct-sequence code division multiple access/frame reservation multiple access (DS-CDMA/FRMA) cellular networks. The fuzzy/neural congestion controller is constituted by a pipeline recurrent neural network (PRNN) interference predictor, a fuzzy performance indicator, and a fuzzy/neural access probability controller. It regulates the traffic input to the integrated voice and data DS-CDMA/FRMA cellular system by determining proper access probabilities for users so that congestion can be avoided and the throughput can be maximized. Simulation results show that the DS-CDMA/FRMA fuzzy/neural congestion controllers perform better than conventional DS-CDMA/PRMA with channel access function in terms of voice packet dropping ratio, corruption ratio, and utilization. In addition, the neural congestion controller outperforms the fuzzy congestion controller.
Keywords :
access protocols; cellular radio; code division multiple access; fuzzy neural nets; integrated voice/data communication; multiuser channels; packet radio networks; pipeline processing; probability; radio networks; radiofrequency interference; recurrent neural nets; spread spectrum communication; telecommunication computing; telecommunication congestion control; telecommunication traffic; DS-CDMA/FRMA cellular networks; PRNN interference predictor; access probabilities; channel access function; corruption ratio; direct-sequence code division multiple access; frame reservation multiple access; fuzzy congestion controller; fuzzy performance indicator; fuzzy/neural access probability controller; fuzzy/neural congestion control; fuzzy/neural congestion controller; integrated voice; integrated voice/data network; neural congestion controller; pipeline recurrent neural network; protocol; simulation results; throughput maximization; traffic input regulation; utilization; voice packet dropping ratio; Communication system traffic control; Fuzzy control; Fuzzy neural networks; Interference; Land mobile radio cellular systems; Multiaccess communication; Pipeline processing; Recurrent neural networks; Throughput; Traffic control;
Journal_Title :
Selected Areas in Communications, IEEE Journal on
