Fuzzy/neural congestion control for integrated voice and data DS-CDMA/FRMAcellular networks

The paper proposes congestion control using fuzzy/neural techniques for int egrated voice and data direct-sequence code division multiple access/frame reservation multiple access (DS-CDMA/FRMA) cellular networks. The fuzzy/neu ral congestion controller is constituted by a pipeline recurrent neural net work (PRNN) interference predictor, a fuzzy performance indicator, and a fu zzy/neural access probability controller It regulates traffic input to the integrated voice and data DS-CDMA/FRMA cellular system by determining prope r access probabilities for users so that congestion can be avoided and thro ughput can be maximized. Simulation results show that the DS-CDMA/FRMA fuzz y/neural congestion controllers perform better than conventional DS-CDMA/PR MA with channel access function in voice packet dropping ratio, corruption ratio, and utilization. In addition, the neural congestion controller outpe rforms the fuzzy congestion controller.