Optical Access Network Based on Non-Orthogonal Multiple Access and Convolutional Neural Network

Pengcheng Deng; Rui Wang; Hui Yang; Anlin Yi

doi:10.3788/LOP202259.1306006

Laser & Optoelectronics Progress, Volume. 59, Issue 13, 1306006(2022)

Optical Access Network Based on Non-Orthogonal Multiple Access and Convolutional Neural Network

Pengcheng Deng, Rui Wang, Hui Yang^*, and Anlin Yi

Author Affiliations

School of Information Science and Technology, Southwest Jiaotong University, Chengdu 610031, Sichuan , China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(7)

Fig. 1. Long reach PON system based on PD-NOMA and CNN

Download full size

Fig. 2. Simulation block diagram for long reach NOMA-PON downstream transmission based on modified CNN receiver

Download full size

Fig. 3. Relationship between receiver sensitivity and PDR for SIC-based demodulation scheme

Download full size

Fig. 4. Receiver BER of user 1 under different PDR

Download full size

Fig. 5. Receiver BER of user 1 under different PDR

Download full size

Table 1. Training parameters of the CNN model
View table
Table 1. Training parameters of the CNN model
Parameter Value
Initial learning rate 0.001
Training dataset size 48000
Test dataset size 48000
Training batch size 800
Epoch size 300

Table 2. System fairness index of different receivers
View table
Table 2. System fairness index of different receivers
PDR FI for SIC-based method FI for CNN-based method
4 0.9869 0.9882
6 0.9959 0.9957
8 0.9998 1.0000
10 0.9904 0.9942

Tools

Get Citation

Copy Citation Text

Pengcheng Deng, Rui Wang, Hui Yang, Anlin Yi. Optical Access Network Based on Non-Orthogonal Multiple Access and Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2022, 59(13): 1306006

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites