Neural-Network-Based Channel Estimation Method for Visible Light Communication Systems

Yong Chen; Zhiqian Wu; Huanlin Liu; Chenyi Hu; Jinlan Wu; Chuangshi Wang

doi:10.3788/AOS221812

Acta Optica Sinica, Volume. 43, Issue 7, 0706004(2023)

Neural-Network-Based Channel Estimation Method for Visible Light Communication Systems

Yong Chen^1、*, Zhiqian Wu¹, Huanlin Liu², Chenyi Hu¹, Jinlan Wu¹, and Chuangshi Wang¹

¹Key Laboratory of Industrial Internet of Things & Network Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

²School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(12)

Fig. 1. Structure diagram of ACO-OFDM VLC system

Download full size

Fig. 2. Channel estimation scheme of ACO-OFDM based on DNN

Download full size

Fig. 3. Overall structure of DNN

Download full size

Fig. 4. Schematic of GC optimization process. (a) Schematic of GC optimization; (b) visualization of the effect of GC method

Download full size

Fig. 5. Optimization process of GC-RMSprop

Download full size

Fig. 6. MSE of different DNN models varying with the iterations

Download full size

Fig. 7. BER of different methods at 8 and 64 pilots. (a) 8 pilots; (b) 64 pilots

Download full size

Fig. 8. MSE of different methods at 8 and 64 pilots. (a) 8 pilots; (b) 64 pilots

Download full size

Fig. 9. BER and MSE performance of GC-DNN method under different number of pilots. (a) BER; (b) MSE

Download full size

Fig. 10. BER of different methods with or without CP

Download full size

Table 1. Parameter setting of LOS Lambertian communication model
View table
Table 1. Parameter setting of LOS Lambertian communication model
Parameter Value
Refractive index 1.5
Viewing angle /（°） 70
Half power angle /（°） 60
Photoelectric conversion efficiency 0.51
Receiving area /cm² 1
Single LED emission power /W 0.05

Table 2. Parameter setting of GC-DNN training phase
View table
Table 2. Parameter setting of GC-DNN training phase
Parameter Value
Learning rate $η$ 0.001
Fraction of gradient decay $ρ$ 0.9
Computability guard $ε$ 10^-7
Maximum number of epochs 500

Tools

Get Citation

Copy Citation Text

Yong Chen, Zhiqian Wu, Huanlin Liu, Chenyi Hu, Jinlan Wu, Chuangshi Wang. Neural-Network-Based Channel Estimation Method for Visible Light Communication Systems[J]. Acta Optica Sinica, 2023, 43(7): 0706004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites