Machine learning assisted LEDs combination selection and user matching of RISs enabled GSSK-VLC system

Abstract

To improve the performance of indoor generalized space shift keying (GSSK) visible light communication (VLC) system, multiple reconfigurable intelligent surfaces (RISs) enabled user matching and light emitting diodes (LEDs) combination selection approach is proposed. Firstly, the multiple RISs enabled GSSK-VLC system model is provided, which arranges multiple RISs to realize the full coverage of the service area in an indoor space. Then, based on received power, the special user is readily matched to the corresponding RIS. Finally, machine learning enabled LEDs combination selection techniques are exploited to reduce hardware costs and improve system bit error rate (BER) performance, wherein the machine learning approaches considered include k-nearest neighbor (k-NN), support vector machine (SVM), Naive Bayes (NB), and back propagation neural network (BPNN). Among these LEDs combination selection approaches, the BPNN has the best BER performance for the highest classification accuracy. Simulation results show that the proposed joint user-RIS matching and LEDs combination selection scheme can achieve better BER performance and reduce system complexity effectively.