A Novel OFDM Format and a Machine Learning Based Dimming Control for LiFi

This paper proposes a new hybrid orthogonal frequency division multiplexing (OFDM) form termed as DC-biased pulse amplitude modulated optical OFDM (DPO-OFDM) by combining the ideas of existing (DCO-OFDM) and discrete multitone (PAM-DMT). The analysis indicates that required DC-bias for DPO-OFDM-based light fidelity (LiFi) depends on dimming level components DPO-OFDM. bit error rate (BER) performance flexibility DPO-OFDM schemes are evaluated using MATLAB tools. results show proposed is power efficient has wide range. Furthermore, switching algorithm introduced LiFi, where individual switched according to target level. Next, machine learning algorithms used first time find appropriate proportions components. It shown polynomial regression degree 4 can reliably predict constellation size DCO-OFDM component given PAM-DMT. With algorithms, LiFi at