An Analysis of Machine Learning Applications in Visible Light Communication Systems

Abstract

With the growing use of high-bandwidth applications, visible light communication (VLC) has surfaced as a promising method for high-speed data transmission due to its dual capability of providing illumination and data transfer. However, VLC faces significant challenges due to various nonlinear distortions that affect signal processing and reduce system efficiency. Machine learning (ML) techniques offer a valuable approach to mitigating these negative effects of transceiver nonlinearity. ML can be applied to numerous VLC issues, such as channel estimation, jitter compensation, position tracking, modulation detection, phase estimation, and security. This study presents an in-depth review of various ML algorithms aimed at simplifying the design of indoor VLC systems and enhancing their performance. Additionally, it explores different ML applications, associated challenges, and potential future research directions in the context of VLC.