Deep Learning Based End-to-End Optical Wireless Communication Systems With Autoencoders

Abstract

The utilization of neural network-based autoencoders (AEs) for the implementation of the physical layer in communication systems has recently emerged as a promising technique for achieving end-to-end optimization of communication links. However, applying conventional AE architecture to intensity modulation/direct detection optical wireless systems is challenging due to positive real-value constraint, eye safety standards, and the limited dynamic range of light sources. To address these issues, in this paper we propose a practical architecture, namely differential AE, that incorporates the concept of differential signaling. This approach allows the transmission of negative encoder output elements. In a shot-noise limited scenario, we evaluate and contrast the performance of differential AE, conventional AE, and a non-AE classical system, showcasing the superior bit-error rate achieved by the differential AE.