Research on the scheme of a CNN-based differential modulation and detection in optical wireless communication with...

The integration of modulation techniques with machine learning in optical wireless communication (OWC) provides a solution for optical wireless access networks (OWANs) that require high-speed and high-reliability wireless connections. An environment-aware differential modulation and detection (DMD) scheme based on a convolutional neural network (CNN) in optical wireless communication systems is proposed in this paper. The scheme adopts a differential modulation and detection method that can mitigate the BER floor limitation of on-off keying (OOK) modulation in atmospheric turbulence channels. In addition, the machine learning approach is proposed for optimization, which notably obviates the need for intricate channel state estimation. In a deep neural network, the detector can extract amplitude features from multi-received signals. Furthermore, an experimental platform is set up for sampling the fluctuation of light intensity. Based on the experiments, the results demonstrate that the scheme exhibits significant performance advantages and effectively improves the system performance of the traditional DMD method in the low SNR region. Performance of the CNN-based method is also in-depth analyzed and compared with other methods of modulation and detection under varying scintillation indices. The insights and investigations provide the probability for the practical application of machine learning in differential OWC system design.