To reduce the atmospheric turbulence-induced power loss, an AlexNet-based convolutional neural network (CNN) for wavefront aberration compensation is experimentally investigated for free-space optical (FSO) communication systems with standard single mode fiber-pigtailed photodiodes. The wavefront aberration is statistically constructed to mimic the received light beams with the Zernike mode-based theory for the Kolmogorov turbulence. By analyzing impacts of CNN structures, quantization resolution/noise, and mode count on the power penalty, the AlexNet-based CNN with 8 bit resolution is identified for experimental study. Experimental results indicate that the average power penalty decreases to 1.8 dB from 12.4 dB in the strong turbulence.

The received signal intensity fluctuation and communication performance of an underwater optical wireless communication (UOWC) system under the air bubble effects are experimentally investigated. For different bubble density and size, lognormal, gamma, Weibull, and generalized extreme value distributions are tested to fit the fluctuation of the signal intensity at the receiving end. The best fitting distribution is found to vary with bubble parameters. The communication system performance with on–off keying and pulse position modulation is further studied.