Instead of conventional knowledge-driven modeling, this study introduced data-driven channel modeling methods based on deep learning (DL) in a free-space optical (FSO) communication system to achieve low complexity, less modeling difficulty, high fidelity, and differentiability. The FSO channel was modeled via three DL algorithms: generative adversarial network (GAN), bidirectional long short-term memory (BiLSTM), and Bayesian neural network (BNN). Consequently, their performance was comprehensively compared in terms of optical amplitude waveforms, Kullback-Leibler (KL) divergence, 95% confidence interval, data distribution, and fitted probability density functions. The results indicated that the GAN-based channel exhibited optimal performance, implying its suitability for learning the stochastic distribution of the FSO channel. In addition, the performance of GAN-based channels was examined under different conditions: turbulence intensities (weak, moderate, and strong), transmission distances (3, 4, and 5 km), launch powers (0, 10, and 20 dBm), modulation formats (on-off keying, pulse position modulation, and pulse amplitude modulation 4), and the adaptability to channel variation. The test results were satisfactory and confirmed the ability of the GAN to learn the approximate distribution function of the FSO channel. Thus, the primary aim was to prove that for FSO channels with statistical distribution characteristics, a data-driven DL model can not only serve as an effective surrogate model for specific scenarios but also provide a potential tool for future modeling methods.

Low Earth orbit (LEO) satellite communication (SATCOM) is a pivotal component of sixth-generation (6G) wireless communication. The dependability of satellite-to-ground communication is severely hampered by large-scale Doppler frequency offsets. We propose a carrier frequency offset (CFO) estimator applied to orthogonal time frequency space (OTFS) modulation. By inserting the pilot and maximum length sequences (MLS) for each OTFS frame in the delay-Doppler domain, the estimator can search for the corresponding equal-amplitude sequences and MLS along different dimensions in the delay-time domain. The fractional CFO, obtained by weighting the signal phase determined by the received sample’s correlation function, is the best linear unbiased estimate. The proposed estimator well enhances the estimation range by employing a correlation technique with MLS to estimate the large-scale CFO. Finally, we conduct numerous simulations on the time-varying channel. The results demonstrate a minimum of 53% reduction in frequency estimation error and a minimum 32-fold increase in estimation range compared with existing algorithms.

To further improve the transmission efficiency and link stability for free space optical (FSO)-based satellite communication (SatCom) systems when transmitting large-scale remote sensing images, a scheme based on the integration of FSO and semantic communication (FSO-SC) is proposed, which employs a vector quantized variational autoencoder with spatial normalization to extract essential semantic features of images while preserving intricate details. Additionally, the Máalaga distribution model is utilized to simulate FSO channels with diverse turbulence conditions. Moreover, a comparative evaluation between the FSO-SC and traditional systems is conducted through 28 GBaud satellite-ground simulation with three modulation formats considering various effects. Compared to the traditional systems, without incurring additional bits for error corrections, the FSO-SC system achieves a power gain of over 3 dB while enabling transmission at zenith angles over 60°. Moreover, it achieves performance on par with state-of-the-art 4-receiver spatial diversity technology, while offering superior hardware and transmission efficiency. Furthermore, we conduct 10 Gbps real-time satellite-ground equivalent experiments to validate the practicality of the FSO-SC, where it achieves a 60% reduction in communication overhead compared to existing solutions while maintaining comparable received image quality and can reach a minimum receiver sensitivity gain of 4 dB. Simulation and experimental results demonstrate that the proposed FSO-SC scheme achieves high system efficiency and stability, holding promise as a viable solution for future SatCom.

As an important technology for achieving 6G global access, low Earth orbit satellite (LEO-Sat) communication still encounters the challenges of scarce spectrum resources and the serious Doppler effect. To improve the performance of image transmission in the LEO-Sat system, this paper proposes an approach that combines semantic communication with orthogonal time-frequency space (OTFS) modulation to effectively mitigate the severe Doppler effect and enhance transmission efficiency. The NTN-TDL-D model in 3GPP is employed to simulate satellite channels and introduce noise into the training process of the semantic model. The performance of semantic-enhanced and traditional LEO-Sat systems is further evaluated under various conditions. Ultimately, simulation results demonstrate that the proposed solution achieves a minimum 6dB signal-to-noise ratio gain, reduces communication overhead by 50%, and ensures higher spectrum utilization efficiency in high-speed scenarios compared to existing solutions.

In this paper, a semantic communication-based scheme was proposed to tackle the optimization challenge of transmission efficiency and link stability in indoor visible light communication (VLC) systems utilizing light-emitting diodes for image transmission. The semantic model, established by deep convolutional generative adversarial network (DCGAN) and vector quantization method, can effectively extract the essential characteristics of images. In addition, indoor VLC channel models including line-of-sight (LOS) and non-line-of-sight (NLOS) links are established in a 5*5*3 room, while incorporating noise interference encountered during signal transmission into the training process of the semantic model to enhance its anti-interference capability. Besides, the performance disparity between the semantic VLC system and the conventional VLC system using Better Portable Graphics (BPG) is assessed across various modulation formats, transmission distances, and receiving locations. The simulation results demonstrate that the semantic VLC system effectively enhances link stability and achieves a signal-to-noise ratio (SNR) gain exceeding 6 dB. Additionally, the semantic VLC system achieves superior performance compared to the conventional VLC system employing convolutional code at a rate of 1/2, without incurring additional bits consumption for error correction. Moreover, the practicality of the semantic VLC system is experimentally validated on an indoor physical testbed online enabled by the field programmable gate array (FPGA) with up to 1 Gbps data rate. In comparison with existing schemes, the semantic VLC system effectively reduces communication overhead by 40% while maintaining similar received image quality. Furthermore, it significantly enlarges the communication coverage of the VLC system by a factor of two without necessitating any hardware modifications and ensures stable transmission of images in high-speed scenarios.