Visible light communication (VLC) is a highly promising complement to conventional wireless communication for local-area networking in future 6G. However, the extra electro-optical and photoelectric conversions in VLC systems usually introduce exceeding complexity to communication channels, in particular severe nonlinearities. Artificial intelligence (AI) techniques are investigated to overcome the unique challenges in VLC, whereas considerable obstacles are found in practical VLC systems applied with intelligent learning approaches. In this paper, we present a comprehensive study of the intelligent physical and network layer technologies for AI-empowered intelligent VLC (IVLC). We first depict a full model of the visible light channel and discuss its main challenges. The advantages and disadvantages of machine learning in VLC are discussed and analyzed by simulation. We then present a detailed overview of advances in intelligent physical layers, including optimal coding, channel emulator, MIMO, channel equalization, and optimal decision. Finally, we envision the prospects of IVLC in both the intelligent physical and network layers. This article lays out a roadmap for developing machine learning-based intelligent visible light communication in 6G.

Visible light communication (VLC) based on light-emitting diodes (LEDs) is supposed as a candidate in 6G networks because it can provide illumination and wireless communication simultaneously. As the widespread use of LEDs, the concern of light pollution and biological safety has arisen. In this paper, we propose a Si-substrate golden light LED array as a new illumination source, using high-efficacy red and yellow LEDs, which has the merits of no phosphor, no blue light, and low color temperature. Based on the golden light LED array and a 2 × 2 PIN array, a 2 × 4 high-speed multiple-input and multiple-output (MIMO) VLC system is demonstrated. Joint MIMO Tomlison-Harashima precoding (THP) scheme is first proposed and conducted for eliminating the combination of inter-symbol interference (ISI) and inter-channel interference (ICI) for carrierless amplitude and phase (CAP) modulation VLC system. Experimental results indicate that MIMO-THP performs well in interference cancellation. The Q factor is improved by 6 dB compared with conventional pure MIMO feedforward equalizer. The overall data rate exceeds 5.4 Gbit/s.

Underwater visible light communication (UVLC) based on light-emitting diodes (LEDs) is considered a potential candidate for underwater wireless data transmission. However, the implementation of high-speed UVLC remains a challenge due to bandwidth limitation and nonlinear effects. In this paper, we investigate the performance of Tomlinson-Harashima precoding (THP) in the bandwidth-limited UVLC system for the first time. Apart from research on linear and Volterra series-based nonlinear THP, neural network (NN)-based THP is first proposed and conducted. At the transmitter, the intersymbol interference (ISI) and nonlinearity can be partially mitigated through a feedback neural network (FBN) without error propagation. A modulo operator is employed to eliminate instability. In addition, for the precoded signals, the power spectral density (PSD) is near-white. Therefore, it is possible to avoid the spectrum-shaping-induced signal-to-noise ratio (SNR) loss problem that is common in pre-emphasis methods. At the receiver, another modulo operator is used for decoding. An adaptive feedforward neural network (FFN) is applied to compensate for the channel state information (CSI) mismatch of the FBN and mitigate the remaining ISI and nonlinear impairments. In the demonstrated UVLC system, the experimental results prove the feasibility of the proposed method. The Q factor is increased by 3.39 dB at a data rate of 2.2 Gbps. 630 MBd CAP-16 transmission under a 7% HD-FEC threshold is realized, which is 90 MBd higher than that when employing linear postequalization only.

The rapid development of emerging technologies has led to a significant increase in data traffic, posing challenges for data centers in terms of storing, transmitting, and processing large volumes of information. Intra- and inter-datacenter connections with high bandwidth, low latency, high reliability, and high energy efficiency are in great demand. Traditional electrical communication is becoming increasingly inadequate, while optical communication has emerged as promising solutions. Visible light laser communication (VLLC) utilizes the spectrum ranging from 380nm to 700nm and has the advantages of offering high transmission rates, cost-effectiveness, and simple system structures. In this paper, enabling technologies including high-bandwidth laser diodes, advanced modulation formats, and artificial intelligence (AI)-based equalization schemes are introduced. A compact 50-channel VLLC interconnect system has been developed, achieving ultra-high-speed short-range VLLC transmission with a record data rate of 534.51Gbps, showcasing the potential of VLLC as a high-capacity and cost-effective optical intra-data center connection solution.

Although the 5G wireless network has made significant advances, it is not enough to accommodate the rapidly rising requirement for broader bandwidth in post-5G and 6G eras. As a result, emerging technologies in higher frequencies including visible light communication (VLC), are becoming a hot topic. In particular, LED-based VLC is foreseen as a key enabler for achieving data rates at the Tb/s level in indoor scenarios using multi-color LED arrays with wavelength division multiplexing (WDM) technology. This paper proposes an optimized multi-color LED array chip for high-speed VLC systems. Its long-wavelength GaN-based LED units are remarkably enhanced by V-pit structure in their efficiency, especially in the “yellow gap” region, and it achieves significant improvement in data rate compared with earlier research. This work investigates the V-pit structure and tries to provide insight by introducing a new equivalent circuit model, which provides an explanation of the simulation and experiment results. In the final test using a laboratory communication system, the data rates of eight channels from short to long wavelength are 3.91 Gb/s, 3.77 Gb/s, 3.67 Gb/s, 4.40 Gb/s, 3.78 Gb/s, 3.18 Gb/s, 4.31 Gb/s, and 4.35 Gb/s (31.38 Gb/s in total), with advanced digital signal processing (DSP) techniques including digital equalization technique and bit-power loading discrete multitone (DMT) modulation format.

The context of the Internet of Vehicles (IoV) and the growing vehicular deployment of sensors and smart devices have demanded alternative wireless communication technologies. Despite the prevalent works on radio-frequency (RF)-based vehicular communication technologies, visible-light communication (VLC) is envisaged to be a promising candidate due to its unlicensed spectrum and high transmission rates. However, the long-distance and high-speed transmission performance of vehicular VLC needs more investigation considering the massive data transmission needs for automotive applications. In this article, a vehicular multiple-input–multiple-output (MIMO) VLC system based on two commercial headlights and a self-designed PIN array is experimentally demonstrated as a proof of concept for the IoV. Considering the relative movement of vehicles, different communication areas are divided based on the position-dependent receiver receiving states. The boundary condition of each area is derived. For the first time, the selection of the strategy that best suits the MIMO demultiplexing scheme is discussed by analyzing the rank and type of the channel matrix. A modified pilot-aided phase recovery method based on polynomial curve fitting (PCF) is proposed to compensate for the phase noise caused by the sampling frequency offset (SFO). The proposed method maintains good robustness even when the VLC system suffers from the strong nonlinearity and bandwidth limitation of the headlights. Based on the proposed MIMO VLC system, we achieve a record-breaking data rate of 3.08 Gb/s at a 2-m indoor transmission link. We further extend the transmission distance to 100 m, and successfully achieve overall data rates of 336 and 362 Mb/s during the daytime and nighttime, respectively. To the best of our knowledge, these are the highest transmission data rates ever reported for a 100-m vehicular VLC system. Our experimental demonstration clearly verifies the feasibility of VLC in the application of IoV.