No abstract

Linear and nonlinear impairments severely limit the transmission performance of high-speed visible light communication systems. Neural network-based equalizers have been applied to optical communication systems, which enables significantly improved system performance, such as transmission data rate and distance. In this paper, a memory-controlled deep long short-term memory (LSTM) neural network post-equalizer is proposed to mitigate both linear and nonlinear impairments in pulse amplitude modulation (PAM) based visible light communication (VLC) systems. Both 1.15-Gbps PAM4 and 0.9Gbps PAM8 VLC systems are successfully demonstrated, based on a single red-LED with bit error ratio (BER) below the hard decision forward error correction (HD-FEC) limit of 3.8 x 10 −3 . Compared with the traditional finite impulse response (FIR) based equalizer, the Q factor performance is improved by 1.2dB and the transmission distance is increased by one-third in the same experimental hardware setups. Compared with traditional nonlinear hybrid Volterra equalizers, the significant complexity and system performance advantages of using a LSTMbased equalizer is demonstrated. To the best of our knowledge, this is the first demonstration of using deep LSTM in VLC systems. IntroductionVisible light communications (VLC) based on light emitting diodes (LEDs) has become an attractive and promising technology due to its cost effectiveness, immunity to electromagnetic interference, license-free and high security [1]. In recent years, transmission rate of visible light systems has been increasing with the use of` high-order modulation, such as orthogonal frequency division multiplexing (OFDM) [2], carrier-less amplitude and phase modulation (CAP) [3] and pulse amplitude modulation (PAM) [4].Equalizer is one of the most critical parts of the VLC systems. As a typical communication system, the transmitted signal of VLC systems is distorted in amplitude and delay causing the inevitable inter-symbol interference (ISI). On the other hand, nonlinear distortion has gradually become a new bottleneck in high-speed transmission systems due to nonlinear V-I response of LED source [5] and other origins that have not been well-modeled such as non-linear distortion arising from the transmitter driving circuits and the electrical amplifier (EA). Recently, Adaptive finite impulse response (FIR) filter based linear equalizers in VLC systems have been widely studied, such as scalar modified constant multi-modulus algorithm (S-MCMMA) blind equalization algorithm [6], data-aided recursive least square (RLS) [7] and least mean squares (LMS) [8]. In order to compensate for both linear and nonlinear effects, hybrid equalization schemes have been shown to be effective approaches to improve the performance of VLC systems, such as adaptive FIR linear equalizer with

No abstract

In this paper, we have experimentally demonstrated the feasibility of a LMS-Volterra based joint MIMO equalizer in multiband super-Nyquist carrierless amplitude phase modulation visible light communication system. To obtain higher spectrum efficiency, overlapping between different sub-bands is introduced in this experiment. By using joint MIMO equalizer, an aggregate data rate of 1.26 Gb/s is successfully achieved in 1-m indoor free space transmission with the BER below the 7% FEC limit of 3.8 × 10. To our best knowledge, this is the first time that our proposed joint MIMO equalizer is used to equalize multiband super-Nyquist data in VLC system.

This paper first brings a single receiver multiple-input-multiple-output (SR-MIMO) model to realize the space multiplexing in the visible light communication (VLC) system. The signals from two transmitters are super-imposed in the receiver thus to realize a specially superposed modulation. Depending on the power ratio between two transmitters, various superposed signal structures can be obtained. In order to separate the superposed signal, we design a novel detection algorithm which consists of the successive interference cancellation (SIC) and the look-up table (LUT). Extensive experiments demonstrate that a data rate of 1.5Gbit/s is achieved in the 1.3-m indoor line-of-sight (LOS) scenario with the bit error rates (BERs) are below the forward error correction (FEC) threshold.