Nonlinear effects have been restricting the development of high-speed visible light communication (VLC) systems. Neural network (NN) has become an effective means to alleviate the nonlinearity of a VLC system due to its powerful ability to fit complicated functions. However, the complex training process of traditional NN limits its application in high-speed VLC. Without performance penalty, reservoir computing (RC) simplifies the training process of NN by training only part of the network connection weights, and has become an alternative scheme to NN. For the indoor visible light orthogonal frequency division multiplexing (VLC-OFDM) system, this paper studies the signal recovery effect of the pilot-assisted reservoir computing (PA-RC) frequency domain equalization algorithm. The pilot information is added to the feature engineering of RC to improve the accuracy of channel estimation by traditional least squares (LS) algorithm. The performance of 64 quadrature amplitude modulation (QAM) signal under different transmission rates and peak to peak voltage (Vpp) conditions is demonstrated in the experiments. Compared with the traditional frequency domain equalization algorithms, PA-RC can further expand the Vpp range that meets the 7% hard-decision forward error correction (FEC) limit of 3.8 × 10−3. At the rate of 240 Mbps, the BER of the system is reduced by about 90%, and the utilization rate of the available frequency band of the system reaches 100%. The results show that PA-RC can effectively improve the transmission performance of VLC system well, and has strong generalization ability.

Semiconductor optical amplifier (SOA) is considered an excellent candidate for power amplification at O-band due to its low cost and small footprint. In passive optical networks (PONs), SOA is popular as a booster and pre-amplifier to improve the link power budget. However, whether as a booster or pre-amplifier, SOA will induce different degrees of nonlinearity when the output power is high, which degrades the transmission performance of the system and leads to a limited receiver dynamic range. In this paper, we experimentally demonstrate the feasibility of using SOA in both transmitter and receiver sides for power budget improvement in 100 Gb/s/λ four-level pulsed amplitude modulation (PAM-4) time division multiplexed PON (TDM-PON) system at O-band. For compensating the linear and nonlinear impairments induced by transceivers and SOA, a look-up-table (LUT) pre-compensation at the optical line terminal (OLT) side and a simple feed-forward equalizer (FFE) at the optical network unit (ONU) side are adopted for downstream transmission. For upstream transmission, a 2nd-order Volterra nonlinear equalizer (VNLE) is utilized at the OLT side, and no pre-compensation is used at the transmitter of the ONU, which releases the digital signal processing (DSP) pressure of ONUs in a multi-user scenario. For the soft-decision FEC (SD-FEC) threshold (1 × 10−2), the IEEE PR-30 power budget requirement is met, and >18 dB dynamic range is achieved in both 25 km downstream and upstream transmission.