Demonstration of 50 Gbps Long-Haul D-Band Radio-over-Fiber System with 2D-Convolutional Neural Network Equalizer for Joint Phase Noise and Nonlinearity Mitigation

Abstract

High demand for 6G wireless has made photonics-aided D-band (110-170 GHz) communication a research priority. Photonics-aided technology integrates optical and wireless communications to boost spectral efficiency and transmission distance. This study presents a Radio-over-Fiber (RoF) communication system utilizing photonics-aided technology for 4600 m long-distance D-band transmission. We successfully show the transmission of a 50 Gbps (25 Gbaud) QPSK signal utilizing a 128.75 GHz carrier frequency. Notwithstanding these encouraging outcomes, RoF systems encounter considerable obstacles, including pronounced nonlinear distortions and phase noise related to laser linewidth. Numerous factors can induce nonlinear impairments, including high-power amplifiers (PAs) in wireless channels, the operational mechanisms of optoelectronic devices (such as electrical amplifiers, modulators, and photodiodes), and elevated optical power levels during fiber transmission. Phase noise (PN) is generated by laser linewidth. Despite the notable advantages of classical Volterra series and deep neural network (DNN) methods in alleviating nonlinear distortion, they display considerable performance limitations in adjusting for phase noise. To address these problems, we propose a novel post-processing approach utilizing a two-dimensional convolutional neural network (2D-CNN). This methodology allows for the extraction of intricate features from data preprocessed using traditional Digital Signal Processing (DSP) techniques, enabling concurrent compensation for phase noise and nonlinear distortions. The 4600 m long-distance D-band transmission experiment demonstrated that the proposed 2D-CNN post-processing method achieved a Bit Error Rate (BER) of 5.3 × 10^-3 at 8 dBm optical power, satisfying the soft-decision forward error correction (SD-FEC) criterion of 1.56 × 10^-2 with a 15% overhead. The 2D-CNN outperformed Volterra series and deep neural network approaches in long-haul D-band RoF systems by compensating for phase noise and nonlinear distortions via spatiotemporal feature integration, hierarchical feature extraction, and nonlinear modelling.

Keywords: 2D-convolutional neural network; D-band; nonlinear equalization; phase noise compensation; photonics-aided; wireless transmission.

Figure 1

Two-dimensional structure of the input data.

Figure 2

Schematic flowchart of 2D-CNN.

Figure 3

The experimental setup: (a) single-channel 4600 m wireless testing configuration, (b) transmitter-side and receiver-side DSP.

Figure 4

Curve of the BER performance for 2D-CNN, 1D-CNN, 1D-DNN, and VNE.

Figure 5

Comparison of signal constellation diagrams for various neural networks and VNE (optical power: 8 dBm).

Figure 6

BER performance curve of 2D-CNN with varying quantities of trainable parameters.

Figure 7

Training and validation loss curves for different numbers of trainable parameters at 8 dBm. (a) 100,000 parameters; (b) 150,000 parameters; (c) 200,000 parameters; (d) 350,000 parameters.

Figure 8

Impact of various activation functions on the BER of 2D-CNN, with insets of recovered constellation diagrams for (i) Sigmoid, (ii) Tanh, (iii) Mish, and (iv) ReLU with an optical power of 8 dBm.

Figure 9

The BER performance of the 2D-CNN utilizing various loss functions.

Figure 10

The impact of various optimizers on the BER of 2D-CNN.