Waveform-to-Waveform End-to-End Learning Framework in a Seamless Fiber-Terahertz Integrated Communication System

• DOI: 10.1109/jlt.2023.3236400
• Publication Date: 2023-01-12T21:24:39Z
• Authors: Jianyang Shi; Zhongya Li; Junlian Jia; Ziwei Li; Chao Shen; Junwen Zhang; Nan Chi
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Seamless fiber-terahertz integrated communication has emerged as a promising technology in the special field of 6G, including mobile fronthaul and wireless bridges. Electronic terahertz systems have advantages high-level integration, small form factors, potentially low costs, but their drawbacks are bandwidths high harmonic interference levels. In this paper, an end-to-end learning-based waveform-to-waveform automatic equalization framework (W2WAEF) is proposed to overcome above shortcomings seamless system. An attention-based three-tributary heterogeneous neural network (ATTH) designed simulate channel model fiber-wireless system, taking fiber optics, optical-to-electrical conversion, electrogenerated waves into account. With method, data rate 80.78 Gbps experimentally demonstrated for discrete multitone modulation (DMT) signals over 5 km 1 m 209-GHz under 20% soft decision-forward error correction (SD-FEC) threshold 2.4 × 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−2</sup> . Compared with approach without preprocessing, receiver sensitivity gain exceeding 1.3 dB successfully achieved at 60 Gbps. The method scheme meeting speed low-cost demands future systems.