Echo State Network Based Nonlinear Equalization for 4.6 km 135 GHz D-Band Wireless Transmission

Echo state network Volterra series Forward error correction
DOI: 10.1109/jlt.2022.3220570 Publication Date: 2022-11-08T20:35:49Z
ABSTRACT
Reservoir computing (RC) is a novel computational framework derived from recurrent neural networks (RNN). It can reduce the training complexity of RNN and suitable for time-series learning tasks. The echo state network (ESN) one most popular forms RC. In this paper, an ESN-based equalizer applied to perform signal equalization in wireless D-band communication system compensate nonlinear distortion. Based on photonics-based technology multiple amplifiers, long-range transmission successfully established at D-band. We experimentally demonstrated that our proposed link realize up 4.6-km delivery over 8 Gbit/s quadrature phase shift keying (QPSK) millimeter-wave 135 GHz with bit-error-rate (BER) less than hard decision forward error correction (HD-FEC) threshold 3.8 × 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−3</sup> . Compared traditional CMA Volterra equalizer, experimental results show achieve better balance between BER performance complexity.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (39)
CITATIONS (15)