Experimental Validation of CNN vs. FFNN for Time- and Energy-Efficient EVM Estimation in Coherent Optical Systems
Artikel i vetenskaplig tidskrift, 2021

Error vector magnitude (EVM) has proven to be one of the optical performance monitoring (OPM) metrics providing the quantitative estimation of the error statistics. However, the EVM estimation efficiency is not fully exploited in terms of complexity and energy consumption. Therefore, in this article, we explore two deep-learning-based EVM estimation schemes. The first scheme exploits convolutional neural networks (CNNs) to extract EVM information from images of constellation diagram in the In-phase/Quadrature (IQ) complex plane or amplitude histograms (AH). The second scheme relies on feedforward neural networks (FFNN) extracting features from a vectorized representation of AHs. In both cases, we use short sequences of 32 Gbaud m-ary quadrature amplitude modulation (mQAM) signals captured before or after a carrier phase recovery (CPR). The impacts of the sequence length, neural network structure, and dataset representation on the EVM estimation accuracy as well as the model training time are thoroughly studied. Furthermore, we validate the performance of the proposed schemes using the experimental implementation of 28 Gbaud 64QAM signals. We achieve a mean absolute estimation error below 0.15% with short signals consisting of only 100 symbols per IQ cluster. Considering the estimation accuracy, the implementation complexity, and the potential energy savings, the proposed CNN- and FFNN-based schemes can be used to perform time-sensitive and accurate EVM estimation for mQAM signal quality monitoring purposes.

Författare

Yuchuan Fan

RISE Research Institutes of Sweden

Kungliga Tekniska Högskolan (KTH)

Aleksejs Udalcovs

RISE Research Institutes of Sweden

Carlos Natalino Da Silva

Chalmers, Elektroteknik, Kommunikations- och antennsystem, Optiska nätverk

Xiaodan Pang

RISE Research Institutes of Sweden

Kungliga Tekniska Högskolan (KTH)

Richard Schatz

Kungliga Tekniska Högskolan (KTH)

Marija Furdek Prekratic

Chalmers, Elektroteknik, Kommunikations- och antennsystem, Optiska nätverk

Sergei Popov

Kungliga Tekniska Högskolan (KTH)

Oskars Ozolins

Kungliga Tekniska Högskolan (KTH)

RISE Research Institutes of Sweden

Journal of Optical Communications and Networking

1943-0620 (ISSN)

Vol. 13 10 E63-E71

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Telekommunikation

Datavetenskap (datalogi)

Datorsystem

DOI

10.1364/JOCN.423384

Mer information

Skapat

2021-06-14