Related Experiment Video
Updated: Nov 21, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
Published on: March 20, 2017
Joint Fiber Nonlinear Noise Estimation, OSNR Estimation and Modulation Format Identification Based on Asynchronous
Shuailong Yang1, Liu Yang1, Fengguang Luo1
1The School of Optics and Electronics Information, Huazhong University of Science and Technology, Wuhan 430074, China.
This study introduces asynchronous complex histogram-based multi-task artificial neural networks for simultaneous modulation format identification, OSNR, and nonlinear noise estimation in coherent optical systems. The novel approach achieves high accuracy across various modulation formats and long fiber links.
Area of Science:
- Optical Communications
- Artificial Intelligence
Background:
- Coherent optical communication systems require robust optical performance monitoring (OPM).
- Simultaneous estimation of multiple parameters like modulation format, OSNR, and nonlinear noise is challenging.
Purpose of the Study:
- To propose and demonstrate an asynchronous complex histogram (ACH)-based multi-task artificial neural network (MT-ANN) for simultaneous OPM.
- To enable simultaneous modulation format identification (MFI), optical signal-to-noise ratio (OSNR) estimation, and fiber nonlinear (NL) noise power estimation.
Main Methods:
- Development of ACH-based MT-ANNs for integrated OPM.
- Demonstration with polarization mode multiplexing (PDM), 16QAM, PDM-32QAM, and PDM-star 16QAM (S-16QAM).
- Testing across a wide range of launched power (-3 to -2 dBm) and fiber lengths (160-1600 km).
Main Results:
- Achieved 100% accuracy for MFI.
- Obtained an average root mean square error (RMSE) of 0.37 dB for OSNR estimation.
- Achieved an average RMSE of 0.25 dB for NL noise power estimation.
- Demonstrated robustness to increased fiber length.
Conclusions:
- The proposed ACH MT-ANN offers a robust and efficient solution for simultaneous OPM in long-haul coherent optical systems.
- This method allows monitoring multiple optical network parameters with improved performance and reduced training data requirements.
- The system holds significant reference value for future long-haul coherent OPM systems.
Related Concept Videos
Linear Approximation in Frequency Domain
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
Receiver Operating Characteristic Plot
Classification of Signals
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations
Reconstruction of Signal using Interpolation
Linear Approximation in Time Domain
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...

