Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeural-network-based MDG and Optical SNR Estimation in SDM Transmission
71
0
0.0
(
0
)
Added by
Menno van den Hout
Publication date
2021
fields
Electronic Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We propose a neural network model for MDG and optical SNR estimation in SDM transmission. We show that the proposed neural-network-based solution estimates MDG and SNR with high accuracy and low complexity from features extracted after DSP.
rate research
Read More
The capacity in space division multiplexing (SDM) systems with coupled channels is fundamentally limited by mode-dependent loss (MDL) and mode-dependent gain (MDG) generated in components and amplifiers. In these systems, MDL/MDG must be accurately estimated for performance analysis and troubleshooting. Most recent demonstrations of SDM with coupled channels perform MDL/MDG estimation by digital signal processing (DSP) techniques based on the coefficients of multiple-input multiple-output (MIMO) adaptive equalizers. Although these methods provide a valid indication of the order of magnitude of the accumulated MDL/MDG over the link, MIMO equalizers are usually updated according to the minimum mean square error (MMSE) criterion, which is known to depend on the channel signal-to-noise ratio (SNR). Therefore, MDL/MDG estimation techniques based on the adaptive filter coefficients are also impaired by noise. In this paper, we model analytically the influence of the SNR on DSP-based MDL/MDG estimation, and show that the technique is prone to errors. Based on the transfer function of MIMO MMSE equalizers, and assuming a known SNR, we calculate a correction factor that improves the estimation process in moderate levels of MDL/MDG and SNR. The correction factor is validated by simulation of a 6-mode long-haul transmission link, and experimentally using a 3-mode transmission link. The results confirm the limitations of the standard estimation method in scenarios of high additive noise and MDL/MDG, and indicate the correction factor as a possible solution in practical SDM scenarios.
We experimentally validate a mode-dependent loss (MDL) estimation technique employing acorrection factor to remove the MDL estimation dependence on the SNR when using a minimum meansquare error (MMSE) equalizer. A reduction of the MDL estimation error is observed for both transmitter-side and in-span MDL emulation.
In this work, a neural network based terramechanics model and terrain estimator are presented with an outlook for optimal control applications such as model predictive control. Recognizing the limitations of the state-of-the-art terramechanics models in terms of operating conditions, computational cost, and continuous differentiability for gradient-based optimization, an efficient and twice continuously differentiable terramechanics model is developed using neural networks for dynamic operations on deformable terrains. It is demonstrated that the neural network terramechanics model is able to predict the lateral tire forces accurately and efficiently compared to the Soil Contact Model as a state-of-the-art model. Furthermore, the neural network terramechanics model is implemented within a terrain estimator and it is shown that using this model the estimator converges within around 2% of the true terrain parameter. Finally, with model predictive control applications in mind, which typically rely on bicycle models for their predictions, it is demonstrated that utilizing the estimated terrain parameter can reduce prediction errors of a bicycle model by orders of magnitude. The result is an efficient, dynamic, twice continuously differentiable terramechanics model and estimator that has inherent advantages for implementation in model predictive control as compared to previously established models.
In this paper, a novel principle-driven fiber transmission model based on physical induced neural network (PINN) is proposed. Unlike data-driven models which regard fiber transmission problem as data regression tasks, this model views it as an equation solving problem. Instead of adopting input signals and output signals which are calculated by SSFM algorithm in advance before training, this principle-driven PINN based fiber model adopts frames of time and distance as its inputs and the corresponding real and imaginary parts of NLSE solutions as its outputs. By taking into account of pulses and signals before transmission as initial conditions and fiber physical principles as NLSE in the design of loss functions, this model will progressively learn the transmission rules. Therefore, it can be effectively trained without the data labels, referred as the pre-calculated signals after transmission in data-driven models. Due to this advantage, SSFM algorithm is no longer needed before the training of principle-driven fiber model which can save considerable time consumption. Through numerical demonstration, the results show that this principle-driven PINN based fiber model can handle the prediction tasks of pulse evolution, signal transmission and fiber birefringence for different transmission parameters of fiber telecommunications.
Transfer learning is proposed to adapt an NN-based nonlinear equalizer across different launch powers and modulation formats using a 450km TWC-fiber transmission. The result shows up to 92% reduction in epochs or 90% in the training dataset.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
