no code implementations • 12 Dec 2023 • Lars E. Kruse, Sebastian Kühl, Annika Dochhan, Stephan Pachnicke
In this paper, we experimentally compare the performance of soft-failure management of different machine learning algorithms.
no code implementations • 8 Jul 2023 • Khouloud Abdelli, Carsten Tropschug, Helmut Griesser, Stephan Pachnicke
Passive optical network (PON) systems are vulnerable to a variety of failures, including fiber cuts and optical network unit (ONU) transmitter/receiver failures.
no code implementations • 3 Apr 2023 • Khouloud Abdelli, Carsten Tropschug, Helmut Griesser, Stephan Pachnicke
In this paper, to overcome the aforementioned issues, we propose a generic ML approach trained independently of the network architecture for identifying the faulty branch in PON systems given OTDR signals for the cases of branches with close lengths.
no code implementations • 1 Apr 2023 • Khouloud Abdelli, Carsten Tropschug, Helmut Griesser, Sander Jansen, Stephan Pachnicke
A machine learning approach for improving monitoring in passive optical networks with almost equidistant branches is proposed and experimentally validated.
no code implementations • 30 Mar 2023 • Md Sabbir-Bin Hossain, Georg Bocherer, Talha Rahman, Tom Wettlin, Nebojsa Stojanovic, Stefano Calabro, Stephan Pachnicke
Probabilistic constellation shaping has been used in long-haul optically amplified coherent systems for its capability to approach the Shannon limit and realize fine rate granularity.
no code implementations • 5 Nov 2022 • Khouloud Abdelli, Helmut Griesser, Christian Neumeyr, Robert Hohenleitner, Stephan Pachnicke
Semiconductor lasers have been rapidly evolving to meet the demands of next-generation optical networks.
no code implementations • 5 Nov 2022 • Khouloud Abdelli, Helmut Griesser, Stephan Pachnicke
First of all, an attention based gated recurrent unit (GRU) model is adopted for real-time prediction of performance degradation.
no code implementations • 14 Jun 2022 • Md Sabbir-Bin Hossain, Georg Böcherer, Youxi Lin, Shuangxu Li, Stefano Calabrò, Andrei Nedelcu, Talha Rahman, Tom Wettlin, Jinlong Wei, Nebojša Stojanović, Changsong Xie, Maxim Kuschnerov, Stephan Pachnicke
For 200Gb/s net rates, cap probabilistic shaped PAM-8 with different Gaussian orders are experimentally compared against uniform PAM-8.
no code implementations • 18 May 2022 • Md Sabbir-Bin Hossain, Georg Boecherer, Talha Rahman, Nebojsa Stojanovic, Patrick Schulte, Stefano Calabrò, Jinlong Wei, Christian Bluemm, Tom Wettlin, Changsong Xie, Maxim Kuschnerov, Stephan Pachnicke
For 200Gbit/s net rates, uniform PAM-4, 6 and 8 are experimentally compared against probabilistic shaped PAM-8 cap and cup variants.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Danish Rafique, Stephan Pachnicke
Laser degradation analysis is a crucial process for the enhancement of laser reliability.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Helmut Griesser, Stephan Pachnicke
In this paper, a data-driven diagnostic and prognostic approach based on machine learning is proposed to detect laser failure modes and to predict the remaining useful life (RUL) of a laser during its operation.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke
Optical time-domain reflectometry (OTDR) has been widely used for characterizing fiber optical links and for detecting and locating fiber faults.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Danish Rafique, Helmut Griesser, Stephan Pachnicke
A novel approach based on an artificial neural network (ANN) for lifetime prediction of 1. 55 um InGaAsP MQW-DFB laser diodes is presented.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Helmut Griesser, Stephan Pachnicke
Fast and accurate fault detection and localization in fiber optic cables is extremely important to ensure the optical network survivability and reliability.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Helmut Griesser, Peter Ehrle, Carsten Tropschug, Stephan Pachnicke
To reduce operation-and-maintenance expenses (OPEX) and to ensure optical network survivability, optical network operators need to detect and diagnose faults in a timely manner and with high accuracy.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, JOO YEON CHO, Florian Azendorf, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke
The proposed method combines an autoencoder-based anomaly detection and an attention-based bidirectional gated recurrent unit algorithm, whereby the former is used for fault detection and the latter is adopted for fault diagnosis and localization once an anomaly is detected by the autoencoder.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Florian Azendorf, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke
We propose a deep learning approach based on an autoencoder for identifying and localizing fiber faults in passive optical networks.
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Helmut Griesser, Stephan Pachnicke
A hybrid prognostic model based on convolutional neural networks (CNN) and long short-term memory (LSTM) is proposed to predict the laser remaining useful life (RUL).
no code implementations • 19 Mar 2022 • Khouloud Abdelli, Helmut Griesser, Stephan Pachnicke
A new privacy-preserving federated learning framework allowing laser manufacturers to collaboratively build a robust ML-based laser lifetime prediction model, is proposed.
no code implementations • 16 Feb 2022 • Khouloud Abdelli, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke
A novel multitask learning approach based on stacked bidirectional long short-term memory (BiLSTM) networks and convolutional neural networks (CNN) for detecting, locating, characterizing, and identifying fiber faults is proposed.
no code implementations • 17 May 2021 • Irene Estébanez, Shi Li, Janek Schwind, Ingo Fischer, Stephan Pachnicke, Apostolos Argyris
In this work, we show that the effectiveness of the internal fading memory depends significantly on the properties of the signal to be processed.
no code implementations • 29 May 2020 • Tom Wettlin, Talha Rahman, Jinlong Wei, Stefano Calabrò, Nebojsa Stojanovic, Stephan Pachnicke
We show an example, in which the number of third-order kernels is halved without any appreciable performance degradation.