scholarly journals Protection against Failure of Machine Learning-based QoT Prediction

2021 ◽  
Author(s):  
Ningning Guo ◽  
Longfei Li ◽  
Biswanath Mukherjee ◽  
Gangxiang Shen
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Signal To Noise Ratio ◽  
Optical Network ◽  
Optical Signal ◽  
Spectrum Efficiency ◽  
Service Availability ◽  
Protection Mechanism ◽  
Backup Path ◽  
Path Protection

Machine learning (ML)-based methods are widely explored to predict the quality of transmission (QoT) of a lightpath, which is expected to reduce optical signal to noise ratio (OSNR) margin reserved for the lightpath and therefore improve the spectrum efficiency of an optical network. However, many studies conducting this prediction are often based on synthetic datasets or datasets obtained from laboratory. As such, these datasets may not be amply representative to cover the entire status space of a real optical network, which is often exposed in harsh environment. There are risks of failure when using these ML-based QoT prediction models. It is necessary to develop a mechanism that can guarantee the reliability of a lightpath service even if the prediction models fail. For this, we propose to take advantage of the conventional network protection techniques that are popularly implemented in an optical network and reuse their protection resources to also protect against such a type of failure. Based on the two representative protection techniques, i.e., 1+1 dedicated path protection and shared backup path protection (SBPP), the performance of the proposed protection mechanism is evaluated by reserving different margins for the working and protection lightpaths. For 1+1 path protection, we find that the proposed mechanism can achieve a zero design-margin (D-margin) for a working lightpath thereby significantly improving network spectrum efficiency, while not scarifying the availability of lightpath services. For SBPP, we find that an optimal D-margin should be identified to balance the spectrum efficiency and service availability, and although not significant, the proposed mechanism can save an up to 0.5-dB D-margin for a working lightpath, while guaranteeing the service availability.

scholarly journals Protection against Failure of Machine Learning-based QoT Prediction

2021 ◽  
Author(s):  
Ningning Guo ◽  
Longfei Li ◽  
Biswanath Mukherjee ◽  
Gangxiang Shen
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Signal To Noise Ratio ◽  
Optical Network ◽  
Optical Signal ◽  
Spectrum Efficiency ◽  
Service Availability ◽  
Protection Mechanism ◽  
Backup Path ◽  
Path Protection

Machine learning (ML)-based methods are widely explored to predict the quality of transmission (QoT) of a lightpath, which is expected to reduce optical signal to noise ratio (OSNR) margin reserved for the lightpath and therefore improve the spectrum efficiency of an optical network. However, many studies conducting this prediction are often based on synthetic datasets or datasets obtained from laboratory. As such, these datasets may not be amply representative to cover the entire status space of a real optical network, which is often exposed in harsh environment. There are risks of failure when using these ML-based QoT prediction models. It is necessary to develop a mechanism that can guarantee the reliability of a lightpath service even if the prediction models fail. For this, we propose to take advantage of the conventional network protection techniques that are popularly implemented in an optical network and reuse their protection resources to also protect against such a type of failure. Based on the two representative protection techniques, i.e., 1+1 dedicated path protection and shared backup path protection (SBPP), the performance of the proposed protection mechanism is evaluated by reserving different margins for the working and protection lightpaths. For 1+1 path protection, we find that the proposed mechanism can achieve a zero design-margin (D-margin) for a working lightpath thereby significantly improving network spectrum efficiency, while not scarifying the availability of lightpath services. For SBPP, we find that an optimal D-margin should be identified to balance the spectrum efficiency and service availability, and although not significant, the proposed mechanism can save an up to 0.5-dB D-margin for a working lightpath, while guaranteeing the service availability.

A Shared Path Protection Mechanism Based on Delay Constraint in the Optical Network

2013 ◽  
Vol 427-429 ◽  
pp. 2237-2244
Author(s):  
Jie Li ◽  
Xing Wei Wang ◽  
Min Huang
Keyword(s):  
Real Time ◽  
Optical Network ◽  
Propagation Delay ◽  
Wavelength Assignment ◽  
Delay Constraint ◽  
Protection Mechanism ◽  
Path Protection ◽  
Important Concern ◽  
Efficient Protection ◽  
Shared Path Protection

Survivability is an important concern in the optical network. In order to offer an effective and efficient protection mechanism that meeting both delay constraint and availability guarantees for real-time services in the optical network, a shared path protection mechanism based on delay constraint is proposed in this paper. Thinking of the processing delay and the propagation delay as main factors which have great effect on the delay of real-time services, the mechanism designs the routing and wavelength assignment schemes for the working path and the protection path. Simulation results show that the proposed mechanism is both feasible and effective.

Optical SNR estimation using machine learning

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Palash Rai ◽  
Rahul Kaushik
Keyword(s):  
Machine Learning ◽  
Signal Analysis ◽  
Nearest Neighbor ◽  
Signal To Noise Ratio ◽  
Optical Signal ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbor ◽  
Eye Diagram ◽  
Test Instrument ◽  
Data Signal

Abstract A technique for the estimation of an optical signal-to-noise ratio (OSNR) using machine learning algorithms has been proposed. The algorithms are trained with parameters derived from eye-diagram via simulation in 10 Gb/s On-Off Keying (OOK) nonreturn-to-zero (NRZ) data signal. The performance of different machine learning (ML) techniques namely, multiple linear regression, random forest, and K-nearest neighbor (K-NN) for OSNR estimation in terms of mean square error and R-squared value has been compared. The proposed methods may be useful for intelligent signal analysis in a test instrument and to monitor optical performance.

Applying Smart Security Model to Protect Client Services From the Threats of the Optical Network

2021 ◽  
pp. 80-113
Author(s):  
Kamel H. Rahouma ◽  
Ayman A. Ali
Keyword(s):  
Signal To Noise Ratio ◽  
Optical Network ◽  
Optical Signal ◽  
Software Defined Network ◽  
Security Model ◽  
Signal To Noise ◽  
New Model ◽  
Intelligent Software ◽  
Optical Transport Network ◽  
The Right

The chapter discusses the security of the client signals over the optical network from any wiretapping or loosing. The physical layer of the optical transport network (OTN) is the weakest layer in the network; anyone can access the optical cables from any location and states his attack. A security layer is proposed to be added in the mapping of OTN frames. The detection of any intrusion is done by monitoring the variations in the optical signal to noise ratio (OSNR) by using intelligent software defined network. The signal cryptographic is done at the source and the destination only. The chapter shows how the multi-failure restorations in the multi-domains could be done. A new model is introduced by slicing the multi-domains to three layers to fit the needs of 5G. The results show that the multi-failure restoration improved from 25% to 100%, the revenue from some OTN domains increased by 50%, the switching time enhanced by 50%, the latency reduced from 27 msec to 742 usec, and it will take many years to figure out the right keys to perform the decryption process.

Complete suppression of FWM in ultra dense WDM-PON optical networks using centralized light source

2015 ◽  
Vol 24 (04) ◽  
pp. 1550053 ◽  
Author(s):  
Habib Ullah Manzoor ◽  
Ashiq Hussain ◽  
Chong Xiu Yu ◽  
Tareq Manzoor
Keyword(s):  
Optical Networks ◽  
Light Source ◽  
Signal To Noise Ratio ◽  
Optical Network ◽  
Optical Signal ◽  
Complete Suppression ◽  
Left Hand ◽  
Circular Polarizer ◽  
Received Power ◽  
Dense Wdm

In this paper, a novel technique to completely eliminate FWM has been introduced. Alternative circular polarizer have been used to change the polarization of incoming pulses into left-hand and right-hand polarizations before multiplexing in UDWDM optical network with centralized light source. System’s performance have been calculated on the bases of Q factor, optical signal to noise ratio, received power and bit error rate. All simulation has been performed in OptiSystem.

scholarly journals Joint Fiber Nonlinear Noise Estimation, OSNR Estimation and Modulation Format Identification Based on Asynchronous Complex Histograms and Deep Learning for Digital Coherent Receivers

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 380
Author(s):  
Shuailong Yang ◽  
Liu Yang ◽  
Fengguang Luo ◽  
Bin Li ◽  
Xiaobo Wang ◽  
...  
Keyword(s):  
Performance Monitoring ◽  
Signal To Noise Ratio ◽  
Optical Network ◽  
Power Estimation ◽  
Optical Signal ◽  
Training Data ◽  
Noise Power ◽  
Optical Performance Monitoring ◽  
Modulation Format ◽  
Coherent Receivers

In this paper, asynchronous complex histogram (ACH)-based multi-task artificial neural networks (MT-ANNs), are proposed to realize modulation format identification (MFI), optical signal-to-noise ratio (OSNR) estimation and fiber nonlinear (NL) noise power estimation simultaneously for coherent optical communication. Optical performance monitoring (OPM) is demonstrated with polarization mode multiplexing (PDM), 16 quadrature amplitude modulation (QAM), PDM-32QAM, as well as PDM-star 16QAM (S-16QAM) for the first time. The range of launched power is −3 to −2 dBm with a fiber link of 160–1600 km. Then, the accuracy of MFI reaches 100%. The average root mean square error (RMSE) of OSNR estimation can reach 0.37 dB. The average RMSE of NL noise power estimation can reach 0.25 dB. The results show that the monitoring scheme is robust to the increase of fiber length, and the solution can monitor more optical network parameters with better performance and fewer training data, simultaneously. The proposed ACH MT-ANN has certain reference significance for the future long-haul coherent OPM system.

Impairments Computation for Routing Purposes in a Transparent-Access Optical Network Based on Optical CDMA and WDM

2016 ◽  
Vol 37 (2) ◽  
Author(s):  
Ahmed Musa
Keyword(s):  
Wavelength Division Multiplexing ◽  
Wavelength Conversion ◽  
Signal To Noise Ratio ◽  
Optical Network ◽  
Routing Algorithm ◽  
Optical Signal ◽  
Network Routing ◽  
Optical Cdma ◽  
Fiber Types ◽  
Wavelength Division

AbstractOptical access networks are becoming more widespread and the use of multiple services might require a transparent optical network (TON). Multiplexing and privacy could benefit from the combination of wavelength division multiplexing (WDM) and optical coding (OC) and wavelength conversion in optical switches. The routing process needs to be cognizant of different resource types and characteristics such as fiber types, fiber linear impairments such as attenuation, dispersion, etc. as well as fiber nonlinear impairments such as four-wave mixing, cross-phase modulation, etc. Other types of impairments, generated by optical nodes or photonic switches, also affect the signal quality (Q) or the optical signal to noise ratio (OSNR), which is related to the bit error rate (BER). Therefore, both link and switch impairments must be addressed and somehow incorporated into the routing algorithm. However, it is not practical to fully integrate all photonic-specific attributes in the routing process. In this study, new routing parameters and constraints are defined that reflect the distinct characteristics of photonic networking. These constraints are applied to the design phase of TON and expressed as a cost or metric form that will be used in the network routing algorithm.

Sign in / Sign up

Export Citation Format

Share Document