112 research outputs found
Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks
No full textThe quality of transmission (QoT) estimation of lightpaths (LPs) has both technological and economic significance from the operator’s perspective. TThe quality of transmission (QoT) estimation of lightpaths (LPs) has both technological and economic significance from the operator’s perspective. Typically, the network administrator configures the network element (NE) working point according to the specified nominal values given by vendors. These operational NEs experienced some variation from the given nominal working point and thus put up uncertainty during their operation, resulting in the introduction of uncertainty in estimating LP QoT. Consequently, a substantial margin is required to avoid any network outage. In this context, to reduce the required margin provisioning, a machine learning (ML) based framework is proposed which is cross-trained using the information retrieved from the fully operational network and utilized to support the QoT estimation unit of an un-used sister network
Advanced Formulation of QoT-Estimation for Un-established Lightpaths Using Cross-train Machine Learning Methods
No full textPlanning tools with excellent accuracy along with precise and advance estimation of the quality of transmission (QoT) of lightpaths (LPs) have techno-economic importance for a network operator. The QoT metric of LPs is defined by the generalized signal-to-noise ratio (GSNR) which includes the effect of both amplified spontaneous emission (ASE) noise and non-linear interference (NLI) accumulation. Typically, a considerable number of analytical models are available for the estimation of QoT but all of them require the exact description of system parameters. Thus, the analytical models are impractical in case of un-used network scenarios. In this study, we exploit an alternative approach based on three machine learning (ML) techniques for QoT estimation (QoT-E). The proposed ML based techniques are cross-trained on the characteristic features extracted from the telemetry data of the already in-service network. This new approach provides a reliable QoT-E and consequently assists the network operator in network planning and also enables the reliable low-margin LP deployment
Assessment of Cross-train Machine Learning Techniques for QoT-Estimation in agnostic Optical Networks
No full textWith the evolution of 5G technology, high definition video, virtual reality, and the internet of things (IoT), the demand for high capacity optical networks has been increasing dramatically. To support the capacity demand, low-margin optical networks engage operator interest. To engross this techno-economic interest, planning tools with higher accuracy and accurate models for the quality of transmission estimation (QoT-E) are needed. However, considering the state-of-the-art optical network’s heterogeneity, it is challenging to develop such an accurate planning tool and low-margin QoT-E models using the traditional analytical approach. Fortunately, data-driven machine-learning (ML) cognition provides a promising path. This paper reports the use of cross-trained ML-based learning methods to predict the QoT of an un-established lightpath (LP) in an agnostic network based on the retrieved data from already established LPs of an in-service network. This advanced prediction of the QoT of un-established LP in an agnostic network is a key enabler not only for the optimal planning of this network but it also provides the opportunity to automatically deploy the LPs with a minimum margin in a reliable manner. The QoT metric of the LPs are defined by the generalized signal-to-noise ratio (GSNR), which includes the effect of both amplified spontaneous emission (ASE) noise and non-linear interference (NLI) accumulation. The real field data is mimicked by using a well reliable and tested network simulation tool GNPy. Using the generated synthetic data set, supervised ML techniques such as wide deep neural network, deep neural network, multi-layer perceptron regressor, boasted tree regressor, decision tree regressor, and random forest regressor are applied, demonstrating the GSNR prediction of an un-established LP in an agnostic network with a maximum error of 0.40 dB
Optimal control of Beneš optical networks assisted by machine learning
No full textOptimal control of Beneˇs optical networks
assisted by machine learning
Ihtesham Khana, Lorenzo Tunesia, Muhammad Umar Masooda, Enrico Ghillinob,
Paolo Bardellaa, Andrea Carenaa, and Vittorio Curria
aPolitecnico di Torino, Corso Duca degli Abruzzi 24, Torino, Italy
bSynopsys Inc., Executive Blvd 101, Ossining, New York, USA
ABSTRACT
Beneˇs networks represent an excellent solution for the routing of optical telecom signals in integrated, fully
reconfigurable networks because of their limited number of elementary 2x2 crossbar switches and their non-
blocking properties. Various solutions have been proposed to determine a proper Control State (CS) providing
the required permutation of the input channels; since for a particular permutation, the choice is not unique, the
number of cross-points has often been used to estimate the cost of the routing operation. This work presents an
advanced version of this approach: we deterministically estimate all (or a reasonably large number of) the CSs
corresponding to the permutation requested by the user. After this, the retrieved CSs are exploited by a data-
driven framework to predict the Optical Signal to Noise Ratio (OSNR) penalty for each CS at each output port,
finally selecting the CS providing minimum OSNR penalty. Moreover, three different data-driven techniques are
proposed, and their prediction performance is analyzed and compared.
The proposed approach is demonstrated using 8x8 Beneˇs architecture with 20 ring resonator-based crossbar
switches. The dataset of 1000 OSNRs realizations is generated synthetically for random combinations of the
CSs using Synopsys® OptsimTM simulator. The computational cost of the proposed scheme enables its real-time
operation in the field
QoT Estimation for Light-path Provisioning in Un-Seen Optical Networks using Machine Learning
No full textWe propose the use of machine-learning based regression model to predict the quality of transmission (QoT) of an un-established lightpath (LP) in an un-seen network prior to its actual deployment, based on telemetry data of already established LPs of different network. This advance prediction of the QoT of un-established LP in an un-seen network has a promising factor not only for the optimal designing of this network but also enables the possibility to automatically deploy the LPs with a minimum margin in a reliable manner. The QoT metric of the LPs are defined by the Generalized Signal-to-Noise Ratio (GSNR) which includes the effect of both Amplified Spontaneous Emission (ASE) noise and Non-Linear Interference (NLI) accumulation. In the response of present simulation scenario, the real field telemetry data is mimicked by using a well reliable and tested network simulation tool GNPy. Using the generated data set, a machine-learning technique is applied, demonstrating the GSNR prediction of an un-established LP in an unrevealed network with maximum error of 0.53 dB
Smart Provisioning of Sliceable Bandwidth Variable Transponders in Elastic Optical Networks
No full textPrior provisioning of optical source technologies have techno-economic importance for the operator during the design and planning of optical network architectonics. Advancement towards the latest technology paradigm such as Elastic Optical Networks (EONs) and Software Defined Networking (SDN) open a gateway for a flexible and re-configurable optical network architecture. In order to achieve the required degree of flexibility, a flexible and dynamic behaviour is required both at the control and data plane. In this regards, SDN-enabled flexible optical transceivers are proposed to provide the required degree of flexibility. Sliceable Bandwidth Variable Transponders (SBVTs) is one of the recent type of flexible optical transceivers. Based on the type/technology of optical carrier source, the SBVTs are categorized into two types; Multi-Laser SBVT (ML-SBVT) and Multi-wavelength SBVT (MW-SBVT). Both architectures have their own pros and cons when it comes to accommodate traffic request. In this paper, we propose a selection model for the SBVTs before its actual deployment in the network. The selection model consider various design and planning phase network characteristics. In addition to this selection model, the comparison of centralized Flex-OCSM architecture is also presented with the already discussed SBVT types. The analysis in this work is performed on random network (20 nodes) and the German Network (17 nodes)
Convolutional neural network for quality of transmission prediction of unestablished lightpaths
No full textWith the advancement in evolving concepts of software-defined networks and elastic-optical-network, the number of design parameters is growing dramatically, making the lightpath (LP) deployment more complex. Typically, worst-case assumptions are utilized to calculate the quality-of-transmission (QoT) with the provisioning of high-margin requirements. To this aim, precise and advanced estimation of the QoT of the LP is essential for reducing this provisioning margin. In this investigation, we present convolutional-neural-networks (CNN) based architecture to accurately calculate QoT before the actual deployment of LP in an unseen network. The proposed model is trained on the data acquired from already established LP of a completely different network. The metric considered to evaluate the QoT of LP is the generalized signal-to-noise ratio (GSNR). The synthetic dataset is generated by utilizing well appraised GNPy simulation tool. Promising results are achieved, showing that the proposed CNN model considerably minimizes the GSNR uncertainty and, consequently, the provisioning margin
Cross-feature trained machine learning models for QoT-estimation in optical networks
No full textThe ever-increasing demand for global internet traffic, together with evolving concepts of software-defined networks and elastic-optical-networks, demand not only the total capacity utilization of underlying infrastructure but also a dynamic, flexible, and transparent optical network. In general, worst-case assumptions are utilized to calculate the quality of transmission (QoT) with provisioning of high-margin requirements. Thus, precise estimation of the QoT for the lightpath (LP) establishment is crucial for reducing the provisioning margins. We propose and compare several data-driven machine learning (ML) models to make an accurate calculation of the QoT before the actual establishment of the LP in an unseen network. The proposed models are trained on the data acquired from an already established LP of a completely different network. The metric considered to evaluate the QoT of the LP is the generalized signal-to-noise ratio (GSNR), which accumulates the impact of both nonlinear interference and amplified spontaneous emission noise. The dataset is generated synthetically using a well-tested GNPy simulation tool. Promising results are achieved, showing that the proposed neural network considerably minimizes the GSNR uncertainty and, consequently, the provisioning margin. Furthermore, we also analyze the impact of cross-features and relevant features training on the proposed ML models’ performance
QoT- Estimation Assisted by Transfer learning in Extended C-band Network Operating on 400ZR
No full textWe propose a transfer learning-based technique that assists in estimating the Quality-of-transmission (QoT) of the lightpaths in an extended C-band network on 400ZR. The proposed scheme develops the cognition using the traditional C-band operating network knowledge
- …
