1,721,021 research outputs found
Machine Learning for Multi-Layer Open and Disaggregated Optical Networks
Full text linkL'abstract è presente nell'allegato / the abstract is in the attachmen
Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks
Full text linkThe 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
Full text linkPlanning 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
Smart Provisioning of Sliceable Bandwidth Variable Transponders in Elastic Optical Networks
Full text linkPrior 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)
Performance evaluation of data-driven techniques for the softwarized and agnostic management of an N×N photonic switch
Full text linkThe emerging Software Defined Networking (SDN) paradigm paves the way for flexible and automatized management at each layer. The SDN-enabled optical network requires each network element’s software abstraction to enable complete control by the centralized network controller. Nowadays, silicon photonics due to its low energy consumption, low latency, and small footprint is a promising technology for implementing photonic switching topologies, enabling transparent lightpath routing in re-configurable add-drop multiplexers. To this aim, a model for the complete management of photonic switching systems’ control states is fundamental for network control. Typically, photonics-based switches are structured by exploiting the modern technology of Photonic Integrated Circuit (PIC) that enables complex elementary cell structures to be driven individually. Thus PIC switches’ control states are combinations of a large set of elementary controls, and their definition is a challenging task. In this scenario, we propose the use of several data-driven techniques based on Machine Learning (ML) to model the control states of a PIC N×N photonic switch in a completely blind manner. The proposed ML-based techniques are trained and tested in a completely topological and technological agnostic way, and we envision their application in a real-time control plane. The proposed techniques’ scalability and accuracy are validated by considering three different switching topologies: the Honey-Comb Rearrangeable Optical Switch (HCROS), Spanke-Beneš, and the Beneš network. Excellent results in terms of predicting the control states are achieved for all of the considered topologies
QoT- Estimation Assisted by Transfer learning in Extended C-band Network Operating on 400ZR
Full text linkWe 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
Novel Design and Operation of Photonic- integrated WSS for Ultra-wideband Applications
Full text linkPhotonic integrated solutions for switching applications can yield large bandwidth and high reconfigurability while requiring low power and footprint. We propose a modular, scalable photonic integrated multi-band wavelength selective switch, able to independently route the input fiber channels to an arbitrary number of output ports
Iterative Transfer Learning Approach for QoT Prediction of Lightpath in Optical Networks
Full text linkMachine learning (ML) has been widely used in optical networks for accurate Quality-of-transmission (QoT) estimation of Lightpaths (LPs). However, this domain has two main issues: ML-based models require a sufficiently large amount of data for training, and once the model is trained on one type of configuration, it cannot be used for another configuration. This paper focuses on these two issues and proposes an Active Transfer Learning (ATL) based solution. In ATL, Active learning (AL) helps in reducing the dataset’s size while not compromising the model’s performance, while the Transfer learning (TL) concept enables the transfer of knowledge from a source domain to the target domain with improved accuracy. This combined approach of ATL delivers promising results with minimum data samples and enhanced performance
Photonic-integrated wavelength selective switch for S+C+L applications
Full text linkWe propose a novel modular photonic integrated Wavelength Selective Switch (WSS) based on a reconfigurable optical multiplexer architecture, capable to operate over the S+C+L bands and scalable. The densely integrated solution takes advantage of an input stage with grating assisted contra-directional couplers to separate channels in the three considered communication bands, followed by a cascade of two-stage ladder ring resonators, to separating each transmitted channel. A final switching stage routes the signal to the desired output fiber, with a cascade of thermally controlled Mach-Zehnder interferometers. The transmission penalty of the proposed solution has been evaluated in a coherent transmission scenario
- …
