dc.contributor.author | Velasco Esteban, Luis Domingo |
dc.contributor.author | Shariati, Mohammad Behnam |
dc.contributor.author | Boitier, Fabien |
dc.contributor.author | Layec, Patricia |
dc.contributor.author | Ruiz Ramírez, Marc |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors |
dc.date.accessioned | 2019-06-13T07:25:20Z |
dc.date.available | 2019-06-13T07:25:20Z |
dc.date.issued | 2019-04-05 |
dc.identifier.citation | Velasco, L. [et al.]. Learning life cycle to speed up autonomic optical transmission and networking adoption. "Journal of optical communications and networking", 5 Abril 2019, vol. 11, núm. 5, p. 226-237. |
dc.identifier.issn | 1943-0620 |
dc.identifier.uri | http://hdl.handle.net/2117/134370 |
dc.description.abstract | Autonomic optical transmission and networking requires machine learning (ML) models to be trained with large datasets. However, the availability of enough real data to produce accurate ML models is rarely ensured since new optical equipment and techniques are continuously being deployed in the network. One option is to generate data from simulations and lab experiments, but such data could not cover the whole features space and would translate into inaccuracies in the ML models. In this paper, we propose an ML-based algorithm life cycle to facilitate ML deployment in real operator networks. The dataset for ML training can be initially populated based on the results from simulations and lab experiments. Once ML models are generated, ML retraining can be performed after inaccuracies are detected to improve their precision. Illustrative numerical results show the benefits of the proposed learning cycle for general use cases. In addition, two specific use cases are proposed and demonstrated that implement different learning strategies: (i) a two-phase strategy performing out-of-field training using data from simulations and lab experiments with generic equipment, followed by an in-field adaptation to support heterogeneous equipment (the accuracy of this strategy is shown for a use case of failure detection and identification), and (ii) in-field retraining, where ML models are retrained after detecting model inaccuracies. Different approaches are analyzed and evaluated for a use case of autonomic transmission, where results show the significant benefits of collective learning. |
dc.format.extent | 12 p. |
dc.language.iso | eng |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telecomunicació òptica |
dc.subject.lcsh | Machine learning |
dc.subject.lcsh | Optical communications |
dc.subject.other | Autonomic optical transmission and net-working |
dc.subject.other | Training function placement |
dc.title | Learning life cycle to speed up autonomic optical transmission and networking adoption |
dc.type | Article |
dc.subject.lemac | Aprenentatge automàtic |
dc.subject.lemac | Comunicacions òptiques |
dc.contributor.group | Universitat Politècnica de Catalunya. GCO - Grup de Comunicacions Òptiques |
dc.identifier.doi | 10.1364/JOCN.11.000226 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://www.osapublishing.org/jocn/abstract.cfm?uri=jocn-11-5-226 |
dc.rights.access | Open Access |
local.identifier.drac | 25164351 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TEC2017-90097-R/ES/COGNITIVE 5G APPLICATION-AWARE OPTICAL METRO NETWORKS INTEGRATING MONITORING, DATA ANALYTICS AND OPTIMIZATION/ |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/H2020/761727/EU/METRO High bandwidth, 5G Application-aware optical network, with edge storage, compUte and low Latency/METRO-HAUL |
dc.relation.projectid | info:eu-repo/grantAgreement/ICREA/V PRI/ICREA ACADEMIA 2015-05 |
local.citation.author | Velasco, L.; Shariati, M.; Boitier, F.; Layec, P.; Ruiz, M. |
local.citation.publicationName | Journal of optical communications and networking |
local.citation.volume | 11 |
local.citation.number | 5 |
local.citation.startingPage | 226 |
local.citation.endingPage | 237 |