Distributed and centralized options for self-learning
Document typeConference report
Rights accessOpen Access
European Commission's projectMETRO-HAUL - METRO High bandwidth, 5G Application-aware optical network, with edge storage, compUte and low Latency (EC-H2020-761727)
In general, the availability of enough real data from real fog computing scenarios to produce accurate Machine Learning (ML) models is rarely ensured since new equipment, techniques, etc., are continuously being deployed in the field. Although an option is to generate data from simulation and lab experiments, such data could not cover the whole features space, which would translate into ML models inaccuracies. In this paper, we propose a self-learning approach to facilitate ML deployment in real scenarios. A dataset for ML training can be initially populated based on the results from simulation and lab experiments and once ML models are generated, ML re-training can be performed after inaccuracies are detected to improve their precision. Illustrative numerical results show the benefits from the proposed self-learning approach for two general use cases of regression and classification.
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
CitationTabatabaeimehr, F.; Ruiz, M.; Velasco, L. Distributed and centralized options for self-learning. A: International Conference on Transparent Optical Networks. "ICTON 2019, 21st International Conference on Transparent Optical Networks: 9-13 July 2019, Angers France". 2019, p. 1-4. ISBN 978-1-7281-2779-8. DOI 10.1109/ICTON.2019.8840514.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder