Change search
Link to record
Permanent link

Direct link
Publications (2 of 2) Show all publications
Natalino, C., Udalcovs, A., Wosinska, L., Ozolins, O. & Furdek, M. (2021). Spectrum Anomaly Detection for Optical Network Monitoring using Deep Unsupervised Learning. IEEE Communications Letters, 25(5), 1583-1586
Open this publication in new window or tab >>Spectrum Anomaly Detection for Optical Network Monitoring using Deep Unsupervised Learning
Show others...
2021 (English)In: IEEE Communications Letters, ISSN 1089-7798, E-ISSN 1558-2558, Vol. 25, no 5, p. 1583-1586Article in journal (Refereed) Published
Abstract [en]

Accurate and efficient anomaly detection is a key enabler for the cognitive management of optical networks, but traditional anomaly detection algorithms are computationally complex and do not scale well with the amount of monitoring data. Therefore, we propose an optical spectrum anomaly detection scheme that exploits computer vision and deep unsupervised learning to perform optical network monitoring relying only on constellation diagrams of received signals. The proposed scheme achieves 100% detection accuracy even without prior knowledge of the anomalies. Furthermore, operation with encoded images of constellation diagrams reduces the runtime by up to 200 times. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2021
Anomaly detection, autoencoder, Constellation diagram, Deep unsupervised learning, Optical fiber networks, optical network monitoring, Optical noise, Optical sensors, Signal to noise ratio, Training, Deep learning, Fiber optic networks, Unsupervised learning, Anomaly-detection algorithms, Cognitive managements, Constellation diagrams, Detection accuracy, Network Monitoring, Optical spectra, Prior knowledge, Received signals
National Category
Engineering and Technology
urn:nbn:se:ri:diva-52552 (URN)10.1109/LCOMM.2021.3055064 (DOI)2-s2.0-85100519047 (Scopus ID)
Available from: 2021-03-08 Created: 2021-03-08 Last updated: 2023-06-02Bibliographically approved
Öhlén, P., Skubic, B., Rostami, A., Fiorani, M., Monti, P., Ghebretensaé, Z., . . . Wosinska, L. (2016). Data Plane and Control Architectures for 5G Transport Networks. Journal of Lightwave Technology, 34(6), 1501-1508
Open this publication in new window or tab >>Data Plane and Control Architectures for 5G Transport Networks
Show others...
2016 (English)In: Journal of Lightwave Technology, ISSN 0733-8724, E-ISSN 1558-2213, Vol. 34, no 6, p. 1501-1508Article in journal (Refereed) Published
Abstract [en]

Next generation 5G mobile system will support the vision of connecting all devices that benefit from a connection, and support a wide range of services. Consequently, 5G transport networks need to provide the required capacity, latency, and flexibility in order to integrate the different technology domains of radio, transport, and cloud. This paper outlines the main challenges, which the 5G transport networks are facing and discusses in more detail data plane, control architectures, and the tradeoff between different network abstraction models.

5G mobile communication, 5G transport, Optical transport networks, Software defined networking
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
urn:nbn:se:ri:diva-25978 (URN)10.1109/JLT.2016.2524209 (DOI)2-s2.0-84963946869 (Scopus ID)
Available from: 2016-11-01 Created: 2016-11-01 Last updated: 2021-06-14Bibliographically approved

Search in DiVA

Show all publications