Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks

Ihtesham Khan; Muhammad Bilal; Vittorio Curri

doi:10.1007/978-981-16-5692-7_9

Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks

Ihtesham Khan^*, Muhammad Bilal, Vittorio Curri

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

The 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.

Original language	English
Title of host publication	Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020
Editors	Maode Ma
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	78-87
Number of pages	10
ISBN (Print)	9789811656910
DOIs	https://doi.org/10.1007/978-981-16-5692-7_9
State	Published - 2022
Externally published	Yes
Event	4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020 - Singapore, Singapore Duration: 4 Dec 2020 → 6 Dec 2020

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	797 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020
Country/Territory	Singapore
City	Singapore
Period	4/12/20 → 6/12/20

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Generalized SNR
Machine learning
QoT-estimation

ASJC Scopus subject areas

Industrial and Manufacturing Engineering

Access to Document

10.1007/978-981-16-5692-7_9

Cite this

Khan, I., Bilal, M., & Curri, V. (2022). Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks. In M. Ma (Ed.), Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020 (pp. 78-87). (Lecture Notes in Electrical Engineering; Vol. 797 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-5692-7_9

Khan, Ihtesham ; Bilal, Muhammad ; Curri, Vittorio. / Cross-Train : Machine Learning Assisted QoT-Estimation in Un-used Optical Networks. Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020. editor / Maode Ma. Springer Science and Business Media Deutschland GmbH, 2022. pp. 78-87 (Lecture Notes in Electrical Engineering).

@inproceedings{e28ac896735b46318b07a179225320ac,

title = "Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks",

abstract = "The quality of transmission (QoT) estimation of lightpaths (LPs) has both technological and economic significance from the operator{\textquoteright}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.",

keywords = "Generalized SNR, Machine learning, QoT-estimation",

author = "Ihtesham Khan and Muhammad Bilal and Vittorio Curri",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020 ; Conference date: 04-12-2020 Through 06-12-2020",

year = "2022",

doi = "10.1007/978-981-16-5692-7\_9",

language = "English",

isbn = "9789811656910",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "78--87",

editor = "Maode Ma",

booktitle = "Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020",

address = "Germany",

}

Khan, I, Bilal, M & Curri, V 2022, Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks. in M Ma (ed.), Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020. Lecture Notes in Electrical Engineering, vol. 797 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 78-87, 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020, Singapore, Singapore, 4/12/20. https://doi.org/10.1007/978-981-16-5692-7_9

Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks. / Khan, Ihtesham; Bilal, Muhammad; Curri, Vittorio.
Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020. ed. / Maode Ma. Springer Science and Business Media Deutschland GmbH, 2022. p. 78-87 (Lecture Notes in Electrical Engineering; Vol. 797 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Cross-Train

T2 - 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020

AU - Khan, Ihtesham

AU - Bilal, Muhammad

AU - Curri, Vittorio

PY - 2022

Y1 - 2022

N2 - The 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.

AB - The 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.

KW - Generalized SNR

KW - Machine learning

KW - QoT-estimation

UR - https://www.scopus.com/pages/publications/85115248976

U2 - 10.1007/978-981-16-5692-7_9

DO - 10.1007/978-981-16-5692-7_9

M3 - Conference contribution

AN - SCOPUS:85115248976

SN - 9789811656910

T3 - Lecture Notes in Electrical Engineering

SP - 78

EP - 87

BT - Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020

A2 - Ma, Maode

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 4 December 2020 through 6 December 2020

ER -

Khan I, Bilal M, Curri V. Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks. In Ma M, editor, Proceedings of the 4th International Conference on Telecommunications and Communication Engineering, ICTCE 2020. Springer Science and Business Media Deutschland GmbH. 2022. p. 78-87. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-16-5692-7_9

Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this