A Cognitive System for Fast Quality of Transmission Estimation in Core Optical Networks

Jiménez, Tamara; Aguado, Juan Carlos; Miguel, Ignacio de; Durán, Ramón J.; Fernández, Natalia; Angelou, M.; Sánchez, David; Merayo, N.; Fernández, Patricia; Atallah, N.; Lorenzo, Rubén M.; Tomkos, Ioannis; Abril, Evaristo J.

doi:10.1364/ofc.2012.ow3a.5

Cited by 10 publications

(21 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1(b) shows the percentage of successful classifications of lightpaths into high or low QoT categories when using different techniques such as a naive Bayes classifier, different types of decision trees, and a case-based reasoning (CBR) approach for the 34-node GÉANT2 dispersion-compensated network, equipped with 64 wavelengths. As shown in the figure, and as demonstrated in [8], the CBR approach achieves more than 99% successful classifications of optical connections, and is much faster for on-line operation than an existing non-cognitive approach, thus demonstrating the advantages of cognition. A second example of the potential of cognition in optical networks is related to the virtual topology design module.…”

Section: Applications Of Cognition In Optical Networkmentioning

confidence: 78%

Cognitive Dynamic Optical Networks

Miguel

Durán

Lorenzo

et al. 2013

Optical Fiber Communication Conference/National Fiber Optic Engineers Conference 2013

View full text Add to dashboard Cite

show abstract

Section: Applications Of Cognition In Optical Networkmentioning

confidence: 78%

Cognitive Dynamic Optical Networks

Miguel

Durán

Lorenzo

et al. 2013

Optical Fiber Communication Conference/National Fiber Optic Engineers Conference 2013

View full text Add to dashboard Cite

show abstract

“…2), but also to a great reduction in the computing time (around three orders of magnitude) when compared to a previous tool for QoT assessment which does not employ cognition [20].…”

Section: Fig 1 Main Elements Of the Chron Approachmentioning

confidence: 97%

“…In the framework of this architecture, the advantages of cognition have already been demonstrated in a number of scenarios, such as on quickly and effectively assessing whether an optical connection (i.e., a lightpath) satisfies QoT requirements [20], or on determining which set of connections should be established on an optical network (i.e., the so-called virtual topology) in order to support the traffic load while satisfying QoT requirements and minimizing energy consumption and congestion [21].…”

Section: Fig 1 Main Elements Of the Chron Approachmentioning

confidence: 99%

Next Generation Flexible and Cognitive Heterogeneous Optical Networks

Tomkos

Angelou

Barroso

et al. 2012

The Future Internet

View full text Add to dashboard Cite

Abstract. Optical networking is the cornerstone of the Future Internet as it provides the physical infrastructure of the core backbone networks. Recent developments have enabled much better quality of service/experience for the end users, enabled through the much higher capacities that can be supported. Furthermore, optical networking developments facilitate the reduction of complexity of operations at the IP layer and therefore reduce the latency of the connections and the expenditures to deploy and operate the networks. New research directions in optical networking promise to further advance the capabilities of the Future Internet. In this book chapter, we highlight the latest activities of the optical networking community and in particular what has been the focus of EU funded research. The concepts of flexible and cognitive optical networks are introduced and their key expected benefits are highlighted. The overall framework envisioned for the future cognitive flexible optical networks are introduced and recent developments are presented.

show abstract

“…The first one, referred as R-CBR (Regular CBR), is a cognitive QoT estimator that does not optimize the KB prior to online operation (i.e., it operates as described in Section II-A) [11]. The second one, called FixE-CBR (Fixed Error CBR), is a cognitive estimator which applies learning and forgetting techniques in order to perform an off-line optimization of the KB with a fixed permitted error [12].…”

Section: B Optimization Of the Kbmentioning

confidence: 99%

“…First of all, in Section II, we explain the fundamentals of the cognitive QoT estimator, which was introduced in [11], and discuss how the underlying knowledge base can be optimized by means of learning and forgetting techniques [12]. Then in Section III, the performance of the cognitive QoT estimator is analyzed by means of a simulation study on a long-haul and in an ultralong haul network, with different numbers of nodes, in order to analyze potential scalability issues.…”

Section: Introductionmentioning

confidence: 99%

A Cognitive Quality of Transmission Estimator for Core Optical Networks

Jiménez

Aguado

Miguel

et al. 2013

J. Lightwave Technol.

View full text Add to dashboard Cite

We propose a cognitive Quality of Transmission (QoT) estimator for classifying lightpaths into high or low quality categories in impairment-aware wavelength-routed optical networks. The technique is based on Case-Based Reasoning (CBR), an artificial intelligence technique which solves new problems by exploiting previous experiences, which are stored on a knowledge base. We also show that by including learning and forgetting techniques, the underlying knowledge base can be optimized, thus leading to a significant reduction on the computing time for on-line operation. The performance of the cognitive estimator is evaluated in a long haul and in an ultra-long haul network, and we demonstrate that it achieves more than 98% successful classifications, and that it is up to four orders of magnitude faster when compared with a non-cognitive QoT estimator, the Q-Tool.Index Terms-Case-based reasoning (CBR), cognitive networks, impairment-aware networking, quality of transmission (QoT), wavelength-routed optical network (WRON).

show abstract

A Cognitive System for Fast Quality of Transmission Estimation in Core Optical Networks

Cited by 10 publications

References 3 publications

Cognitive Dynamic Optical Networks

Cognitive Dynamic Optical Networks

Next Generation Flexible and Cognitive Heterogeneous Optical Networks

A Cognitive Quality of Transmission Estimator for Core Optical Networks

Contact Info

Product

Resources

About