Machine Learning for Spectrum Defragmentation in Space-Division Multiplexing Elastic Optical Networks

Trindade, Silvana; Fonseca, Nelson L. S. da

doi:10.1109/mnet.011.2000367

Cited by 14 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning techniques have recently found a useful application in SD as well. An unsupervised machine learning technique for rearranging the fragmented spectrum based on lightpath clustering was presented in [17]. In [18], Elman neural networks were used to forecast traffic demands, and the spectrum was allocated using a two-dimensional rectangular packing model that reduces unnecessary fragmentation.…”

Section: Related Workmentioning

confidence: 99%

DeepDefrag: a deep reinforcement learning framework for spectrum defragmentation

Etezadi¹,

Natalino²,

Diaz³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>An exponential growth of bandwidth demand, spurred by emerging network services, often with diverse characteristics and stringent performance requirements, drive the need for more dynamic operation of optical networks, efficient use of spectral resources, and automation. Spectrum fragmentation is one of the main challenges of dynamic, resource-efficient Elastic Optical Networks (EONs). Fragmented, stranded spectrum slots lead to poor resource utilization and increase the blocking probability of incoming service requests. Conventional approaches for Spectrum Defragmentation (SD) apply various criteria to decide when, and which portion of the spectrum to defragment. However, these polices often address only a subset of tasks related to defragmentation, are not adaptable, and have limited automation potential. To address these issues, we propose DeepDefrag, a novel framework based on reinforcement learning that addresses the main aspects of the SD process: determining when to perform defragmentation, which connections to reconfigure, and which part of the spectrum to reallocate them to. DeepDefrag outperforms the well-known Oldest-First FirstFit (OF-FF) defragmentation heuristic, substantially reducing blocking probability and defragmentation overhead.</p>

show abstract

Section: Related Workmentioning

confidence: 99%

DeepDefrag: a deep reinforcement learning framework for spectrum defragmentation

Etezadi¹,

Natalino²,

Diaz³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In References [ 24 , 25 ], the authors use machine learning to handle the spectrum fragmentation problem. In Reference [ 24 ], the authors employed a shortest path algorithm and reinforcement learning to cope with spectrum fragmentation and energy consumption in elastic optical networks based on single-core fiber [ 24 ].…”

Section: Related Workmentioning

confidence: 99%

“…The authors also proposed a new network architecture composed of a virtual network layer, network container layer, and physical network layer. Unsupervised learning algorithm is employed in Reference [ 25 ] to handle spectrum fragmentation in EON-SDM networks. When the fragmentation ratio reaches a limit, the spectrum is defragmented.…”

Section: Related Workmentioning

confidence: 99%

Cognitive Control-Loop for Elastic Optical Networks with Space-Division Multiplexing

Trindade

Torres

Zhu

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

This paper introduces a new solution to improve network performance by decreasing spectrum fragmentation, crosstalk interference, blocking of virtual networks, cost, and link load imbalance. These problems degrade the performance of Elastic Optical Networks with Space-Division Multiplexing. The proposed solution, called Cognitive control loop (CO-OP), is capable of identifying a set of problems and creating plans to mitigate these problems. The CO-OP comprises four functions that employ learning algorithms to identify problems and plan a series of actions to reduce or eliminate them. The results show that the CO-OP can effectively decrease up to 30% the blocking of requests and up to 50% the crosstalk occurrence compared to existing algorithms.

show abstract

“…Redes neurais artificiais vem ganhando cada vez mais espaço na literatura devido a sua capacidade de autoaprendizagem e aplicabilidade em diversos problemas [Khokhar et al 2015], tais como processar sinais de áudio, fala, conteúdos visuais (imagens e vídeos) e textuais. No contexto das redes ópticas elásticas, diferentes autores vem propondo aplicações das redes neurais nos diversos problemas encontrados nesse tipo de rede, tais como: roteamento, desfragmentação, realocação de circuitos, escolha do tamanho da banda de guarda e etc [Troia et al 2018, Trindade and da Fonseca 2021, Rodrigues et al 2020.…”

Section: Redes Neurais Artificiaisunclassified

IRON: uma abordagem inteligente para roteamento em redes ópticas elásticas

Monteiro¹,

Soares²

2021

Anais Do XXXIX Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2021)

View full text Add to dashboard Cite

As redes ópticas elásticas compõem uma infraestrutura de rede capaz de suportar a grande demanda de tráfego de dados da Internet. Um dos principais problemas que devem ser solucionados para garantir o bom funcionamento deste tipo de rede é o chamado Routing, Modulation Level and Spectrum Assignment (RMLSA). Este artigo foca em uma nova solução para o problema de roteamento. A nova solução utiliza uma rede neural Multi Layer Perceptron e é chamada de Intelligent Routing for Optical Networks (IRON). A solução é comparada com o algoritmo Complete Sharing em dois cenários diferentes utilizando as topologias Cost239 e Pan-European. O algoritmo IRON obteve uma redução na probabilidade de bloqueio de banda de aproximadamente 28,59% e 21,83% em relação ao Complete Sharing nas topologias Cost239 e Pan-European respectivamente.

show abstract

Machine Learning for Spectrum Defragmentation in Space-Division Multiplexing Elastic Optical Networks

Cited by 14 publications

References 14 publications

DeepDefrag: a deep reinforcement learning framework for spectrum defragmentation

DeepDefrag: a deep reinforcement learning framework for spectrum defragmentation

Cognitive Control-Loop for Elastic Optical Networks with Space-Division Multiplexing

IRON: uma abordagem inteligente para roteamento em redes ópticas elásticas

Contact Info

Product

Resources

About