Physical-Layer-Aware Performance Evaluation of SDM Networks Based on SMF Bundles, MCFs, and FMFs

Shariati, Behnam; Mastropaolo, Antonia; Diamantopoulos, Nikolaos-Panteleimon; Rivas-Moscoso, Jose Manuel; Klonidis, Dimitrios; Tomkos, Ioannis

doi:10.1364/jocn.10.000712

Cited by 29 publications

(41 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ground truth y s was generated by the Q-factor model [1]. Q-threshold was set to a corresponding BER of 10 −3 [1]. As shown in Table 1, 3 datasets D were created, that differ in their size.…”

Section: Dataset Generation Model Training and Accuracymentioning

confidence: 99%

“…Traditional network planning tools estimate Quality-of-Transmission (QoT) with static Q-factor models [1] which are functions of the physical layer impairments (PLIs). The calculation of these PLIs requires complex computations, timeconsuming measurements, and expensive equipment that take considerable human effort and lack self-adaptivenes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for QoT Estimation of Unseen Optical Network States

Panayiotou¹,

Savva²,

Shariati³

et al. 2019

Optical Fiber Communication Conference (OFC) 2019

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Dataset Generation Model Training and Accuracymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning for QoT Estimation of Unseen Optical Network States

Panayiotou¹,

Savva²,

Shariati³

et al. 2019

Optical Fiber Communication Conference (OFC) 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The single-slice QoT-aware RSA heuristic, integrating only the QoT model of the lowest BER requirement, is used as a benchmark. The reader should note that in the literature, existing QoT-aware RSA algorithms consider only a single BER requirement [28][29][30]. In this work, we show that the multi-slice QoT-aware RSA outperforms the state-of-the-art single-slice QoT-aware RSA approach by avoiding slice/connection overprovisioning, an indicator that the diverse BER requirements must be specifically taken into account during slice/connection provisioning.…”

Section: Research Articlementioning

confidence: 72%

“…Dijkstra's shortest path algorithm [43] was used for the R sub-problem, and the first-fit technique was utilized for the SA sub-problem, while at the same time ensuring that all three SA constraints are met. For each lightpath provisioned, the Q-tool (described in [28]) was used for estimating the ground truth values (i.e., BER n ). In practical implementations, the BER ground truth values can be extracted trough OPM at the receivers [11].…”

Section: Dataset Generation and Model Training And Evaluation A Datamentioning

confidence: 99%

Decentralizing machine-learning-based QoT estimation for sliceable optical networks

Panayiotou

Savva

Tomkos

et al. 2020

J. Opt. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

Dynamic network slicing has emerged as a promising and fundamental framework for meeting 5G's diverse use cases. As machine learning (ML) is expected to play a pivotal role in the efficient control and management of these networks, in this work, we examine the ML-based quality-of-transmission (QoT) estimation problem under the dynamic network slicing context, where each slice has to meet a different QoT requirement. Specifically, we examine ML-based QoT frameworks with the aim of finding QoT model/s that are fine-tuned according to the diverse QoT requirements. Centralized and distributed frameworks are examined and compared according to their model accuracy, routing and spectrum allocation (RSA) accuracy, and CPU (training time) and RAM (memory) requirements. We show that the distributed QoT models outperform the centralized QoT model in accuracy and CPU usage. The RSA accuracy, i.e., measuring the accuracy of the models with regard to the QoT-aware RSA decisions, is sufficiently high for both frameworks. Regarding the RAM usage, as the distributed framework has to train in parallel several QoT models, it may require higher memory, especially as the number of diverse QoT requirements increases. This memory, however, tends to be reserved for a shorter period of time. Moreover, this work develops a dynamic multi-slice QoT-aware (RSA) framework that integrates the ML-based QoT models. The aim is to examine the network performance when the diverse QoT models are considered, as opposed to the state-of-the-art single-slice QoT-aware RSA approach where all connections/slices are provisioned according to a single QoT requirement. We show that the multi-slice QoT-aware RSA approach significantly improves network performance, a clear indicator that the commonly considered single-slice QoT-aware RSA approach may lead to connection overprovisioning.few years adopted network slicing as an emerging technology and business model [2,3].In general, the implementation of network slicing is conceived as an end-to-end feature spanning over different technology domains. While relevant work focuses mostly on the implementation of network slicing in the radio access network (RAN) segment [1,2,4,5], recent work also focuses on extending the scope of network slicing beyond the RAN to include both mobile and transport (optical) network segments [6][7][8]. In particular, recent work deals with SDN/NFV demonstrations, network orchestration implementations, and traffic demand analysis, towards the vision of end-to-end network slicing. In general, SDN/NFV, network orchestration, and analytics are considered as the key ingredients for successful implementation of end-to-end network slicing [1]. However, regarding the efficient control and management of these slices (i.e., enabling not only their creation but also their 1943-0620/20/070146-17 Journal smart deployment at the right place, at the right time, with optimized resources), little has been done so far.Without doubt, machine learning (ML) will be instrumental in the efficient control an...

show abstract

“…This QAN was designed for resource and cost sharing where the most expensive components, the single photon detectors, were placed in the central location to be shared by multiple users.The full capacity of QKD can be unleashed by incorporating the spatial division multiplexing (SDM) domain on top of the existing wavelength division multiplexing (WDM) layer. SDM is now being considered the route towards capacity upgrade for current core optical communication networks [15,16] and will progressively permeate into the access…”

mentioning

confidence: 99%

Modeling optical fiber space division multiplexed quantum key distribution systems

Ureña¹,

Gasulla²,

Fraile³

et al. 2019

Opt. Express

View full text Add to dashboard Cite

We report a model to evaluate the performance of multiple quantum key distribution (QKD) channel transmission using spatial division multiplexing (SDM) in multicore (MCF) and few-mode fibers (FMF). The model is then used to analyze the feasibility of QKD transmission in 7-core MCFs for two scenarios of practical interest. First for transmission of only QKD channels, the second for simultaneous transmission of QKD and classical channels. In the first case, standard homogeneous MCFs enable transmission distances per core compatible with transmission parameters (distance and net key rate) very close to those of single core singlemode fibers. For the second case, heterogeneous MCFs must be employed to make this option feasible. IntroductionQuantum key distribution (QKD) provides an intrinsically secure way to distribute such secret keys between remote parties [1][2][3]. The secrecy of the keys distributed by QKD is verifiable [4], since it relies upon quantum mechanical principles featuring resilience against an eavesdropper. Early QKD experiments focused upon the feasibility of the technology, starting from proof-of-principle laboratory experiments. Subsequent developments in the field dramatically improved the security, performance, accessibility and reliability of the QKD technology. Its security can be rigorously proven even when implemented with practical components only, such as attenuated lasers [5]. The secure bit rate has been increased by three orders of magnitude to 1 Mb/s over 50 km fiber thanks to the development of efficient QKD protocol [6] and high-speed single photon detectors [7].A second evolution step has been connected to the integration of QKD systems into telecommunication networks. In a first stage, the effort concentrated in the development of backbone and metropolitan QKD network demonstrators to enable multi-user connectivity in Japan [8], the US [9], Europe [10], and China [11,12]. A nodal network of point-to-point (P2P) QKD links can then be used to relay a global key between any two distant locations in the network [8][9][10][11]. Alternative approaches based on active routing of optical signals were reported [12,13]. A second stage has focused on the integration of QKD systems into access networks. Here, a point-to-multiple-point (P2MP) architecture is more suitable to allow simultaneous access by multiple users rather than resorting to P2P QKD links. For instance, researchers at Toshiba demonstrated a quantum access network (QAN) of this type allowing a high-speed detector to be simultaneously used by up to 64 users [14]. This QAN was designed for resource and cost sharing where the most expensive components, the single photon detectors, were placed in the central location to be shared by multiple users.The full capacity of QKD can be unleashed by incorporating the spatial division multiplexing (SDM) domain on top of the existing wavelength division multiplexing (WDM) layer. SDM is now being considered the route towards capacity upgrade for current core optical communication networks [...

show abstract

Physical-Layer-Aware Performance Evaluation of SDM Networks Based on SMF Bundles, MCFs, and FMFs

Cited by 29 publications

References 29 publications

Machine Learning for QoT Estimation of Unseen Optical Network States

Machine Learning for QoT Estimation of Unseen Optical Network States

Decentralizing machine-learning-based QoT estimation for sliceable optical networks

Modeling optical fiber space division multiplexed quantum key distribution systems

Contact Info

Product

Resources

About