Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]

Rafique, Danish; Velasco, Luis

doi:10.1364/jocn.10.00d126

Cited by 231 publications

(135 citation statements)

References 33 publications

(37 reference statements)

Supporting

Mentioning

132

Contrasting

Unclassified

Order By: Relevance

“…Monitoring heterogeneous network elements (observe) produces huge amounts of metered data containing relevant information about network performance. Monitoring data is then processed by statistical and/or machine learning algorithms (analyze) [6] aiming at detecting and identifying some evidence requiring some further actions to be taken (act). Some examples include the reconfiguration of virtual network topologies following traffic changes [7]- [8] and the dimensioning of next planning steps based on traffic prediction [9]; both require the analysis of monitoring data to model and characterize network traffic.…”

Section: Introductionmentioning

confidence: 99%

CURSA-SQ: A Methodology for Service-Centric Traffic Flow Analysis

Ruiz¹,

Coltraro²,

Velasco³

2018

J. Opt. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

The rapid availability of new services makes that network operators cannot exhaustively test their impact on the network or anticipate any capacity exhaustion. This situation will be worse with the imminent introduction of the 5G technology and the kind of totally new services that it will support. In addition, the increasing complexity of the network makes unreachable analyzing its behavior in front of the specific traffic that needs to be supported, which prevents from training human operators and much less, machine learning algorithms that might automatize network operation. In this paper, we present CURSA-SQ, a methodology to analyze the network behavior when the specific traffic that would be generated by groups of service consumers is injected. CURSA-SQ includes input traffic flow modelling with second and sub-second granularity based on specific service and consumer behaviors, as well as a continuous G/G/1/k queue model based on the logistic function. The methodology allows to accurately study traffic flows at the input and outputs of complex scenarios with multiples queues systems, as well as other metrics such as delays, while showing noticeable scalability. Application use cases include, packet and optical network planning, service introduction assessment, and autonomic networking, just to mention a few.

show abstract

Section: Introductionmentioning

confidence: 99%

CURSA-SQ: A Methodology for Service-Centric Traffic Flow Analysis

Ruiz¹,

Coltraro²,

Velasco³

2018

J. Opt. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this case, data-driven ML methods are essential tools for network planning and management, but these methods should be improved to be cost-effective and reliable for deployment. Several previous review works have provided comprehensive summaries of the applications of ML techniques in optical networks [2,[16][17][18][19]. They discuss the ML-based techniques adopted in various domains and point out many possible directions for the future deployment strategies.…”

Section: Monitoringmentioning

confidence: 99%

AI-Based Modeling and Monitoring Techniques for Future Intelligent Elastic Optical Networks

Liu

Lun

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

With the development of 5G technology, high definition video and internet of things, the capacity demand for optical networks has been increasing dramatically. To fulfill the capacity demand, low-margin optical network is attracting attentions. Therefore, planning tools with higher accuracy are needed and accurate models for quality of transmission (QoT) and impairments are the key elements to achieve this. Moreover, since the margin is low, maintaining the reliability of the optical network is also essential and optical performance monitoring (OPM) is desired. With OPM, controllers can adapt the configuration of the physical layer and detect anomalies. However, considering the heterogeneity of the modern optical network, it is difficult to build such accurate modeling and monitoring tools using traditional analytical methods. Fortunately, data-driven artificial intelligence (AI) provides a promising path. In this paper, we firstly discuss the requirements for adopting AI approaches in optical networks. Then, we review various recent progress of AI-based QoT/impairments modeling and monitoring schemes. We categorize these proposed methods by their functions and summarize advantages and challenges of adopting AI methods for these tasks. We discuss the problems remained for deploying AI-based methods to a practical system and present some possible directions for future investigation.

show abstract

“…In this sense, the article [2] reviews the applications of fundamental ML concepts on communication networks, and presents a case study which aims at detecting abnormal elements in a multi-layer real network using unsupervised ML. Another paper [3] reviews the well-known ML concepts along with their applications in the context of optical networks, and discusses different aspects of ML implementations such as algorithm choice, data and model management strategies, and integration into existing network control and management tools. The survey paper [4] provides an overview of deep learning architectures and algorithms for controlling network traffic, and surveys the state-of-the-art ML and new deep learning researches in networking related areas.…”

Section: A Related Workmentioning

confidence: 99%

A Machine Learning Based Management System for Network Services

Türk¹,

Zeydan²,

Bilgin³

2019

2019 International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

View full text Add to dashboard Cite

Providing high quality and uninterrupted network service is becoming crucial for service providers. In this paper, we present an approach to quantify and indicate service quality based on the topology state transitions from the perspective of network service provider. Building our model as a Finite State Machine (FSM), we show novel application of machine learning (ML) classification algorithms to classify appropriate states for undefined input alphabets in FSM. In other words, we implement ML algorithms to extract both service states and possible root causes of service degradation only from measured certain Key Performance Indicator (KPI) values that are observed directly through network elements. We have implemented our network topology state classification approach using the dataset obtained in Graphical Network Simulator 3 (GNS3) simulation environment, and performed measurements to evaluate classification accuracy of different algorithms. Additionally, we have identified priority of relevant KPIs impacting the service quality. Our results indicate that network topology state changes can be classified up to 88% accuracy and F1 scores using ensemble learning methods such as Gradient Boosting Classifiers.

show abstract

Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]

Cited by 231 publications

References 33 publications

CURSA-SQ: A Methodology for Service-Centric Traffic Flow Analysis

CURSA-SQ: A Methodology for Service-Centric Traffic Flow Analysis

AI-Based Modeling and Monitoring Techniques for Future Intelligent Elastic Optical Networks

A Machine Learning Based Management System for Network Services

Contact Info

Product

Resources

About