Learning from Network Device Statistics

Stadler, Rolf; Pasquini, Rafael; Fodor, Viktória

doi:10.1007/s10922-017-9426-z

Cited by 21 publications

(39 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning (ML) techniques are starting to be applied to different aspects of the orchestration process in the cloud, such as data centre scheduling [31,57,104], IaaS instance selection [134], optimising resource scalability [35,25,21], network flow classification [172,158], network performance prediction [148], and software defect classification [115]. When fed with the enormous Predictive resource estimation [25,21] Predictive scheduling [31] Delegation, asymptotic deployment [121,20] Data access prediction Workflow delegation/handover -…”

Section: Learning To Orchestratementioning

confidence: 99%

Research challenges in nextgen service orchestration

Vaquero

Cuadrado

Elkhatib

et al. 2019

Future Generation Computer Systems

View full text Add to dashboard Cite

Fog/edge computing, function as a service, and programmable infrastructures, like software-defined networking or network function virtualisation, are becoming ubiquitously used in modern Information Technology infrastructures. These technologies change the characteristics and capabilities of the underlying computational substrate where services run (e.g. higher volatility, scarcer computational power, or programmability). As a consequence, the nature of the services that can be run on them changes too (smaller codebases, more fragmented state, etc.). These changes bring new requirements for service orchestrators, which need to evolve so as to support new scenarios where a close interaction between service and infrastructure becomes essential to deliver a seamless user experience. Here, we present the challenges brought forward by this new breed of technologies and where current orchestration techniques stand with regards to the new challenges. We also present a set of promising technologies that can help tame this brave new world.

show abstract

Section: Learning To Orchestratementioning

confidence: 99%

Research challenges in nextgen service orchestration

Vaquero

Cuadrado

Elkhatib

et al. 2019

Future Generation Computer Systems

View full text Add to dashboard Cite

show abstract

“…In [96], port and flow statistics are polled from all networks switches. Similarly did authors in [155], [158], they periodically collect port statistic from all network switches.…”

Section: ) From Part Vs All Elementsmentioning

confidence: 99%

“…The authors in [155], [158] estimated end-to-end service metrics based on statistics collected from the network (i.e., port-based) and back-end clusters (i.e., the infrastructure of video streaming service). It is expected that degradation on the infrastructure will affect the end user.…”

Section: ) Prediction Of Qosmentioning

confidence: 99%

“…Analysis and Plan functions resemble the brain and muscles of the autonomic QoS management and ML can add more intelligence in their functionality. For instance, patterns of service degradation can be detected using such techniques if well-trained models are used in conjunction with collected switches statistics [155].…”

Section: B Machine Learning Incorporation In Qos Managementmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Autonomic Provisioning and Management of QoS in SDN Networks

BinSahaq

Sheltami

2019

IEEE Access

View full text Add to dashboard Cite

In today's Internet, killer network services and applications, such as video and audio streaming, network storage, and online video games, are pushing the network infrastructure resources to the edge. By design and for the most part, the Internet is the best offer delivery ecosystem with little or no endto-end quality-of-service (QoS) guarantees. Even, frameworks, such as IntServ and DiffServ that were designed and implemented to provide QoS guarantees, still fail to solve this problem at a wide scale. Software-defined networking (SDN) is a fast emerging networking paradigm that promises to provide endto-end QoS guaranteeing by offering greater network flexibility, abstraction, control, and programmability to network resources. In this paper, we review, survey, and discuss the current state of the art on QoS provisioning in the area of SDN, with respect to applying the concept of autonomic computing (AC) to automatically support, provision, monitor, and maintain QoS requirements. This paper includes in-depth classification, taxonomy, and comparative analysis for the autonomic-based QoS provisioning in accordance with the famous influential and widely adopted the monitor-analyze-plan-execute-knowledge (MAPE-K) IBM architectural model for autonomic computing.

show abstract

“…But all of this work relies on custom data sets which might not even be publicly available. The available public data sets, such as [12], are however not available at a common repository and thus are often hard to find. Our work improves this situation by offering a common repository to host and share data sets focusing on performance measurements of softwarised networks as well as the involved arXiv:1905.04962v2 [cs.NI] 6 Aug 2019 P R E P R I N T platforms and components.…”

Section: Related Workmentioning

confidence: 99%

The Softwarised Network Data Zoo

Peuster

Schneider

Karl

2019

2019 15th International Conference on Network and Service Management (CNSM)

View full text Add to dashboard Cite

More and more management and orchestration approaches for (software) networks are based on machine learning paradigms and solutions. These approaches depend not only on their program code to operate properly, but also require enough input data to train their internal models. However, such training data is barely available for the software networking domain and most presented solutions rely on their own, sometimes not even published, data sets. This makes it hard, or even infeasible, to reproduce and compare many of the existing solutions. As a result, it ultimately slows down the adoption of machine learning approaches in softwarised networks.To this end, we introduce the "softwarised network data zoo" (SNDZoo), an open collection of software networking data sets aiming to streamline and ease machine learning research in the software networking domain. We present a general methodology to collect, archive, and publish those data sets for use by other researches and, as an example, eight initial data sets, focusing on the performance of virtualised network functions. 1

show abstract

Learning from Network Device Statistics

Cited by 21 publications

References 23 publications

Research challenges in nextgen service orchestration

Research challenges in nextgen service orchestration

A Survey on Autonomic Provisioning and Management of QoS in SDN Networks

The Softwarised Network Data Zoo

Contact Info

Product

Resources

About