Topology-Aware Prediction of Virtual Network Function Resource Requirements

Mijumbi, Rashid; Hasija, Sidhant; Davy, Steven; Davy, Alan; Jennings, Brendan; Boutaba, Raouf

doi:10.1109/tnsm.2017.2666781

Cited by 115 publications

(72 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is specifically well suited for NFV/SDN scenarios, which shall be highly automated to allow zero-touch network operations following DevOps methods [1], [2]. Existing work focuses on, e.g., learning and predicting of service metrics, such as response time and frame rate [12], [13], scaling and resource dimensioning [4] as well as placement decisions [5]. But all of this work relies on custom data sets which might not even be publicly available.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Related Workmentioning

confidence: 99%

“…The full hardware and software specifications of the used testbed are available as part of the SNDZoo repositories 4. Considering configurations, repetitions, and collected metrics results in: 40·20·593=474,400 time series records.…”

mentioning

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

show abstract

“…On one hand, most of works dealing with scaling focus on mechanisms/strategies for virtual resource estimation (e.g., [2]) and allocation (e.g., [3]). The policy-based rules and input data that these proposals use for the scaling operation are not retrieved from an NSD; instead, they are specified manually for every NS.…”

Section: Introductionmentioning

confidence: 99%

Automated Network Service Scaling in NFV: Concepts, Mechanisms and Scaling Workflow

et al. 2018

View full text Add to dashboard Cite

Next-generation systems are anticipated to be digital platforms supporting innovative services with rapidly changing traffic patterns. To cope with this dynamicity in a cost-efficient manner, operators need advanced service management capabilities such as those provided by NFV. NFV enables operators to scale network services with higher granularity and agility than today. For this end, automation is key. In search of this automation, the European Telecommunications Standards Institute (ETSI) has defined a reference NFV framework that make use of model-driven templates called Network Service Descriptors (NSDs) to operate network services through their lifecycle. For the scaling operation, an NSD defines a discrete set of instantiation levels among which a network service instance can be resized throughout its lifecycle. Thus, the design of these levels is key for ensuring an effective scaling. In this article, we provide an overview of the automation of the network service scaling operation in NFV, addressing the options and boundaries introduced by ETSI normative specifications. We start by providing a description of the NSD structure, focusing on how instantiation levels are constructed. For illustrative purposes, we propose an NSD for a representative NS. This NSD includes different instantiation levels that enable different ways to automatically scale this NS. Then, we show the different scaling procedures the NFV framework has available, and how it may automate their triggering. Finally, we propose an ETSI-compliant workflow to describe in detail a representative scaling procedure. This workflow clarifies the interactions and information exchanges between the functional blocks in the NFV framework when performing the scaling operation.

show abstract

“…M ANY network management tools use Linux tools for State Acquisition to acquire inputs for higher-level functions such as network monitoring algorithms [1], service level prediction algorithms [2], [3] and resource allocation routines [4]. Some examples of these acquisition tools include the System Activity Report (SAR) [5], Nagios [6] and top [7] (in association with tools such as netstat and dropwatch).…”

Section: Introductionmentioning

confidence: 99%

“…effects in particular in [15]. For a video and voice resource allocation application the authors of [4] acquired measurements of resource parameters (CPU, RAM, latency and call drops) every 15s from a Clearwater cloud ISM test-bed, using SNMP and Cacti [16] to determine how physical resources could be dynamically allocated to virtualized network functions. More generally, RTCP [17] is commonly used to provide out-of-band statistics for RTP sessions by periodically reporting on packet counts, packet loss, packet delay variation, and round-trip delay time to participants in a streaming multimedia session [18].…”

Section: Introductionmentioning

confidence: 99%

State Acquisition in Computer Networks

Fréin¹

2018

2018 IFIP Networking Conference (IFIP Networking) and Workshops

View full text Add to dashboard Cite

We establish that State Acquisition should be performed in networks at a rate which is consistent with the rate-of-change of the element or service being observed. We demonstrate that many existing monitoring and service-level prediction tools do not acquire network state in an appropriate manner. To address this challenge: (1) we define the rate-ofchange of different applications; (2) we use methods for analysis of unevenly spaced time series, specifically, time series arising from video and voice applications, to estimate the rate-of-change of these services; and finally, (3) we demonstrate how to acquire network state accurately for a number of real-world traces using Greedy Acquisition. The accuracy of State Acquisition is improved when it is performed at a rate which is consistent with its rate-of-change. An improvement in representation accuracy of one order of magnitude is achieved for voice and video streaming applications; this improvement does not incur any additional bandwidth or storage cost.

show abstract

Topology-Aware Prediction of Virtual Network Function Resource Requirements

Cited by 115 publications

References 24 publications

The Softwarised Network Data Zoo

The Softwarised Network Data Zoo

Automated Network Service Scaling in NFV: Concepts, Mechanisms and Scaling Workflow

State Acquisition in Computer Networks

Contact Info

Product

Resources

About