2020 IEEE Wireless Communications and Networking Conference (WCNC) 2020
DOI: 10.1109/wcnc45663.2020.9120635
|View full text |Cite
|
Sign up to set email alerts
|

Root Cause Analysis of Noisy Neighbors in a Virtualized Infrastructure

Abstract: This paper proposes a model to identify the noise source in a virtualized infrastructure. This phenomenon appears when network functions running under virtual machines that are deployed on the same physical server compete for physical resources. First, an anomaly detection model is proposed to identify the machines that are in an abnormal state in the infrastructure by performing an unsupervised learning. An investigation of the root cause is later achieved by searching how anomalies are propagated in the syst… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(4 citation statements)
references
References 10 publications
0
4
0
Order By: Relevance
“…The most common method consists of the employment of a Cloud Computing infrastructure to deploy a NN scenario. Over such infrastructure, several VMs are deployed on this infrastructure: one running the evaluated VNF and another one running a "noisy" process, which is a highconsumption process that demands a large number of CPU resources ( [22]). Since the assignment of resources is dynamic, the VMs that contain the "noisy" process will make use of most of the available resources and cause a NN behaviour.…”
Section: State Of the Artmentioning
confidence: 99%
See 2 more Smart Citations
“…The most common method consists of the employment of a Cloud Computing infrastructure to deploy a NN scenario. Over such infrastructure, several VMs are deployed on this infrastructure: one running the evaluated VNF and another one running a "noisy" process, which is a highconsumption process that demands a large number of CPU resources ( [22]). Since the assignment of resources is dynamic, the VMs that contain the "noisy" process will make use of most of the available resources and cause a NN behaviour.…”
Section: State Of the Artmentioning
confidence: 99%
“…Numerous studies have been conducted on the identification of this entity through the application of techniques based on artificial intelligence, supported by Machine Learning (ML) models, such as Support Vector Machine (SVM) and Random Forest (RF), addressed in [13] and Deep Learning, such as Convolutional Neural Networks (CNNs), applied in [27]. Other works focus on the evaluation of their possible causes (Root Cause Analysis, RCA) [22]. On the other hand, the results in [28], [7] address the assessment and management of the NN problem.…”
Section: State Of the Artmentioning
confidence: 99%
See 1 more Smart Citation
“…The proposed approach considers a two-level availability model where (i) the low level considers the network topology structure and NFV connectivity requirements through the definition of the system structure function based on minimal-cut sets and (ii) the higher level examines dynamics and failure modes of network and NFV elements through stochastic activity networks. Bouattour et al propose,in [29] a model to identify the noise source in a virtualized infrastructure. First, an anomaly detection model based on unsupervised learning is proposed to identify the machines that are in an abnormal state in the infrastructure.…”
Section: Related Workmentioning
confidence: 99%