Towards Black-Box Anomaly Detection in Virtual Network Functions

Sauvanaud, Carla; Lazri, Kahina; Kaâniche, Mohamed; Kanoun, Karama

doi:10.1109/dsn-w.2016.17

Cited by 11 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These two works, only provide detection solutions without fault type identification and localization. One of the non-statistical data driven approaches uses fault injection techniques to generate data and applies a Random Forest (RF) algorithm [7] to detect malfunctions and localize the root cause (one task at a time) in the context of NFV. Although these two approaches [6] [7] achieve good level of accuracy, they do not provide any complexity analysis while using a high number of metrics.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Approaches to Early Fault Detection and Identification in NFV Architectures

Elmajed

Aghasaryan

Fabre

2020

2020 6th IEEE Conference on Network Softwarization (NetSoft)

View full text Add to dashboard Cite

Virtualization technologies become pervasive in networking, as a way to better exploit hardware capabilities and to quickly deploy tailored networking solutions for customers. But these new programmability abilities of networks also come with new management challenges: it is critical to quickly detect performance degradation, before they impact Quality of Service (QoS) or produce outages and alarms, as this takes part in the closed loop that adapts resources to services. This paper addresses the early detection, localization and identification of faults, before alarms are produced. We rely on the abundance of metrics available on virtualized networks, and explore various data preprocessing and classification techniques. As all Machine Learning approaches must be fed with large datasets, we turn to our advantage the softwarization of networks: one can easily deploy in a cloud the very same software that is used in production, and analyze its behaviour under stress, by fault injection.

show abstract

Section: Related Workmentioning

confidence: 99%

Machine Learning Approaches to Early Fault Detection and Identification in NFV Architectures

Elmajed

Aghasaryan

Fabre

2020

2020 6th IEEE Conference on Network Softwarization (NetSoft)

View full text Add to dashboard Cite

show abstract

“…They study several use-cases and show the applicability and benefits of adopting the machine learning paradigm to the networking field. Following this trend, anomaly detection in the cloud with machine learning is studied in [10], VNF anomaly detection in [11], traffic control with deep learning in [12], and identification of host roles with supervised learning with sFlow in [13].…”

Section: Related Workmentioning

confidence: 99%

Tuning optimal traffic measurement parameters in virtual networks with machine learning

Gogunska¹,

Barakat²,

Urvoy-Keller

2019

2019 IEEE 8th International Conference on Cloud Networking (CloudNet)

View full text Add to dashboard Cite

With the increasing popularity of cloud networking and the widespread usage of virtualization as a way to offer flexible and virtual network and computing resources, it becomes more and more complex to monitor this new virtual environment. Yet, monitoring remains crucial for network troubleshooting and analysis. Controlling the measurement footprint in the virtual network is one of the main priorities in the process of monitoring as resources are shared between the compute nodes of tenants and the measurement process itself. In this paper, first, we assess the capability of machine learning to predict measurement impact on the ongoing traffic between virtual machines; second, we propose a data-driven solution that is able to provide optimal monitoring parameters for virtual network measurement with minimum traffic interference.

show abstract

“…Carla Sauvanaud et al in [7] used tree-based algorithm, random forests for anomaly detection on VNF monitoring data. They presented results evaluating receiver operating characteristics (ROC) and the precision call (PR).…”

Section: Anomaly Detection Techniquesmentioning

confidence: 99%

Anomaly Detection in NFV Using Tree-Based Unsupervised Learning Method

Girish¹

2019

Preprint

View full text Add to dashboard Cite

With the increased adoption of virtualized NFs in data center, it is crucial to address some of the challenges such as performance and availability of the applications in virtualized network environment. The normal operation of the network can be analyzed with respect to the usage of various resources like, CPU, memory, network and disk. Inefficient usage or over usage of these resources leads to anomalous behavior. Anomalies are often preceded by faults. It is important to detect anomalies before they occur. The detected anomalies can be used for corrective and optimization actions. This paper presents that; unsupervised machine learning algorithm performs better compared to supervised machine learning algorithms in detecting anomalies. Here we use isolation forest algorithm on time series dataset, which is collected using monitoring agent collectd. Stress is induced to the computer using traffic monitoring generator and stress-ng. The results show that isolation forest algorithm gives better performance in anomaly detection with good anomaly score.

show abstract

Towards Black-Box Anomaly Detection in Virtual Network Functions

Cited by 11 publications

References 7 publications

Machine Learning Approaches to Early Fault Detection and Identification in NFV Architectures

Machine Learning Approaches to Early Fault Detection and Identification in NFV Architectures

Tuning optimal traffic measurement parameters in virtual networks with machine learning

Anomaly Detection in NFV Using Tree-Based Unsupervised Learning Method

Contact Info

Product

Resources

About