NFV-Inspector: A Systematic Approach to Profile and Analyze Virtual Network Functions

Khan, Michel Gokan; Bastani, Saeed; Taheri, Javid; Kassler, Andreas; Deng, Shuiguang

doi:10.1109/cloudnet.2018.8549333

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [21], log processing-based approaches are proposed to predict faulty network conditions. In [22], authors propose to profile Network Function Virtualization (NFV) deployments by classifying Virtual Network Function (VNF) resource characteristics and correlating their performance indicators to optimize the resource allocation, and VNF placement policies under the context of VNF behavior uncertainty. Similar efforts on resource allocation optimization based on VNF performance profiling are presented in [23]- [25].…”

Section: Resultsmentioning

confidence: 99%

Cloud Native Applications Profiling using a Graph Neural Networks Approach

Boukhtouta

Madi

Pourzandi

et al. 2022

2022 IEEE Future Networks World Forum (FNWF)

View full text Add to dashboard Cite

The convergence of Telecommunication and industry operational networks towards cloud native applications has enabled the idea to integrate protection layers to harden security posture and management of cloud native based deployments. In this paper, we propose a data-driven approach to support detection of anomalies in cloud native application based on a graph neural network. The essence of the profiling relies on capturing interactions between different perspectives in cloud native applications through a network dependency graph and transforming it to a computational graph neural network. The latter is used to profile different deployed assets like micro-service types, workloads' namespaces, worker machines, management and orchestration machines as well as clusters. As a first phase of the profiling, we consider a fine-grained profiling on microservice types with an emphasis on network traffic indicators. These indicators are collected on distributed Kubernetes (K8S) deployment premises. Experimental results shows good trade-off in terms of accuracy and recall with respect to micro-service types profiling (around 96%). In addition, we used predictions entropy scores to infer anomalies in testing data. These scores allow to segregate between benign and anomalous graphs, where we identified 19 out of 23 anomalies. Moreover, by using entropy scores, we can conduct a root cause analysis to infer problematic micro-services.

show abstract

Section: Resultsmentioning

confidence: 99%

Cloud Native Applications Profiling using a Graph Neural Networks Approach

Boukhtouta

Madi

Pourzandi

et al. 2022

2022 IEEE Future Networks World Forum (FNWF)

View full text Add to dashboard Cite

show abstract

“…Resource management in NFV is a challenging problem considering the inadequacy of the resources allocated to VNFs [12]. The optimal placement and chaining of VNFs has been extensively investigated [13,[30][31][32][33][34] when the network is static. However, the dynamic real environment calls for algorithms able to continuously scale the amount of resources allocated to VNFs to process the uctuating tra c passing through them (for example lter the tra c or detect intrusion).…”

Section: B Online Vnf Deploymentmentioning

confidence: 99%

Precise Dynamic Resource Allocation for Virtualised Network Functions

Chapanduka

Olwal

Kurien

2023

Preprint

View full text Add to dashboard Cite

The chaining and optimal placement of Virtual Network Functions (VNFs) in a static network has been extensively discussed and investigated. However a key trend of current network evolution is towards network softwarisation which is targeted at addressing the exponential growth in traffic demand that is causing progressive congestions in today’s Communication Service Providers (CSPs) networks. In network softwarisation, VNFs are being deployed as part of complex network service chains, containing multiple VNFs distributed across multiple points of presence (PoPs). VNFs are instantiated and resources have to be precisely allocated dynamically on-demand otherwise this can lead easily to either bad quality of service or waste of resources if too few or too many are allocated. To mitigate the challenges, we propose a Precise Dynamic Resource Allocation (PDRA) model which is a machine learning-based dynamic resource allocation targeted at adequately allocating VNF resources. The model has the following components: VNF profiling, VNF performance measurement, machine learning training and VNF auto scaling and placement. In comparison to standard fixed resource allocation, our model significantly addresses VNF under and over allocation of resources resulting in low latency and improved service quality.

show abstract

“…In [56], the authors showed that the container-based microservices architecture brings challenges to service performance and resource management due to the additional granularity compared to VM-based microservices. The performance and the reliability of the container-based microservices were constrained by QoS metrics (i.e., latency, serving throughput, request rate) which were collected by NFV-Inspector [57]. They used the machine learning approach to estimate the relationship between the QoS and microservice resource configuration, then the Machine Learning (ML) model was used to predict the required resources to set up a productive environment and the capability of a productive environment.…”

Section: Prometheusmentioning

confidence: 99%

“…[3], [49], [66], [57] investigated in the literature review, the list of information collected that is most useful includes: : (i) the latency for Pods initialization, (ii) the host's network device name and speed, (iii) the network throughput during the sample period, (iv) the CPU temperature, (v) the CPU and memory utilization, (vi) the HTTP request delay, (vii) the HTTP request error rate, (viii) the total number of HTTP request and its increasing rate. By leveraging the powerful PromQL built-in functions and aggregate operations, it becomes possible to calculate the traffic pattern and predict the trends in real-time.…”

Section: Deploying the Prometheus Monitoring Systemmentioning

confidence: 99%

Design and Implementation of a Reliable Container-based Service Function Chaining Testbed in Cloud-native System: An Open Source Approach

Wang¹

View full text Add to dashboard Cite

Academia has been moving attention from Virtual Network Function (VNF) to Cloudnative Network Function (CNF) since cloudification has brought the Network Function Virtualization (NFV) to an advanced level. It has already been demonstrated that cloud-native technology brings high flexibility and efficiency to large-scale network service deployment compared to the traditional VNF with Virtual Machines (VMs). However, more work is needed to provide a flexible and reliable Service Function Chaining (SFC) development solution. This thesis proposes a solution to dynamically deploy reliable SFCs consisting of multiple CNFs in a multi-node Kubernetes cluster using Network Service Mesh (NSM). Further, hardware and network usage are presented with the support of an open-source monitoring system, Prometheus, to help the network operator understand the deployed SFC. Additionally, the performance and limitations of this approach are analyzed and presented. i VM Virtual Machines VNF Virtual Network Function VPP Vector Packet Processing V-wire Virtual Wire

show abstract

NFV-Inspector: A Systematic Approach to Profile and Analyze Virtual Network Functions

Cited by 6 publications

References 12 publications

Cloud Native Applications Profiling using a Graph Neural Networks Approach

Cloud Native Applications Profiling using a Graph Neural Networks Approach

Precise Dynamic Resource Allocation for Virtualised Network Functions

Design and Implementation of a Reliable Container-based Service Function Chaining Testbed in Cloud-native System: An Open Source Approach

Contact Info

Product

Resources

About