Performance Modeling of SDN with NFV under or aside the Controller

Fahmin, Ahmed; Lai, Yuan‐Cheng; Hossain, S.; Lin, Ying-Dar; Saha, Dipon

doi:10.1109/ficloudw.2017.76

Cited by 19 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fahmin, Lai, Hossain, Lin and Saha in [17] presented the performance modeling of SDN with network virtualisation function (NFV) under or aside the controller, which are the different methods of combining SDN with NFV; using M/M/1 queueing model. Fahmin et al used queueing theory to develop mathematical models for both scenarios resulting to queueing networks which were then analysed.…”

Section: A Modelling Based On M/m/1 Distributionmentioning

confidence: 99%

Resilience Analysis of Software-Defined Networks Using Queueing Networks

Nweke

Wolthusen

2020

2020 International Conference on Computing, Networking and Communications (ICNC)

View full text Add to dashboard Cite

Software-Defined Networks (SDN) are being adopted widely and are also likely to be deployed as the infrastructure of systems with critical real-time properties such as Industrial Control Systems (ICS). This raises the question of what security and performance guarantees can be given for the data plane of such critical systems and whether any control plane actions will adversely affect these guarantees, particularly for quality of service in real-time systems. In this paper we study the existing literature on the analysis of SDN using queueing networks and show ways in which models need to be extended to study attacks that are based on arrival rates and service time distributions of flows in SDN.

show abstract

Section: A Modelling Based On M/m/1 Distributionmentioning

confidence: 99%

Resilience Analysis of Software-Defined Networks Using Queueing Networks

Nweke

Wolthusen

2020

2020 International Conference on Computing, Networking and Communications (ICNC)

View full text Add to dashboard Cite

show abstract

“…For performance modelling and analytics, most of the existing studies resort to the queueing theory [28] [29] [30] [31] [32], which is a fundamental mathematical approach to capture the behaviour of the network system. For instance, Fahmin et al [32] designed an analytical model for NFV-enabled SDN architecture, where VNFs are deployed aside to SDN controller; the network devices in the proposed architecture are modelled as M/M/1 queueing system and the average delay for NFV packets is achieved and validated by the simulation results. Miao et al [33] designed an analytical model for SDN network with priority queues in data plane and the queues are modelled as MMPP/M/1 system.…”

Section: Related Workmentioning

confidence: 99%

“…Then an analytical model is developed with the bursty and correlated network traffic modelled by Markov Modulated Poisson Process (MMPP). For the service process, to be consistent with the existing work on NFV analytical modelling [32], we used exponential distribution process to model the normal NFV service process. However, to obtain an end-to-end NFV deployment, from access, core, backbone to datacenter networks, we need to consider the impact of wireless channel on the end-to-end delay bound and Markov-modulated off-on process is used to model wireless channels.…”

Section: Performance Derivationmentioning

confidence: 99%

“…Furthermore, we conducted comprehensive simulation experiments to evaluate the performance of the proposed algorithm with the bursty traffic. Additionally, the baseline parameters in the analysis and simulation are set to be consistent with the work in [32]. For numerically evaluating the accuracy of the developed model, we apply the proposed analytical model to the analysis of two common queueing systems, i.e.…”

Section: A Performance Evaluationmentioning

confidence: 99%

“…(35). Without loss of generality, according to the baseline values in [32], the system configuration is shown as follows: service rate is set to be 0.095M packets/second; the arrival rates are set from 0 to 0.095M packets/second with an interval of a 10% of service rate; two violation error settings are adopted to reflect different SLA requirements: 10 −6 and 10 −4 ; the packet size is set to be 1024 bits. As shown in Fig.…”

Section: A Performance Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Stochastic Performance Analysis of Network Function Virtualization in Future Internet

Miao

Min

et al. 2019

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

Network Function Virtualisation (NFV) has been considered as a promising technology for future Internet to increase network flexibility, accelerate service innovation and reduce the Capital Expenditures (CAPEX) and Operational Expenditures (OPEX) costs, through migrating network functions from dedicated network devices to commodity hardware. Recent studies reveal that although this migration of network function brings the network operation unprecedented flexibility and controllability, NFV-based architecture suffers from serious performance degradation compared with traditional service provisioning on dedicated devices. In order to achieve a comprehensive understanding of the service provisioning capability of NFV, this paper proposes a novel analytical model based on Stochastic Network Calculus (SNC) to quantitatively investigate the end-to-end performance bound of NFV networks. To capture the dynamic and on-demand NFV features, both the non-bursty traffic, e.g. Poisson process, and the bursty traffic, e.g. Markov Modulated Poisson Process (MMPP), are jointly considered in the developed model to characterise the arriving traffic. To address the challenges of resource competition and end-to-end NFV chaining, the property of convolution associativity and leftover service technologies of SNC are exploited to calculate the available resources of Virtual Network Function (VNF) nodes in the presence of multiple competing traffic, and transfer the complex NFV chain into an equivalent system for performance derivation and analysis. Both the numerical analysis and extensive simulation experiments are conducted to validate the accuracy of the proposed analytical model. Results demonstrate that the analytical performance metrics match well with those obtained from the simulation experiments and numerical analysis. In addition, the developed model is used as a practical and cost-effective tool to investigate the strategies of the service chain design and resource allocations in NFV networks.

show abstract

Analytical modeling of distributed network functions virtualization architectures and the impact of the distribution on the packet sojourn time

Ilievski

Latkoski

2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Distribution of network functions virtualization (NFV) environment on multiple locations and datacenters is a hot topic in research and engineering communities. In this article, we are making analytical models to calculate the network packet sojourn time in three different scenarios: classical NFV environment where all NFV elements are on the same location, distributed architecture of the data plane with centralized management and orchestration (MANO) environment, and distributed environment where every location has its own data plane and MANO elements. The analytical models are tested and discussed through Matlab based simulations. Through the simulation results, we discuss the impact of changes of different parameters on the packet sojourn time, and we compare the architectures in order to see how they can be fitted in practical services provided in an NFV environment.

show abstract

Performance Modeling of SDN with NFV under or aside the Controller

Cited by 19 publications

References 9 publications

Resilience Analysis of Software-Defined Networks Using Queueing Networks

Resilience Analysis of Software-Defined Networks Using Queueing Networks

Stochastic Performance Analysis of Network Function Virtualization in Future Internet

Analytical modeling of distributed network functions virtualization architectures and the impact of the distribution on the packet sojourn time

Contact Info

Product

Resources

About