Machine Learning for Performance-Aware Virtual Network Function Placement

被引：31

作者：

Manias, Dimitrios Michael ^{[1
]}

Jammal, Manar ^{[1
]}

Hawilo, Hassan ^{[1
]}

Shami, Abdallah ^{[1
]}

Heidari, Parisa ^{[2
]}

Larabi, Adel ^{[2
]}

Brunner, Richard ^{[2
]}

机构：

[1] Western Univ, ECE Dept, London, ON, Canada

[2] Edge Grav Ericsson, Montreal, PQ, Canada

来源：

2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) | 2019年

关键词：

Network Function Virtualization; Virtual Network Functions; Service Function Chain; VNF Placement; Machine Learning; Decision Tree;

D O I：

10.1109/globecom38437.2019.9013246

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

With the growing demand for data connectivity, network service providers are faced with the task of reducing their capital and operational expenses while simultaneously improving network performance and addressing the increased connectivity demand. Although Network Function Virtualization (NFV) has been identified as a solution, several challenges must be addressed to ensure its feasibility. In this paper, we address the Virtual Network Function (VNF) placement problem by developing a machine learning decision tree model that learns from the effective placement of the various VNF instances forming a Service Function Chain (SFC). The model takes several performance-related features from the network as an input and selects the placement of the various VNF instances on network servers with the objective of minimizing the delay between dependent VNF instances. The benefits of using machine learning are realized by moving away from a complex mathematical modelling of the system and towards a data-based understanding of the system. Using the Evolved Packet Core (EPC) as a use case, we evaluate our model on different data center networks and compare it to the BACON algorithm in terms of the delay between interconnected components and the total delay across the SFC. Furthermore, a time complexity analysis is performed to show the effectiveness of the model in NFV applications.

引用

页数：6

共 18 条

[1]

Buda TS, 2016, IEEE IFIP NETW OPER, P1279, DOI 10.1109/NOMS.2016.7503003

[2]

Burke E. K., 2014, Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques, DOI DOI 10.1007/0-387-28356-0_6

[3]

Chiosi Margaret., 2012, NETWORK FUNCTIONS VI

[4]

Riera JF, 2016, 2016 IEEE NETSOFT CONFERENCE AND WORKSHOPS (NETSOFT), P243, DOI 10.1109/NETSOFT.2016.7502419

[5]

Hawilo H., 2019, IEEE Netw, V33, P1

[6]

Hawilo H., 2019, IEEE J. Sel. Areas Commun, V37, P1

[7] NFV: State of the Art, Challenges, and Implementation in Next Generation Mobile Networks (vEPC) [J].

Hawilo, Hassan ;

Shami, Abdallah ;

Mirahmadi, Maysam ;

Asal, Rasool .

IEEE NETWORK, 2014, 28 (06) :18-26

[8]

Khezri H. R., 2018, DEEP Q LEARNING DYNA

[9]

Le L.-V., 2018, T NETWORKS COMMUN, V6

[10]

Mantovani R G., 2018, An empirical study on hyperparameter tuning of decision trees. arXiv

← 1 2 →