Delay-aware VNF placement and chaining based on a flexible resource allocation approach

Network Function Virtualization (NFV) is a promising technology that is receiving significant attention in both academia and the industry. NFV paradigm proposes to decouple Network Functions (NFs) from dedicated hardware equipment, offering a better sharing of physical resources and providing more flexibility to network operators. However, in such environment, efficient management mechanisms are crucial to address the problem of Placement and Chaining of Virtual Network Functions (PC-VNF). In this paper, we introduce a PC-VNF model based on a flexible resource allocation approach that takes into account service requirements in terms of latency, in addition to traditional connectivity and resource utilization. This is particularly important for emerging 5G services such as ultrareliable, low latency and massive machine type communications. The end-to-end performance needs to meet the user expectations as well as service requirements to provide the desired QoS/QoE. Our main goal is to determine the optimal VNF placement minimizing resource consumption while providing specific latency (i.e., end-to-end delay) and avoiding violation of Service Level Agreements (SLA) by constraining allocated resources to a given VNF to reach its required performance. Results show that our approach achieves the required latency with better resources utilization compared to the classical approaches, with a reduction of up to 40% of resource consumption and a higher rate of accepted requests by recovering 15 to 60 % of the rejected requests.

[1]  Konstantina Papagiannaki,et al.  Analysis of point-to-point packet delay in an operational network , 2004, IEEE INFOCOM 2004.

[2]  Tarik Taleb,et al.  User mobility-aware Virtual Network Function placement for Virtual 5G Network Infrastructure , 2015, 2015 IEEE International Conference on Communications (ICC).

[3]  Filip De Turck,et al.  Algorithms for efficient data management of component-based applications in cloud environments , 2014, 2014 IEEE Network Operations and Management Symposium (NOMS).

[4]  Paul Quinn,et al.  Service Function Chaining Problem Statement , 2013 .

[5]  De Giusti,et al.  Structured Parallel Programming: patterns for efficient computation , 2015 .

[6]  Thomas Bauschert,et al.  Mobile core network virtualization: A model for combined virtual core network function placement and topology optimization , 2015, Proceedings of the 2015 1st IEEE Conference on Network Softwarization (NetSoft).

[7]  J. Nash.  Equilibrium Points in N-Person Games. , 1950, Proceedings of the National Academy of Sciences of the United States of America.

[8]  G. Amdhal,et al.  Validity of the single processor approach to achieving large scale computing capabilities , 1967, AFIPS '67 (Spring).

[9]  John L. Gustafson,et al.  Reevaluating Amdahl's law , 1988, CACM.

[10]  Johannes Bisschop,et al.  AIMMS - Optimization Modeling , 2006 .

[11]  Filip De Turck,et al.  Network Function Virtualization: State-of-the-Art and Research Challenges , 2015, IEEE Communications Surveys & Tutorials.