Distributed Auction-Based SFC Placement in a Multi-domain 5G Environment

Evandro L. C. Macedo, Anselmo Luiz Éden Battisti, Juan Lucas Vieira, Julia Noce, Paulo F. Pires, Débora C. Muchaluat-Saade, Ana Cristina Bernardo de Oliveira, Flávia Coimbra Delicato

Abstract: The fifth generation of mobile networks (5G) brings an evolution of network service provisioning through a new communication paradigm, which enables the development of new applications and improves users’ experience. With 5G, it is envisioned that networks will provide services accessed by a variety of mobile users, some of such services requiring ultra-low latency and very high reliability. 5G also enables massive connectivity of sensors and actuators in the Internet of Things and Cyber-physical Systems scenarios, standing for massive Machine-Type Communication applications. Network Function Virtualization (NFV) is an emerging and promising solution to deal with such demands for flexible and agile service provisioning by replacing dedicated hardware implementations with software instances based on virtualization. A well-known challenge in NFV is the resource allocation problem. In particular, the Service Function Chain (SFC) placement problem is considered a major challenge, even more, when considering the distributed placement in a multi-administrative domain context. We propose a novel solution for the SFC placement problem called Multi-Domain Distributed Auction-Based SFC Placement Algorithm, which relies on an auction-based strategy. The proposed algorithm targets different 5G application scenarios with a focus on solving the SFC placement problem taking into consideration the dynamic aspects of unpredictable requests and the management of the entire auction process to decide which domain will be selected to meet the required SFC. Evaluations were carried out in a simulated environment aiming at assessing the performance of the algorithm in terms of the profit for each service provider during the allocation of the requested services in the respective domain that the service provider is responsible for. Results showed that adopting an auction-based mechanism, and thus allowing a domain to outsource the provision of requested services, successfully reduced the total cost of the service execution in a multi-domain environment. The auction-based approach increases the service provider profit by around 20% in the tested scenarios. Moreover, the number of services placed increases in comparison to the approach where all the services must be executed in the decision domain (with no auction).