An Adaptive QoE-Based Network Interface Selection for Multi-homed eHealth Devices
Conventional network control mechanisms are no longer suitable for Internet of Things (IoT) because they don’t allow scalability with a guarantee of Quality of Experience (QoE) especially when it comes to the health sector characterized by its real time and critical life aspects. That’s why we need to think differently about control. One aspect consists of improving the network accessibility by considering Multi-homed terminals using multiple network access points simultaneously. In this paper we present a new Q-Learning-based adaptive network interface selection approach. Experimental results show that the proposed approach involve QoE compared to a simple linear programming approach. abstract environment.
KeywordsReinforcement Learning Q-learning Quality of Experience Mean Opinion Score (MOS) Multi-homed devices ICT health Internet of Things (IoT)
- 2.Mitharwal, P., Lohr, C., Gravey, A.: Survey on network interface selection in multihomed mobile networks. In: Kermarrec, Y. (ed.) EUNICE 2014. LNCS, vol. 8846, pp. 134–146. Springer, Heidelberg (2014)Google Scholar
- 3.Souidi, M., Souihi, S., Hoceini, S., Mellouk, A.: An adaptive real time mechanism for IaaS cloud provider selection based on QoE aspects. In: IEEE International Conference on Communications (ICC), London, United Kingdom, 8–12 June 2015. (confrence de rfrence dans le domaine des rseaux)Google Scholar
- 4.Mellouk, A., Tran, H.A., Hoceini, S.: Quality-of-Experience for Multimedia. Wiley-ISTE, October 2013. ISBN: 978-1-84821-563-4Google Scholar
- 6.Proko, E., Ninka, I.: Analysis and strategy for the performance testing in cloud computing. Global J. Comput. Sci. Technol. Cloud Distrib. 12(10), 11–14 (2012)Google Scholar