Quality of cloud orchestrated services in 5G mobile networks

Abstract

The rapid increase of the mobile devices resulted the mobile users to demand more and more ubiquitous mobile broadband services comparable to the fixed broadband Internet. In that direction on a global level the number of research initiatives on 5G mobile networks has rapidly increased. 5G networks would act as a nervous system of the digital society, on the economy and people’s everyday lives and would create new paradigms of Internet services such as “Anything as a Service”, where the devices, terminals, machines, smart things and the robots would become innovative tools that would create applications, services, and data and at the same time would use them. In order to satisfy the requests for big data processing and more intelligent networking demands in 5G networks, the main trend in the last decade was to push the processing, computing and the storage of data in the Cloud Computing environment. However, the cloud alone encounters growing limitations for reduced latency, high degree of mobility, high scalability, and real-time execution. A new paradigm called Fog Computing has emerged to overcome the limitations in the Cloud Computing technology. The fog computing extends the cloud computing at the edge of the network, that distributes computing, data processing, and networking services closer to end users. It is an architecture where distributed edge and user devices collaborate with each other and with the clouds to carry out computing, control, networking, and data management tasks. The application of fog computing in 5G mobile networks would contribute significantly to improve the network performances in terms of spectral and energy efficiency, enable direct device-to-device wireless communications, and support the growing trend of network function virtualization and the separation of network control intelligence from radio network hardware. This doctoral dissertation performs an evaluation of the quality of cloud and fog orchestrated services in 5G mobile networks through the delay (latency), user throughput, and the energy efficiency for the power consumed. In addition, 5 possible algorithms are proposed for an optimal selection of the best 5G radio access network depending from the types of the services that have certain requirements in terms of throughput, latency, and energy efficiency of the power consumed. The performed analysis of the results of this doctoral dissertation demonstrate that 5G networks would have a great benefit of implementing the fog computing technology, because the fog computing technology possess mechanisms that would handle with the new up-coming services, which would require low latency, high level of mobility, high scalability and real-time execution.