0000000000272753
AUTHOR
Alessandro Randazzo
Mobile Edge Computing: Architetture ed Analisi della Live Migration
Con l'ormai prossima rete mobile 5G entreranno a far parte della nostra quotidianità nuovi servizi applicativi, mai prima possibili, grazie all'avvicinamento di risorse di calcolo e di memoria nei pressi dell'utente in mobilità. Un’architettura abilitante i futuri servizi è quella di Mobile Edge Computing (MEC) in cui cloud di capacità inferiori rispetto a quelli presenti nella core della rete sono dislocati nei pressi della stazioni radio e metteranno a disposizione risorse di calcolo tali da permettere, tramite la tecnica di offloading, la fruizione di servizi quali realtà aumentata, gaming online, contenuti streaming ad alta risoluzione ed operazioni di data analytics. Ogni nuovo paradig…
Performance Analysis of Memory Cloning Solutions in Mobile Edge Computing
This paper deals with the problem of service migration in the emerging scenarios of Mobile Edge Computing. Mobile edge computing is achieved by moving the traditional cloud infrastructures, exploited by many today applications, close to the network edge in order to reduce the response times in the so called tactile-internet. However, because of user mobility, such an application architecture may pose the problem of service migration in case of handover from one server site to another. After introducing the current solutions for dealing with service migration and, in particular, the approaches based on service decomposition into multiple layers, we quantify the migration time and the service…
Kata Containers: An Emerging Architecture for Enabling MEC Services in Fast and Secure Way
New coming applications will be only possible through Mobile Edge Servers deployed in proximity of the mobile users. Due to the user's mobility and server's workload, service migration will be an integral part of the services. For this reason, a standardized architecture should be designed to accomplish a workload migration in a secure and timely manner. Most research done to date has focused on the use of either virtual machine (VM) or container or a mix of both recently. A final solution might be an architecture only having the advantages of both technologies as the security of the VM and the speed of the containers. Custom solutions, actually, by using both technologies, need continuous …
Recognizing Video Resolution by Monitoring Memory Metrics in Mobile Clients
Content delivery is one of the most successful applications in mobile networks. Mobile edge servers are significantly contributing to the improvement of this type of applications, by also performing resolution adaptations as a function of the radio link quality observed by the users. In this paper, we face the problem of dynamically tracking the perceived video resolution by mobile clients in a mobile edge environment to guarantee an agreed Service Level Agreement (SLA). To this purpose, we propose a protocol-agnostic approach, based on monitoring some memory metrics of a running video streaming process at the mobile client, for identifying the time-varying resolution of the video content.