Oμιλητής: Γιάννης Χατζηγιαννάκης, Αναπληρωτής Καθηγητής, Department of Computer, Control and Management Engineering, "La Sapienza" University of Rome
Τίτλος: From Cloud to Fog Computing: 10 years of Deployment Experience of Internet of Things Applications
Ημερομηνία-χώρος: Παρασκευή 19 Μαρτίου, 3-5μμ
Περίληψη: Today, a typical Internet of Things (IoT) application uses Cloud Computing services to interconnect the IoT infrastructures and centrally collect the data produced by the deployed devices. Big Data applications process the large amounts of data arriving from the IoT devices. Such compute infrastructures are paving the way towards the future Sharing Economy Systems and they typically follow a producer/consumer model in which the cloud-based analytics platform processes the IoT generated data. With the continuous development of IoT technologies, the total number of interconnected IoT devices sharply increases, thus producing vast amounts of data, which needs to be delivered to distant machine clouds for consumption. Therefore the cloud-based approach needs to address multiple performance issues appearing at all levels of the network architecture: (a) network bandwidth issues at the network edge, (b) network energy consumption as traffic flows through the network core, (c) continuous I/O operations at the data centers where data is processed, (d) increased exposure of data across third-party cloud-based services. Since the processing capabilities of IoT devices are continually increasing, Fog Computing proposes the concept of utilizing such resource-bound, last-mile computational resources as a means to: a) increase both responsiveness and real-time characteristics of analytic applications, b) achieve energy efficient processing by reducing the computational cycles of the heavyweight cluster or cloud-deployed Big Data frameworks, and c) increase the security of the deployment in an end-to-end manner by enabling in-situ computations thus minimizing data exchanges through the network. In this talk we introduce the definition of Fog Computing, followed by several case studies, ranging from cloud offloading for the realization of smart metering and smart cities, to very recent deployments that work towards the convergence of Big Data and IoT to materialize the concept of Fog Computing. Finally, we present several challenges and opportunities in the field of Fog Computing, and hope this talk will gain attention from the community and inspire more research in this research direction.
Σχετικά με τον ομιλητή: Prof. Ioannis Chatzigiannakis holds a PhD from the University of Patras (2003) in the area of ad-hoc wireless mobile networks and a BEng from the University of Kent (1997) in Computer Systems Engineering. He is an Associate Professor at the "La Sapienza" University of Rome at the Department of Computer, Control and Management Engineering. He has co-authored over 150 scientific publications in areas related to dynamic distributed computing, internet of things, algorithm engineering and software systems. He has been a project manager and site leader for numerous research & development projects funded by the EU in the context of H2020, FP7, FP6 and EDA and has participated in the research & development teams of industrial projects. He has an active role in many open-source projects and regularly participates in open-source international events. He has started a number of technology-based start-ups related to the Internet-of-Things. He served as the Secretary of the European Association for Theoretical Computer Science (EATCS). He is a member of the ACM and IEEE.