The Internet of Things (IoT) will consist of billions (50 billions by 2020) of interconnected heterogeneous devices denoted as “Smart Objects:” tiny, constrained devices which are going to be pervasively deployed in several contexts. To meet low-latency requirements, IoT applications must rely on specific architectures designed to handle the gigantic stream of data coming from Smart Objects. This paper propose a novel Cloud architecture for Big Stream applications that can efficiently handle data coming from Smart Objects through a Graph-based processing platform and deliver processed data to consumer applications with low latency. The authors reverse the traditional “Big Data” paradigm, where real-time constraints are not considered, and introduce the new “Big Stream” paradigm, which better fits IoT scenarios. The paper provides a performance evaluation of a practical open-source implementation of the proposed architecture. Other practical aspects, such as security considerations, and possible business oriented exploitation plans are presented.
A Scalable Big Stream Cloud Architecture for the Internet of Things / Belli, Laura; Cirani, Simone; Davoli, Luca; Ferrari, Gianluigi; Melegari, Lorenzo; Montón, Màrius; Picone, Marco. - In: INTERNATIONAL JOURNAL OF SYSTEMS AND SERVICE ORIENTED ENGINEERING. - ISSN 1947-3052. - 5:4(2015), pp. 26-53. [10.4018/IJSSOE.2015100102]
A Scalable Big Stream Cloud Architecture for the Internet of Things
Belli, Laura;Cirani, Simone;DAVOLI, LUCA;FERRARI, Gianluigi;Picone, Marco
2015-01-01
Abstract
The Internet of Things (IoT) will consist of billions (50 billions by 2020) of interconnected heterogeneous devices denoted as “Smart Objects:” tiny, constrained devices which are going to be pervasively deployed in several contexts. To meet low-latency requirements, IoT applications must rely on specific architectures designed to handle the gigantic stream of data coming from Smart Objects. This paper propose a novel Cloud architecture for Big Stream applications that can efficiently handle data coming from Smart Objects through a Graph-based processing platform and deliver processed data to consumer applications with low latency. The authors reverse the traditional “Big Data” paradigm, where real-time constraints are not considered, and introduce the new “Big Stream” paradigm, which better fits IoT scenarios. The paper provides a performance evaluation of a practical open-source implementation of the proposed architecture. Other practical aspects, such as security considerations, and possible business oriented exploitation plans are presented.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.