Authors:
Theo Zschörnig
1
;
Jonah Windolph
1
;
Robert Wehlitz
1
and
Bogdan Franczyk
2
;
3
Affiliations:
1
Institute for Applied Informatics (InfAI), Goerdelerring 9, 04109 Leipzig, Germany
;
2
Business Informatics Institute, Wrocław University of Economics, ul. Komandorska 118-120, 53-345 Wrocław, Poland
;
3
Information Systems Institute, Leipzig University, Grimmaische Str. 12, 04109 Leipzig, Germany
Keyword(s):
Fog Computing, Internet of Things, Smart Home, Analytics Architecture.
Abstract:
Data analytics are an integral part of the utility and growth of the Internet of Things (IoT). The data, which is generated from a wide variety of heterogenous smart devices, presents an opportunity to gain meaningful insights into different aspects of everyday lives of end-consumers, but also into value-adding processes of businesses and industry. The advancements in streaming and machine learning technologies in the past years may further increase the potential benefits that arise from data analytics. However, these developments need to be enabled by the underlying analytics architectures, which have to address a multitude of different challenges. Especially in consumer-centric application domains, such as smart home, there are different requirements, which are influenced by technical, but also legal or personal constraints. As a result, analytics architectures in this domain should support the hybrid deployment of analytics pipelines at different network layers. Currently availabl
e approaches lack the needed capabilities. Consequently, in this paper, we propose an architectural solution, which enables hybrid analytics pipeline deployments, thus addressing several challenges described in previous scientific literature.
(More)