An Elastic Software Architecture for Extreme-Scale Big Data Analytics

	Chapter in a book
Title	An Elastic Software Architecture for Extreme-Scale Big Data Analytics
Authors	Barcelona Supercomputing Center (BSC), Barcelona, Spain Maria A. Serrano & Eduardo Quiñones Information Catalyst for Enterprise Ltd, Crewe, UK César A. Marín Universitat Politècnica de Catalunya (UPC), Barcelona, Spain Anna Queralt Barcelona Supercomputing Center (BSC), Barcelona, Spain Anna Queralt SIXSQ, Meyrin, Switzerland Cristovao Cordeiro Ikerlan Technology Research Centre, Basque Research Technology Alliance (BRTA), Arrasate/Mondragón, Spain Marco Gonzalez Instituto Superior De Engenharia Do Porto (ISEP), Porto, Portugal Luis Miguel Pinho
Publisher	Springer, Cham
Year	2021
Link	https://link.springer.com/chapter/10.1007/978-3-030-78307-5_5
DOI	https://doi.org/10.1007/978-3-030-78307-5_5
ISSN	978-3-030-78307-5
Citation	Serrano, M.A. et al. (2022). An Elastic Software Architecture for Extreme-Scale Big Data Analytics. In: Curry, E., Auer, S., Berre, A.J., Metzger, A., Perez, M.S., Zillner, S. (eds) Technologies and Applications for Big Data Value . Springer, Cham. https://doi.org/10.1007/978-3-030-78307-5_5
Abstract	This chapter describes a software architecture for processing big-data analytics considering the complete compute continuum, from the edge to the cloud. The new generation of smart systems requires processing a vast amount of diverse information from distributed data sources. The software architecture presented in this chapter addresses two main challenges. On the one hand, a new elasticity concept enables smart systems to satisfy the performance requirements of extreme-scale analytics workloads. By extending the elasticity concept (known at cloud side) across the compute continuum in a fog computing environment, combined with the usage of advanced heterogeneous hardware architectures at the edge side, the capabilities of the extreme-scale analytics can significantly increase, integrating both responsive data-in-motion and latent data-at-rest analytics into a single solution. On the other hand, the software architecture also focuses on the fulfilment of the non-functional properties inherited from smart systems, such as real-time, energy-efficiency, communication quality and security, that are of paramount importance for many application domains such as smart cities, smart mobility and smart manufacturing.