Building Analytics Pipelines for Querying Big Streams and Data Histories with H-STREAM - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Building Analytics Pipelines for Querying Big Streams and Data Histories with H-STREAM

Résumé

This paper introduces H-STREAM, a big stream/data processing pipelines evaluation engine that proposes stream processing operators as micro-services to support the analysis and visualisation of Big Data streams stemming from IoT (Internet of Things) environments. H-STREAM micro-services combine stream processing and data storage techniques tuned depending on the number of things producing streams, the pace at which they produce them, and the physical computing resources available for processing them online and delivering them to consumers. H-STREAM delivers stream processing and visualisation micro-services installed in a cloud environment. Micro-services can be composed for implementing specific stream aggregation analysis pipelines as queries. The paper presents an experimental validation using Microsoft Azure as a deployment environment for testing the capacity of H-STREAM for dealing with velocity and volume challenges in an (i) a neuroscience experiment and (in) a social connectivity analysis scenario running on IoT farms.

Dates et versions

hal-03318618 , version 1 (10-08-2021)

Identifiants

Citer

Genoveva Vargas-Solar, Javier A. Espinosa-Oviedo. Building Analytics Pipelines for Querying Big Streams and Data Histories with H-STREAM. 19th International Conference on Service-Oriented Computing, Nov 2021, Dubai, United Arab Emirates. ⟨hal-03318618⟩
38 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More