Towards a dynamic heuristic for task scheduling in application integration platforms to handle large volumes of data

Integration platforms are software tools needed to support the integration process. They have a runtime system responsible for processing the integration process data. Currently, with the growing volume of data coming from the IoT, integration platforms are beginning to show necessary improvements i...

Full description

Saved in:
Bibliographic Details
Published inThe Journal of supercomputing Vol. 79; no. 1; pp. 998 - 1031
Main Authors Mazzonetto, Angela, Frantz, Rafael Z., Sawicki, Sandro, Roos-Frantz, Fabricia, Battisti, Gerson
Format Journal Article
LanguageEnglish
Published New York Springer US 2023
Springer Nature B.V
Subjects
Compilers
Computer Science
Data integration
Efficiency
Heuristic task scheduling
Interpreters
Optimization
Platforms
Processor Architectures
Programming Languages
Run time (computers)
Software
Software engineering
Runtime system
Enterprise application integration
Mathematical modeling
Integration platforms
Integration frameworks
Online AccessGet full text

Cover

More Information
Summary:Integration platforms are software tools needed to support the integration process. They have a runtime system responsible for processing the integration process data. Currently, with the growing volume of data coming from the IoT, integration platforms are beginning to show necessary improvements in their efficiency. Optimization techniques have been applied to the most diverse problems in software engineering, and that’s why in this work, based on optimization techniques, we developed a heuristic technique capable of providing efficiency in different patterns of data input loads. Our results demonstrate that the heuristic that we propose dMQueue provides greater efficiency to the runtime system because it has frequent monitoring and periodicity, making the threads adjusted based on the workload.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-022-04695-x