Improving Self-Adaptation by Combining MAPE-K, Machine and Deep Learning

Monitoring, Analyzing, Planning, and Execution share knowledge and build a favorable approach in the form of a loop (MAPE-K). However, this proposed reference model is not efficient for large self-adaptations. Moreover, the failure of the analyzer component to keep up with the current expansion of d...

Full description

Saved in:
Bibliographic Details
Published in2022 2nd International Conference on New Technologies of Information and Communication (NTIC) pp. 1 - 6
Main Authors Lecheheb, Sabah, Boulehouache, Soufiane, Brahimi, Said
Format Conference Proceeding
LanguageEnglish
Published IEEE 21.12.2022
Subjects
Control systems
Deep learning
Focusing
Hybrid learning
Machine Learning
MAPE-K Control Loop
Monitoring
Optimization
Planning
Self-Adaptive Systems
Online AccessGet full text

Cover

More Information
Summary:Monitoring, Analyzing, Planning, and Execution share knowledge and build a favorable approach in the form of a loop (MAPE-K). However, this proposed reference model is not efficient for large self-adaptations. Moreover, the failure of the analyzer component to keep up with the current expansion of data is one of the reasons that making the MAPE-K loop consumes a lot of time and resources. We suggest a hybrid learning dataflow design for the analysis phase that combines Machine and Deep Learning techniques to enhance the accuracy of the Analyzer component in less time.
DOI:10.1109/NTIC55069.2022.10100459