Microservices Adaptation using Machine Learning: A Systematic Mapping Study

Anouar Hilali, Hatim Hafiddi, Zineb El Akkaoui

2021

Abstract

The Microservice architecture is increasingly becoming the preferred architecture of modern applications. The logically distinct components that make up microservices make continuous delivery easier compared to monolithic architectures. This feature however makes it difficult for engineers to control the underlying services and properly adapt them at run-time. Designing our microservices as self-adaptive systems helps us tackle this issue. Each microservice can then dynamically monitor and adapt its behavior to change certain aspects of itself to achieve self-adaptive goals. The use of statistical and Machine Learning (ML) techniques helps in this area in a lot of ways (e.g., predicting resource usage, anomaly detection, etc.). This paper aims to provide a state of the art of the use of ML in microservice adaptation, the main goal is to provide an overview of the field and identify the most frequent adaptation goals and the types of adaptation techniques used. In order to carry out a comprehensive analysis, a well-defined method of systematic mapping is performed to categorize, according to a detailed scheme, every paper relevant to this topic. The results can potentially shed light on areas where further investigation might be warranted.

Paper Citation

in Harvard Style

Hilali A., Hafiddi H. and El Akkaoui Z. (2021). Microservices Adaptation using Machine Learning: A Systematic Mapping Study. In Proceedings of the 16th International Conference on Software Technologies - Volume 1: ICSOFT, ISBN 978-989-758-523-4, pages 521-532. DOI: 10.5220/0010578905210532

in Bibtex Style

@conference{icsoft21,
author={Anouar Hilali and Hatim Hafiddi and Zineb El Akkaoui},
title={Microservices Adaptation using Machine Learning: A Systematic Mapping Study},
booktitle={Proceedings of the 16th International Conference on Software Technologies - Volume 1: ICSOFT,},
year={2021},
pages={521-532},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010578905210532},
isbn={978-989-758-523-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Software Technologies - Volume 1: ICSOFT,
TI - Microservices Adaptation using Machine Learning: A Systematic Mapping Study
SN - 978-989-758-523-4
AU - Hilali A.
AU - Hafiddi H.
AU - El Akkaoui Z.
PY - 2021
SP - 521
EP - 532
DO - 10.5220/0010578905210532