Machine Learning-based Orchestration of Containers: A Taxonomy and Future Directions

Abstract

Containerization is a lightweight application virtualization technology, providing high environmental consistency, operating system distribution portability, and resource isolation. Existing mainstream cloud service providers have prevalently adopted container technologies in their distributed system infrastructures for automated application management. To handle the automation of deployment, maintenance, autoscaling, and networking of containerized applications, container orchestration is proposed as an essential research problem. However, the highly dynamic and diverse feature of cloud workloads and environments considerably raises the complexity of orchestration mechanisms. Machine learning algorithms are accordingly employed by container orchestration systems for behavior modelling and prediction of multi-dimensional performance metrics. Such insights could further improve the quality of resource provisioning decisions in response to the changing workloads under complex environments. In this paper, we present a comprehensive literature review of existing machine learning-based container orchestration approaches. Detailed taxonomies are proposed to classify the current researches by their common features. Moreover, the evolution of machine learning-based container orchestration technologies from the year 2016 to 2021 has been designed based on objectives and metrics. A comparative analysis of the reviewed techniques is conducted according to the proposed taxonomies, with emphasis on their key characteristics. Finally, various open research challenges and potential future directions are highlighted.

Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration

“…Zhong et al [26] provide an extensive survey of ML-based container orchestration approaches. They form a taxonomy for ML-based container orchestration solutions, consisting of five main categories: application architecture (the composition of containerized applications), cloud infrastructure, optimization objectives, behavior modelling and prediction (workload characterization, performance analysis, anomaly detection and dependency analysis), and resource provisioning operations for containerized applications.…”

“…Synthesizing the taxonomies in a number of recent works (see e.g. [28,29,25,23,26], and those mentioned in Section II-B), in this article, we take a holistic approach to the resources in the computing continuum. These resources, as depicted in Fig.…”

“…In this article, again synthesizing the concepts presented in recent studies on orchestration [28,29,25,23,26], we holistically define orchestration as the management of resources in the computing continuum, from fundamental resources to workflow resources, as depicted in Fig. 2.…”

AI for Next Generation Computing: Emerging Trends and Future Directions

“…The cloud native paradigm derived from cloud computing has shifted the traditional monolithic cloud application into light-weight, loose-coupled and fine-grained microservices [54]. This paradigm can support the applications to be updated in a much more efficient manner.…”

A Learning-based Approach Towards Automated Tuning of SSD Configurations

“…Machine Learning for Systems. Most recently, researchers have started to leverage machine learning techniques to solve system optimization problems, such as the task scheduling [58,74,83], cluster resource management [12,18,24,52,79], performance optimizations [33,45,51,84], data management [10,43,49,73], and others [53,78]. However, few studies conduct a systematic investigation of applying the learning techniques to develop SSD devices.…”