Autoscaling techniques in cloud-native computing: A comprehensive survey

Abstract

Autoscaling, the core technology of cloud-native computing, dynamically adjusts computing resources as per application load fluctuations in order to improve scalability, cost efficiency, and performance continuity. By doing so, autoscaling enables widespread adoption of cloud-native computing across various industries; consequently, autoscaling techniques are critical for supporting the cloud-native paradigm. This study aims to provide a comprehensive survey of cloud-native autoscaling techniques, offering a unified understanding of current approaches and identifying unresolved issues. First, autoscaling algorithms and mechanisms are each classified into three types. Through this classification framework, a wide range of scaling algorithms, from threshold-based reactive policies to artificial intelligence (AI)-based proactive policies, are examined, and their respective advantages and limitations are analyzed. Next, the study comprehensively investigates and summarizes the experimental environments, datasets, and performance metrics used for evaluating autoscaling techniques. Furthermore, it systematically discusses key considerations for optimizing autoscaling techniques across the lifecycle of cloud-native applications by dividing the process into three distinct stages. In addition, this study provides a comprehensive review of cyberattacks that exploit autoscaling and the corresponding mitigation strategies. Finally, it discusses open issues, future directions, and research opportunities related to autoscaling in cloud-native computing.