Analyzing auto-scaling issues in cloud environments
Hanieh Alipour, Yan Liu, Abdelwahab Hamou‐Lhadj · Computer Science and Software Engineering · 2014
Cloud computing is becoming increasingly widespread and sophisticated. A key feature of cloud computing is elasticity, which allows the provisioning and de-provisioning of computing resources on demand, via auto-scaling. Auto-scaling techniques are diverse, and involve various components at the infrastructure, platform and software levels. Auto-scaling also overlaps with other quality attributes, thereby contributing to service level agreements, and often applies modeling and control techniques to make the auto-scaling process adaptive. A study of auto-scaling architectures, existing techniques and open issues provides a comprehensive understanding to identify future research solutions. In this paper, we present a survey that explores definitions of related concepts of auto-scaling and a taxonomy of auto-scaling techniques. Based on the survey results, we then outline open issues and future research directions for this important subject in cloud computing.