Machine learning (ML)-centric resource management in cloud computing: A review and future directions

Cloud computing has rapidly emerged as a model for delivering Internet-based utility services. Infrastructure Service (IaaS) is one of the most important and growing models in cloud computing. Scalability, quality service, optimum utility, decreased overheads, higher throughput, reduced latency, specialised environment, cost-effectiveness, streamlined interface are some essential elements IaaS. Traditionally, resource management been done through static policies, which impose certain limitations various dynamic scenarios, prompting service providers to adopt data-driven, machine-learning-based approaches. Machine learning being used handle tasks, including workload estimation, task scheduling, VM consolidation, optimisation, energy among others. This paper provides detailed review machine learning-based solutions. We begin by introducing background concepts like models, deployment use Then we look at challenges computing, categorise them based on aspects types such prediction, provisioning, placement thermal management, current techniques addressing these challenges, evaluate their key benefits drawbacks. Finally, propose prospective future research directions observed shortcomings approaches solving challenges.