Towards energy and QoS aware dynamic VM consolidation in a multi-resource cloud

As cloud data centers (DCs) have become integral to enterprise computing infrastructure, the upswing in the demand for cloud services has led to significant energy consumption. Thus, efficient energy management techniques have become imperative to address this challenge. Although several methods have been developed for energy reduction through virtual machine consolidation (VMC), they primarily focus on minimizing active hosts, often neglecting the trade -off between energy efficiency and quality of service (QoS) satisfaction. Moreover, optimizing energy efficiency while maintaining QoS becomes increasingly complex in multi-resource environments, especially with diverse workloads. To tackle these issues, we present Resource-Optimized VMC (RO-VMC), a novel VMC framework. It places a primary focus on optimizing resource utilization to balance the energy efficiency-QoS trade -off from the perspectives of both cloud service providers (CSPs) and users. RO-VMC leverages a probabilistic model to capture the inherent stochasticity of workloads and optimizes migration decisions. By considering the complex interplay between energy efficiency and QoS satisfaction, it effectively redistributes the migrating VMs, ensuring the needs and expectations of both CSPs and cloud users are met. Experiments are conducted using the Bitbrains and Google Cloud Cluster traces on a simulated cloud setup to evaluate the effectiveness of RO-VMC. Comparative analysis against state -of -the -art VMC strategies (AFED-EF, EQ-VMC and PEAS) revealed that RO-VMC outperforms them by a significant margin in terms of energy efficiency, QoS satisfaction and resource utilization.