Quality of Service Driven Energy-Efficient Computing to Enhance Sustainable Cloud

In this research, a novel hybrid method is introduced that combines Coati and Gazelle Optimization algorithms to enhance the management of virtual machines (VMs) in Cloud Computing (CC). The goal is to reduce energy usage and prevent server overload by optimizing VM placement. Our approach balances exploring new options with refining existing solutions. The method is tested the method using CloudSim, and the results demonstrate improved performance compared to existing techniques, particularly in energy savings, reduced system slowdowns, and smoother workload handling. CC has become a leading on-demand platform, allowing users to store and access data anytime under a “pay as you go” model. However, the high volume of user requests increases energy consumption, negatively impacting Quality of Service (QoS). Existing research has mainly focused on either QoS or energy efficiency to enhance user experience. To address this, a hybrid approach is employed that integrates Coati with Gazelle optimization to combine QoS and energy efficiency in a cloud environment. The focus is on improving infrastructure performance through resource allocation, workload scheduling, and VM placement while minimizing operational costs and energy consumption through workload adaptation and dynamic resource management. Improved energy efficiency leads to decreased energy consumption and enhanced QoS when users receive timely responses from cloud providers. The three methods is utilized: an energy-aware VM selection policy, EQ-VMC, and the proposed hybrid Coati with Gazelle optimization. These methods are compared using performance metrics such as migration time, throughput, reliability, energy efficiency, and QoS. The proposed model achieves higher performance than the other two methods, making it a valuable solution for effective cloud system management. The Hybrid Coati with Gazelle Optimization has attained the reliability as 98.30 %, scalability as 90.44%, throughput as 99.05% and availability as 98.18%.