An Intelligent Approach for Cloud Infrastructure With Improved Multi-Objective Graywolf Optimization and Resource Allocation for Dynamic Virtual Machine Placement

Abstract

Cloud infrastructure plays a pivotal role in modern computing, yet its optimization and resource allocation often lead to significant delays and power inefficiencies. This research presents an Intelligent Approach for Cloud Infrastructure utilizing Improved multi-objective gray Wolf Optimization and resource allocation for Dynamic Virtual Machine Placement (ICIMRAD). By mimicking the hierarchical structure and hunting strategies of Gray wolves, the Improved Multi-objective Gray Wolf Optimization (IMGWO) algorithm, combined with Genetic Algorithms, effectively enhances the accuracy of virtual machine placement and resource allocation. The Fuzzy Group Genetic Algorithm (FGGA) also addresses complex scheduling challenges, facilitating efficient decision-making across multiple objectives. The dynamic virtual machine system model operates within a Xen environment to monitor power consumption without affecting guest operating systems. Through extensive simulations, the proposed ICIMRAD approach significantly improves metrics such as power consumption, achieving reductions to 0.58 kWh for 50 VMs, and enhances overall system performance compared to traditional optimization methods (e.g., SHOANN, CRASVM, MOOERA). The underlying philosophy emphasizes a powerful synergy between evolutionary strategies and fuzzy logic to drive sustainable and efficient cloud resource management.