Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement Strategy

Network, Год журнала: 2025, Номер 5(2), С. 17 - 17

Опубликована: Май 27, 2025

Cloud computing faces growing challenges in energy consumption due to the increasing demand for services and resource usage data centers. To address this issue, we propose a novel energy-efficient virtual machine (VM) placement strategy that integrates reinforcement learning (Q-learning), Firefly optimization algorithm, VM sensitivity classification model based on random forest self-organizing map. The proposed method, RLVMP, classifies VMs as sensitive or insensitive dynamically allocates resources minimize while ensuring compliance with service level agreements (SLAs). Experimental results using CloudSim simulator, adapted from Microsoft Azure, show our significantly reduces consumption. Specifically, under lr_1.2_mmt strategy, achieves 5.4% reduction compared PABFD, 12.8% PSO, 12% genetic algorithms. Under iqr_1.5_mc reductions are even more significant: 12.11% 15.6% 18.67% Furthermore, number of live migrations, which helps SLA violations. Overall, combination Q-learning algorithm enables adaptive, SLA-compliant improved efficiency.

Язык: Английский

Entropy‐Aware VM Selection and Placement in Cloud Data Centers

Concurrency and Computation Practice and Experience, Год журнала: 2025, Номер 37(15-17)

Опубликована: Май 30, 2025

ABSTRACT The increase in popularity and demand for cloud services has caused a huge growth of data centers, this the challenge energy management centers. Virtual Machine (VM) consolidation is critical process aimed at optimizing resource utilization minimizing usage. VM with turnoff underloaded hosts reducing load overloaded establishes balance between consumption SLA violations. In fact, includes three sub‐problems: determining hosts, selection finding new destination VMs that will be migrated (VM placement). This paper introduces an entropy‐based approach to placement improve efficiency Entropy quantifiable characteristic often linked disorder, randomness, or unpredictability. By leveraging entropy as measure workload distribution uncertainty, proposed method effectively predicts future demands, enabling informed decisions enhance reduce A key advantage significant reduction number migrations, which decreases overhead minimizes potential service disruptions. Experimental results demonstrate our outperforms terms consumption, compliance, system stability. findings suggest offers more sustainable cost‐effective solution managing resources, contributing development efficient reliable computing environments.

Язык: Английский