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

Cloud computing faces growing challenges in energy consumption due to the increasing demand for services and resource usage in data centers. To address this issue, we propose a novel energy-efficient virtual machine (VM) placement strategy that integrates reinforcement learning (Q-learning), a Firef...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdelhadi Amahrouch, Youssef Saadi, Said El Kafhali
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Network
Subjects:
Online Access:https://www.mdpi.com/2673-8732/5/2/17
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164885936144384
author Abdelhadi Amahrouch
Youssef Saadi
Said El Kafhali
author_facet Abdelhadi Amahrouch
Youssef Saadi
Said El Kafhali
author_sort Abdelhadi Amahrouch
collection DOAJ
description Cloud computing faces growing challenges in energy consumption due to the increasing demand for services and resource usage in data centers. To address this issue, we propose a novel energy-efficient virtual machine (VM) placement strategy that integrates reinforcement learning (Q-learning), a Firefly optimization algorithm, and a VM sensitivity classification model based on random forest and self-organizing map. The proposed method, RLVMP, classifies VMs as sensitive or insensitive and dynamically allocates resources to minimize energy consumption while ensuring compliance with service level agreements (SLAs). Experimental results using the CloudSim simulator, adapted with data from Microsoft Azure, show that our model significantly reduces energy consumption. Specifically, under the lr_1.2_mmt strategy, our model achieves a 5.4% reduction in energy consumption compared to PABFD, 12.8% compared to PSO, and 12% compared to genetic algorithms. Under the iqr_1.5_mc strategy, the reductions are even more significant: 12.11% compared to PABFD, 15.6% compared to PSO, and 18.67% compared to genetic algorithms. Furthermore, our model reduces the number of live migrations, which helps minimize SLA violations. Overall, the combination of Q-learning and the Firefly algorithm enables adaptive, SLA-compliant VM placement with improved energy efficiency.
format Article
id doaj-art-bc13d3b2405142be8f9a9dcd06a8d8f9
institution OA Journals
issn 2673-8732
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Network
spelling doaj-art-bc13d3b2405142be8f9a9dcd06a8d8f92025-08-20T02:21:52ZengMDPI AGNetwork2673-87322025-05-01521710.3390/network5020017Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement StrategyAbdelhadi Amahrouch0Youssef Saadi1Said El Kafhali2Data Science for Sustainable Earth Laboratory, Faculty of Sciences and Techniques, Sultan Moulay Slimane University, Beni Mellal 23010, MoroccoData Science for Sustainable Earth Laboratory, Faculty of Sciences and Techniques, Sultan Moulay Slimane University, Beni Mellal 23010, MoroccoComputer, Networks, Modeling, and Mobility Laboratory (IR2M), Faculty of Sciences and Techniques, Hassan First University of Settat, Settat 26000, MoroccoCloud computing faces growing challenges in energy consumption due to the increasing demand for services and resource usage in data centers. To address this issue, we propose a novel energy-efficient virtual machine (VM) placement strategy that integrates reinforcement learning (Q-learning), a Firefly optimization algorithm, and a VM sensitivity classification model based on random forest and self-organizing map. The proposed method, RLVMP, classifies VMs as sensitive or insensitive and dynamically allocates resources to minimize energy consumption while ensuring compliance with service level agreements (SLAs). Experimental results using the CloudSim simulator, adapted with data from Microsoft Azure, show that our model significantly reduces energy consumption. Specifically, under the lr_1.2_mmt strategy, our model achieves a 5.4% reduction in energy consumption compared to PABFD, 12.8% compared to PSO, and 12% compared to genetic algorithms. Under the iqr_1.5_mc strategy, the reductions are even more significant: 12.11% compared to PABFD, 15.6% compared to PSO, and 18.67% compared to genetic algorithms. Furthermore, our model reduces the number of live migrations, which helps minimize SLA violations. Overall, the combination of Q-learning and the Firefly algorithm enables adaptive, SLA-compliant VM placement with improved energy efficiency.https://www.mdpi.com/2673-8732/5/2/17cloud computingserver consolidationenergy consumptionfirefly optimizationmachine learningQ-learning
spellingShingle Abdelhadi Amahrouch
Youssef Saadi
Said El Kafhali
Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement Strategy
Network
cloud computing
server consolidation
energy consumption
firefly optimization
machine learning
Q-learning
title Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement Strategy
title_full Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement Strategy
title_fullStr Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement Strategy
title_full_unstemmed Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement Strategy
title_short Optimizing Energy Efficiency in Cloud Data Centers: A Reinforcement Learning-Based Virtual Machine Placement Strategy
title_sort optimizing energy efficiency in cloud data centers a reinforcement learning based virtual machine placement strategy
topic cloud computing
server consolidation
energy consumption
firefly optimization
machine learning
Q-learning
url https://www.mdpi.com/2673-8732/5/2/17
work_keys_str_mv AT abdelhadiamahrouch optimizingenergyefficiencyinclouddatacentersareinforcementlearningbasedvirtualmachineplacementstrategy
AT youssefsaadi optimizingenergyefficiencyinclouddatacentersareinforcementlearningbasedvirtualmachineplacementstrategy
AT saidelkafhali optimizingenergyefficiencyinclouddatacentersareinforcementlearningbasedvirtualmachineplacementstrategy