TY - JOUR

T1 - Enhancing virtual machine placement efficiency in cloud data centers

T2 - a hybrid approach using multi-objective reinforcement learning and clustering strategies

AU - Ghasemi, Arezoo

AU - Toroghi Haghighat, Abolfazl

AU - Keshavarzi, Amin

N1 - Publisher Copyright: © The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2024.

PY - 2024/9

Y1 - 2024/9

N2 - Deploying virtual machines poses a significant challenge for cloud data centers, requiring careful consideration of various objectives such as minimizing energy consumption, resource wastage, ensuring load balancing, and meeting service level agreements. While researchers have explored multi-objective methods to tackle virtual machine placement, evaluating potential solutions remains complex in such scenarios. In this paper, we introduce two novel multi-objective algorithms tailored to address this challenge. The VMPMFuzzyORL method employs reinforcement learning for virtual machine placement, with candidate solutions assessed using a fuzzy system. While practical, incorporating fuzzy systems introduces notable runtime overhead. To mitigate this, we propose MRRL, an alternative approach involving initial virtual machine clustering using the k-means algorithm, followed by optimized placement utilizing a customized reinforcement learning strategy with multiple reward signals. Extensive simulations highlight the significant advantages of these approaches over existing techniques, particularly energy efficiency, resource utilization, load balancing, and overall execution time.

AB - Deploying virtual machines poses a significant challenge for cloud data centers, requiring careful consideration of various objectives such as minimizing energy consumption, resource wastage, ensuring load balancing, and meeting service level agreements. While researchers have explored multi-objective methods to tackle virtual machine placement, evaluating potential solutions remains complex in such scenarios. In this paper, we introduce two novel multi-objective algorithms tailored to address this challenge. The VMPMFuzzyORL method employs reinforcement learning for virtual machine placement, with candidate solutions assessed using a fuzzy system. While practical, incorporating fuzzy systems introduces notable runtime overhead. To mitigate this, we propose MRRL, an alternative approach involving initial virtual machine clustering using the k-means algorithm, followed by optimized placement utilizing a customized reinforcement learning strategy with multiple reward signals. Extensive simulations highlight the significant advantages of these approaches over existing techniques, particularly energy efficiency, resource utilization, load balancing, and overall execution time.

KW - Cloud computing

KW - Clustering

KW - Machine learning

KW - Virtual machine placement

KW - 68T20

KW - 68T42

KW - 68T05

UR - http://www.scopus.com/inward/record.url?scp=85197251866&partnerID=8YFLogxK

U2 - 10.1007/s00607-024-01311-z

DO - 10.1007/s00607-024-01311-z

M3 - Article

AN - SCOPUS:85197251866

VL - 106

SP - 2897

EP - 2922

JO - Computing

JF - Computing

SN - 0010-485X

IS - 9

ER -