DNN-Based PM Ranking Integrated with Firefly Algorithm for VM Replacement Framework.

Saved in:

Bibliographic Details
Title:	DNN-Based PM Ranking Integrated with Firefly Algorithm for VM Replacement Framework.
Authors:	Raj Kumar, Vipan¹ vipan.phd@rimt.ac.in, Kumar, Saurabh² director.smarttech@gmail.com
Source:	IAENG International Journal of Computer Science. May2026, Vol. 53 Issue 5, p1728-1739. 12p.
Subjects:	Virtual machine systems, Optimization algorithms, Load balancing (Computer networks), Cloud computing, Artificial neural networks, Mathematical optimization, Energy consumption
Abstract:	The study proposed a VM placement mechanism for a dynamic cloud environment that combines the Firefly Algorithm, Modified Best Fit Decreasing (MBFD), and Deep Neural Networks (DNN). The authors assess the PMs based on energy efficiency, reliability, and workload capacity based on historical data. CPU load balancing is maintained through the Firefly Algorithm, MBFD minimizes idle and execution costs, while DNN helps in selecting options by ranking PMs for optimal VM placement. Compared to the state of the art, the proposed scheme achieves a reduction of 14.88%-16.16% in power consumption and a decrease of 10.46%-12.62% in SLA violations. This performance was achieved as a result of a 13.15%-21.89% reduction in the number of VM migrations using the proposed work in comparison to the existing works. Thus, incorporating optimization strategies on different levels mutually improves energy savings, workload balance, and SLA adherence; therefore, this is a scalable and robust solution for cloud computing. Future enhancements will consider optimizations for network latency, resource contention, and reinforcement learning. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	The study proposed a VM placement mechanism for a dynamic cloud environment that combines the Firefly Algorithm, Modified Best Fit Decreasing (MBFD), and Deep Neural Networks (DNN). The authors assess the PMs based on energy efficiency, reliability, and workload capacity based on historical data. CPU load balancing is maintained through the Firefly Algorithm, MBFD minimizes idle and execution costs, while DNN helps in selecting options by ranking PMs for optimal VM placement. Compared to the state of the art, the proposed scheme achieves a reduction of 14.88%-16.16% in power consumption and a decrease of 10.46%-12.62% in SLA violations. This performance was achieved as a result of a 13.15%-21.89% reduction in the number of VM migrations using the proposed work in comparison to the existing works. Thus, incorporating optimization strategies on different levels mutually improves energy savings, workload balance, and SLA adherence; therefore, this is a scalable and robust solution for cloud computing. Future enhancements will consider optimizations for network latency, resource contention, and reinforcement learning. [ABSTRACT FROM AUTHOR]
ISSN:	1819656X