A Hybrid Optimization Algorithm for Efficient Virtual Machine Migration and Task Scheduling Using a Cloud-Based Adaptive Multi-Agent Deep Deterministic Policy Gradient Technique DOI Open Access

Et al. Gurpreet Singh Panesar

International Journal on Recent and Innovation Trends in Computing and Communication, Год журнала: 2023, Номер 11(10), С. 742 - 756

Опубликована: Ноя. 2, 2023

This To achieve optimal system performance in the quickly developing field of cloud computing, efficient resource management—which includes accurate job scheduling and optimized Virtual Machine (VM) migration—is essential. The Adaptive Multi-Agent System with Deep Deterministic Policy Gradient (AMS-DDPG) Algorithm is used this study to propose a cutting-edge hybrid optimization algorithm for effective virtual machine migration task scheduling. An sophisticated combination War Strategy Optimization (WSO) Rat Swarm Optimizer (RSO) algorithms, Iterative Concept (ICWRS) foundation technique. Notably, ICWRS optimizes an amazing 93% accuracy, especially load balancing, scheduling, migration. VM flexibility efficiency are greatly improved by AMS-DDPG technology, which uses powerful deterministic policy gradient deep reinforcement learning. By assuring best possible allocation, method enhances decision-making even more. Performance cloud-based virtualized systems significantly enhanced our method, combines learning multi-agent coordination. Extensive tests that include detailed comparison conventional techniques verify effectiveness suggested strategy. As consequence, approach successful. findings show significant improvements efficiency, shorter completion times, optimum utilization. Cloud-based have unrealized potential synergistic optimization, as shown integration inside framework. Enabling high-performing sustainable computing infrastructure can adapt changing needs modern paradigms made strategic attained via careful computational

Язык: Английский

An energy-aware virtual machine placement method in cloud data centers based on improved Harris Hawks optimization algorithm DOI

Zahra Karimi Mehrabadi,

Mehdi Fartash, Javad Akbari Torkestani

и другие.

Computing, Год журнала: 2025, Номер 107(6)

Опубликована: Май 23, 2025

Язык: Английский

Процитировано

0
Recent Improvements in Cloud Resource Optimization with Dynamic Workloads using Machine Learning DOI

K Nagalatha,

G. Anil Kumar

SSRN Electronic Journal, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

Cloud computing is a crucial concept in contemporary computing, providing adaptable and expandable resources to accommodate the changing demands of different applications. Efficiently managing dynamic workloads cloud huge problem owing intricacies environment. Advances machine learning have enabled new methods for improving allocation administration resources. This article provides comprehensive examination current research advancements optimizing through application learning. The text reviews many approaches, algorithms, frameworks suggested literature tackle complex elements resource optimization systems. analysis an in-depth fundamental ideas, difficulties, patterns this field, emphasizing advantages drawbacks methods. study investigates how such as supervised learning, unsupervised reinforcement evolutionary algorithms might improve usage, performance, cost-effectiveness settings. examines various data sources characteristics may be used estimate allocate accurately. It explores big analytics predictive modeling approaches choices. assesses usefulness efficiency strategies settings by comparing experimental findings case examples from literature. focuses on lowering latency, minimizing operating expenses. suggests potential areas future development, hybrid methods, multi-objective techniques, adaptive mechanisms issues optimization. offers significant insights developments trends using thorough comprehension latest advancements, obstacles, possibilities field combining examining inputs.

Язык: Английский

Процитировано

0
A Hybrid Optimization Algorithm for Efficient Virtual Machine Migration and Task Scheduling Using a Cloud-Based Adaptive Multi-Agent Deep Deterministic Policy Gradient Technique DOI Open Access

Et al. Gurpreet Singh Panesar

International Journal on Recent and Innovation Trends in Computing and Communication, Год журнала: 2023, Номер 11(10), С. 742 - 756

Опубликована: Ноя. 2, 2023

This To achieve optimal system performance in the quickly developing field of cloud computing, efficient resource management—which includes accurate job scheduling and optimized Virtual Machine (VM) migration—is essential. The Adaptive Multi-Agent System with Deep Deterministic Policy Gradient (AMS-DDPG) Algorithm is used this study to propose a cutting-edge hybrid optimization algorithm for effective virtual machine migration task scheduling. An sophisticated combination War Strategy Optimization (WSO) Rat Swarm Optimizer (RSO) algorithms, Iterative Concept (ICWRS) foundation technique. Notably, ICWRS optimizes an amazing 93% accuracy, especially load balancing, scheduling, migration. VM flexibility efficiency are greatly improved by AMS-DDPG technology, which uses powerful deterministic policy gradient deep reinforcement learning. By assuring best possible allocation, method enhances decision-making even more. Performance cloud-based virtualized systems significantly enhanced our method, combines learning multi-agent coordination. Extensive tests that include detailed comparison conventional techniques verify effectiveness suggested strategy. As consequence, approach successful. findings show significant improvements efficiency, shorter completion times, optimum utilization. Cloud-based have unrealized potential synergistic optimization, as shown integration inside framework. Enabling high-performing sustainable computing infrastructure can adapt changing needs modern paradigms made strategic attained via careful computational

Язык: Английский

Процитировано

0