PSO-Based Ensemble Meta-Learning Approach for Cloud Virtual Machine Resource Usage Prediction

Leka, Habte Lejebo; Zhang, Fengli; Kenea, Ayantu Tesfaye; Hundera, Negalign Wake; Tohye, Tewodros Gizaw; Tegene, Abebe Tamrat

doi:10.3390/sym15030613

Cited by 8 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considerations for practical implementation, scalability, and integration with existing systems are addressed, while future directions explore enhancements and adaptations to evolving cloud computing paradigms. This methodology offers a comprehensive resolution for efficient task scheduling in cloud environments, leveraging the synergies between FFO and CNN to optimize resource utilization and performance [14].…”

Section: Proposed Methodology: Maximizing Resource Utilization In Clo...mentioning

confidence: 99%

Optimizing Resource Allocation in Cloud Environments using Fruit Fly Optimization and Convolutional Neural Networks

Gongada,

Desale,

Ghodake

et al. 2024

ijacsa

View full text Add to dashboard Cite

Cloud computing environments play a crucial role in modern computing infrastructures, offering scalability, flexibility, and cost-efficiency. However, optimizing resource utilization and performance in such dynamic and complex environments remains a significant challenge. This study addresses this challenge by proposing a novel framework that integrates Fruit Fly Optimization (FFO) with Convolutional Neural Networks (CNN) for task scheduling optimization. The background emphasizes the importance of efficient resource allocation and management in cloud computing to meet increasing demands for computational resources while minimizing costs and enhancing overall system performance. The objective of this research is to develop a comprehensive framework that leverages the complementary strengths of FFO and CNN to address the shortcomings of traditional task scheduling approaches. The novelty of the proposed framework lies in its integration of optimization techniques with advanced data analysis methods, enabling dynamic and adaptive task allocation based on real-time workload patterns. The proposed framework is thoroughly evaluated using historical workload data, and results demonstrate significant improvements over traditional methods. Specifically, the FFO-CNN framework achieves average response times ranging from 120 to 180 milliseconds, while maintaining high resource utilization rates ranging from 90% to 98%. These results highlight the effectiveness of the FFO-CNN framework in enhancing resource utilization and performance in cloud computing environments. This research contributes to advancing the state-of-the-art in cloud resource management by introducing a novel approach that combines optimization and data analysis techniques. The proposed framework offers a promising solution to the challenges of resource allocation and task scheduling in cloud computing environments, paving the way for more efficient and sustainable cloud infrastructures in the future.

show abstract

Section: Proposed Methodology: Maximizing Resource Utilization In Clo...mentioning

confidence: 99%

Optimizing Resource Allocation in Cloud Environments using Fruit Fly Optimization and Convolutional Neural Networks

Gongada,

Desale,

Ghodake

et al. 2024

ijacsa

View full text Add to dashboard Cite

show abstract

“…This challenges the ensemble models to consider such techniques, which results in the best accuracy and productivity metrics. 7,8 Therefore, this paper has devised an ensemble technique for host load prediction using diverse time-series forecasting models.…”

Section: Motivation and Our Contributionsmentioning

confidence: 99%

“…H. L. Leka et al 8 suggested a particle swarm optimization (PSO)‐based ensemble meta‐learning workload forecasting approach. The proposed model employs a blended ensemble learning strategy to merge three recurrent neural networks (RNNs), followed by a dense neural network layer.…”

Section: Related Workmentioning

confidence: 99%

“…More profoundly, one prediction model would effectively predict some trends, but the same would be imprecise in other trends due to its dynamic performance. This challenges the ensemble models to consider such techniques, which results in the best accuracy and productivity metrics 7,8 . Therefore, this paper has devised an ensemble technique for host load prediction using diverse time‐series forecasting models. Most existing works primarily focus on the over‐utilization of hosts, lacking the importance of tracking under‐utilization parameters through intelligent prediction methods 9 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Auto‐scaling for Host Load Prediction through VM migration in Cloud

Verma,

Bala

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe expeditious deployment of Cloud applications and services on wide‐ranging Cloud Data Centres (CDC) gives rise to the utilization of many resources. Moreover, by the increase in resource utilization, virtualization also greatly impacts achieving desired performance. The major challenges in virtualization are detecting over‐utilized or under‐utilized hosts at the right time and the proper scaling of Virtual Machines (VM) on the accurate host. Auto‐scaling in Cloud Computing allows the service providers to scale up or down the resources automatically and provides on‐demand computing power and storage capacities. Effective utilization and autonomous scaling of resources eventually reduce the load, energy consumption, and operating costs. In this paper, an efficient auto‐scaling approach for predicting host load through VM migration has been proposed. The ensemble method using different time‐series forecasting models has been proposed to forecast the approaching workload on the host. Based on this predicted load, different algorithms have been devised to detect over‐utilized and under‐utilized hosts and VMs can be migrated. The designed approach has been validated by experimentation on a real‐time Google cluster dataset. The proposed technique significantly improves average CPU utilization and reduces over‐utilization and under‐utilization. It also minimizes response time, service level agreement violations, and the slighter number of migrations and scaling overhead.

show abstract

“…Second, the cloud environment is dynamic, task arrivals, departures, and resource requirements are always changing. This dynamic nature renders the requirement for task scheduling algorithms that can be flexible and adaptive in real time to quickly adjust to changing demands [7]. Finally, to accomplish load balancing and maximize resource utilization, efficient task scheduling that relies on the appropriate distribution and application of resources is needed.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approach for Workload Prediction and Balancing in Cloud Computing

Karimunnisa,

Pachipala

2024

IJACSA

View full text Add to dashboard Cite

Cloud Computing voted as one of the most revolutionized technologies serving huge user demand engrosses a prominent place in research. Despite several parameters that influence the cloud performance, factors like Workload prediction and scheduling are triggering challenges for researchers in leveraging the system proficiency. Contributions by practitioners given workload prophesy left scope for further enhancement in terms of makespan, migration efficiency, and cost. Anticipating the future workload in due to avoid unfair allocation of cloud resources is a crucial aspect of efficient resource allocation. Our work aims to address this gap and improve efficiency by proposing a Deep Max-out prediction model, which predicts the future workload and facilitates workload balancing paving the path for enhanced scheduling with a hybrid Tasmanian Devil-assisted Bald Eagle Search (TES) optimization algorithm. The results evaluated proved that the TES scored efficiency in makespan with 16.342%, and migration efficiency of 14.75% over existing approaches like WACO, MPSO, and DBOA (Weighted Ant Colony Optimization Modified Particle Swarm Optimization, Discrete Butterfly Optimization Algorithm). Similarly, the error analysis during the evaluation of prediction performance has been figured out using different approaches like MSE, RMSE, MAE, and MSLE, among which our proposed method overwhelms with less error than the traditional methods.

show abstract

PSO-Based Ensemble Meta-Learning Approach for Cloud Virtual Machine Resource Usage Prediction

Cited by 8 publications

References 46 publications

Optimizing Resource Allocation in Cloud Environments using Fruit Fly Optimization and Convolutional Neural Networks

Optimizing Resource Allocation in Cloud Environments using Fruit Fly Optimization and Convolutional Neural Networks

Efficient Auto‐scaling for Host Load Prediction through VM migration in Cloud

Deep Learning Approach for Workload Prediction and Balancing in Cloud Computing

Contact Info

Product

Resources

About