Leveraging Machine and Deep Learning Models for Load Balancing Strategies in Cloud Computing DOI Open Access

C Thilagavathy

Indian Journal of Science and Technology, Journal Year: 2024, Volume and Issue: 17(45), P. 4722 - 4731

Published: Dec. 14, 2024

Objectives: To evaluate the efficiency of task prediction and resource allocation for load balancing (LB) in cloud environment using combined approach like random Forest(RF) Particle Swarm optimization Convolutional Neural Networks (PSO-CNN) allocation. Methods: The ensemble present study uses Random Forest (RF), a machine learning (ML) model Optimization (PSO+CNN), bio-inspired algorithm Deep Learning (DL) employs PSO techniques to optimize CNN order address investigation algorithmic DL. results show that suggested outperforms other models CNN-LSTM(Long Short-term memory), CNN-GRU(Gated Recurrent Unit), –SVM(Support Vector Machine) increase performance efficacy systems. experiment is implemented Python assessed Google Cluster dataset accessible public. Findings: use ML DL are found be more efficient infrastructure than conventional methods. examines RF, hybrid RF-PSO-CNN models. accuracy, precision, F1. Score metrics were used assess classification recommended them with an accuracy 90% contrasted methods CNN-LSTM, CNN- GRU PSO-SVM. As result, both assessment consumption proposed performs effectively. Novelty: novel suggests LB Computing. predicted by RF assigned chosen CNN, thereby improving Most research any two or either predicting tasks scheduled which allocate. combination (RF) method, (PSO) (CNN) concurrently it effectiveness context. Keywords: Load Balancing (LB), Task scheduling, Resource allocation, (CNN),

Language: Английский

Efficient algorithm for error optimization and resource prediction to mitigate cost and energy consumption in a cloud environment DOI
Sangeeta Sangani, Rudragoud Patil,

R. H. Goudar

et al.

International Journal of Information Technology, Journal Year: 2024, Volume and Issue: 16(4), P. 2187 - 2197

Published: Feb. 24, 2024

Language: Английский

Citations

6
An efficient machine learning based CPU scheduler for heterogeneous multicore processors DOI

Sugariya Firdous Allaqband,

Mir Nazish,

Saltanat Firdous Allaqband

et al.

International Journal of Information Technology, Journal Year: 2024, Volume and Issue: unknown

Published: May 24, 2024

Language: Английский

Citations

4
A reinforcement learning based backup queue strategy for reliable and fault tolerant scheduling DOI

R. Archana,

Krishan Kumar

International Journal of Information Technology, Journal Year: 2025, Volume and Issue: unknown

Published: March 31, 2025

Language: Английский

Citations

0
The IoT resource allocation and scheduling using Elephant Herding Optimization (EHO-RAS) in IoT environment DOI

Umaa Mageswari,

Gerard Deepak,

A. Santhanavijayan

et al.

International Journal of Information Technology, Journal Year: 2024, Volume and Issue: 16(5), P. 3283 - 3293

Published: March 27, 2024

Language: Английский

Citations

3
A heterogeneous multi-core architectural model for video scheduling for transcoding in clouds DOI
Kalyan Baital, Amlan Chakrabarti

International Journal of Information Technology, Journal Year: 2024, Volume and Issue: 16(5), P. 2831 - 2845

Published: April 20, 2024

Language: Английский

Citations

3
Pathways of SME globalization: unveiling the role of niche market leadership and intelligent cloud-based accounting information system DOI Creative Commons
Pham Quang Huy, Vu Kien Phuc

International Journal of Information Technology, Journal Year: 2025, Volume and Issue: unknown

Published: March 7, 2025

Language: Английский

Citations

0
Comparative Study and Analysis of Cloud Container Technology DOI
E. Saravana Kumar, Raghu Ramamoorthy, Selvaraj Kesavan

et al.

2022 9th International Conference on Computing for Sustainable Global Development (INDIACom), Journal Year: 2024, Volume and Issue: unknown, P. 1681 - 1686

Published: Feb. 28, 2024

The advent of digital transformation has revolutionized the way businesses operate. Applications have become focal point this transformation, shifting focus from being organization-centric to user-centric. To realize full potential businesses, high-quality, secure, and agile applications are essential. Containers a cutting-edge invention in world virtualization, gaining immense popularity recent years. They replaced traditional business continuity solutions now used address highly demanding needs. Multiple containers orchestration frameworks available, both as standalone cloud-based services. However, developers industry experts face challenges identifying evaluating appropriate for their application selected tools may not always be feasible due lack available features, inability provide agility, platform support. When deployed across multiple containers, coordination management among container clusters critical. Since play pivotal role edge deployment, cloud-native, continuous integration, it is vital centralized proper re-source scheduling. This paper discusses compares emerging platforms cloud-centric frameworks, highlighting involved.

Language: Английский

Citations

2
A fusion of binary grey wolf optimization algorithm with opposition and weighted positioning for feature selection DOI
Ashutosh Tripathi, Kusum Kumari Bharti, Mohona Ghosh

et al.

International Journal of Information Technology, Journal Year: 2023, Volume and Issue: 15(8), P. 4469 - 4479

Published: Sept. 14, 2023

Language: Английский

Citations

4
A Novel Fault-Tolerant Aware Task Scheduler Using Deep Reinforcement Learning in Cloud Computing DOI Creative Commons

Mallu Shiva Rama Krishna,

Sudheer Mangalampalli

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(21), P. 12015 - 12015

Published: Nov. 3, 2023

Task scheduling poses a wide variety of challenges in the cloud computing paradigm, as heterogeneous tasks from resources come onto platforms. The most important challenge this paradigm is to avoid single points failure, various users are running at provider, and it very improve fault tolerance maintain negligible downtime order render services range customers around world. In paper, tackle challenge, we precisely calculated priorities for virtual machines (VMs) based on unit electricity cost these fed scheduler. This scheduler modeled using deep reinforcement learning technique which known DQN model make decisions generate schedules optimally VMs research extensively conducted Cloudsim. research, real-time dataset Google Cloud Jobs used given input algorithm. carried out two phases by categorizing regular or large with fixed varied both datasets. Our proposed DRFTSA compared existing state-of-the-art approaches, i.e., PSO, ACO, GA algorithms, results reveal that minimizes makespan GA, ACO 30.97%, 35.1%, 37.12%, rates failure 39.4%, 44.13%, 46.19%, energy consumption 18.81%, 23.07%, 28.8%, respectively, datasets VMs.

Language: Английский

Citations

4
Secure data transmission in cloud computing using a cyber-security trust model with multi-risk protection scheme in smart IOT application DOI

Torana Kamble,

Madhuri Ghuge,

Ritu Jain

et al.

Cluster Computing, Journal Year: 2024, Volume and Issue: 28(2)

Published: Nov. 26, 2024

Language: Английский

Citations

1