Cloud-Based Load Balancing using an Enhanced Weighted Round Robin Algorithm

View at publisher Summarise with VIRAT
Authors: Suma Surasingh, Pradeep Sudhakaran, Deepika P S
Cited by: 0
References: 20

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The study presents a cloud-based load balancing architecture using an Enhanced Weighted Round Robin (EWRR) algorithm to optimize job allocation across virtual machines via intelligent weight assignment and queue prioritization. The solution employs a GitHub-hosted dataset that includes structured task flows and weighted scheduling records to replicate authentic cloud workload scenarios. The performance assessment used typical metrics such as Response Time (RT), Throughput (TP), Makespan (MS), Load Imbalance Degree (LID), VM Utilisation (U), and SLA Violation Rate (SVR). The experimental findings indicate an average reaction time of 48.6 ms, a throughput of 220 jobs per second, and a makespan of 310 seconds for batch execution. The load imbalance decreased to 0.12, indicating enhanced workload homogeneity, while VM utilization reached 91.4%, demonstrating effective resource utilization. The SLA violation rate was restricted to 2.8%, indicating robust adherence to service parameters. Response time analysis demonstrated the greatest accuracy in assessing scheduling efficacy across all tests. The quantitative findings confirm the improved algorithm's capacity to provide reliable, equitable, and performance-oriented job execution. The suggested method significantly enhances scheduling efficiency in scalable cloud settings while preserving operational dependability and service quality.

Fields of Study & Subjects

Cloud Computing and Resource Management Distributed and Parallel Computing Systems Energy Efficiency in Computing

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1607–1612
Publication date
21 January 2026
Language
EN