Dynamic Task Scheduling Using Machine Learning and Enhanced Fuzzy Logic System for Efficient Resource Utilization in Virtual Cloud

Panchagnula Kamakshi Thai, Shanker Chandre

2025

Abstract

Virtual clouds need intelligent task scheduling systems because their limited resources become more efficient through workload-based scheduling strategies. Fuzzy logic systems offer the best solutions for handling tasks in cloud computing because they can deal with uncertain situations and changing workloads and resources. The integration of heuristic interpolated models and machine learning algorithms achieves optimized task scheduling while distributing resources evenly and shortening execution duration. Machine learning uses supervised learning to predict resources and reinforcement learning to adjust decisions, helping to construct flexible and accurate execution patterns. An improved version of fuzzy logic contains smart scheduling functionality that adapts priority settings based on both mission-dependent needs along external operational factors such as execution period and urgency level, as well as system resources and system utilization. Enhanced fuzzy logic systems (EFLS) is one of the models used in the research to automatically change schedules based on environmental factors and changes in job demand. The system constructs exhaustive membership functions that show overlapping job priority areas and limits on resources using its method. The system contains four major modules consisting of submission tracking, resource monitoring alongside predictive capabilities, and optimized decision management that permits real-time capability. The performance assessments reveal significant positive outcomes in all three areas: makespan, task completion rates, and resource utilization as compared to conventional methods. The method demonstrates how virtualized cloud systems can implement scalable, efficient, adaptive task management.

Paper Citation

in Harvard Style

Thai P. and Chandre S. (2025). Dynamic Task Scheduling Using Machine Learning and Enhanced Fuzzy Logic System for Efficient Resource Utilization in Virtual Cloud. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 816-822. DOI: 10.5220/0013890400004919

in Bibtex Style

@conference{icrdicct`2525,
author={Panchagnula Thai and Shanker Chandre},
title={Dynamic Task Scheduling Using Machine Learning and Enhanced Fuzzy Logic System for Efficient Resource Utilization in Virtual Cloud},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={816-822},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013890400004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Dynamic Task Scheduling Using Machine Learning and Enhanced Fuzzy Logic System for Efficient Resource Utilization in Virtual Cloud
SN - 978-989-758-777-1
AU - Thai P.
AU - Chandre S.
PY - 2025
SP - 816
EP - 822
DO - 10.5220/0013890400004919
PB - SciTePress