Analyzing Facility Servers Using Random Forest and XGBoost for Optimized Job Allocation

Potula Radha Nishant, Beena B M

2024

Abstract

Computer systems consume huge amount of energy causing higher levels of carbon emissions thus polluting the environment. This study addresses the issue by developing machine learning algorithms to conserve resources across datacentres. The machine learning models have been developed to predict a higher level accuracy focusing job level scheduling. The Random Forest used for job scheduling may result in enhancing performance of green data centres by reducing the energy consumption. Our future research tries to improve the existing resource management solutions focusing on job level characteristics.

Paper Citation

in Harvard Style

Nishant P. and B M B. (2024). Analyzing Facility Servers Using Random Forest and XGBoost for Optimized Job Allocation. In Proceedings of the 2nd International Conference on Intelligent and Sustainable Power and Energy Systems - Volume 1: ISPES; ISBN 978-989-758-756-6, SciTePress, pages 74-81. DOI: 10.5220/0013577100004639

in Bibtex Style

@conference{ispes24,
author={Potula Radha Nishant and Beena B M},
title={Analyzing Facility Servers Using Random Forest and XGBoost for Optimized Job Allocation},
booktitle={Proceedings of the 2nd International Conference on Intelligent and Sustainable Power and Energy Systems - Volume 1: ISPES},
year={2024},
pages={74-81},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013577100004639},
isbn={978-989-758-756-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Intelligent and Sustainable Power and Energy Systems - Volume 1: ISPES
TI - Analyzing Facility Servers Using Random Forest and XGBoost for Optimized Job Allocation
SN - 978-989-758-756-6
AU - Nishant P.
AU - B M B.
PY - 2024
SP - 74
EP - 81
DO - 10.5220/0013577100004639
PB - SciTePress