Machine Learning Based Resource Utilization Prediction in the Computing Continuum
Authors:
- 6 November 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 219-224
Abstract
This paper presents UtilML, a novel approach for tackling resource utilization prediction challenges in the computing continuum. UtilML leverages Long-Short-Term Memory (LSTM) neural networks, a machine learning technique, to forecast resource utilization accurately. The effectiveness of UtilML is demonstrated through its evaluation of data extracted from a real GPU cluster in a computing continuum infrastructure comprising more than 1800 computing devices. To assess the performance of UtilML, we compared it with two related approaches that utilize a Baseline-LSTM model. Furthermore, we analyzed the LSTM results against User-Predicted values provided by GPU cluster owners for task deployment with estimated allocation values. The results indicate that UtilML outperformed user predictions by 2% to 27% for CPU utilization prediction. For memory prediction, UtilML variants excelled, showing improvements of 17% to 20% compared to user predictions.Keywords
This publication has 19 references indexed in Scilit:
- Matching-based Scheduling of Asynchronous Data Processing Workflows on the Computing Continuum2022
- A hybrid CNN-LSTM model for predicting server load in cloud computingThe Journal of Supercomputing, 2022
- An intelligent task offloading algorithm (iTOA) for UAV edge computing networkDigital Communications and Networks, 2020
- Improving Resource Utilization in Data Centers using an LSTM-based Prediction Model2019
- Mean Absolute Percentage Error for regression modelsNeurocomputing, 2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Decision trees: a recent overviewArtificial Intelligence Review, 2011
- Wiley Series in Probability and Statistics2008
- Random ForestsMachine Learning, 2001
- Monte Carlo theory and practiceReports on Progress in Physics, 1980