Bayesian uncertainty modelling for cloud workload prediction

Loading...
Thumbnail Image
Date
2022-07-10
Authors
Rossi, Andrea
Visentin, Andrea
Prestwich, Steven D.
Brown, Kenneth N.
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Research Projects
Organizational Units
Journal Issue
Abstract
Providers of cloud computing systems need to manage resources carefully to meet the desired Quality of Service and reduce waste due to overallocation. An accurate prediction of future demand is crucial to allocate resources to service requests without excessive delays. Current state-of-the-art methods such as Long Short-Term Memory-based models make only point forecasts of demand without considering the uncertainty in their predictions. Forecasting a distribution would provide a more comprehensive picture and inform resource scheduler decisions. We investigate Bayesian Neural Networks and deep learning models to predict workload distribution and evaluate them on the time series forecasting of CPU and memory workload of 8 clusters on the Google Cloud data centre. Experiments show that the proposed models provide accurate demand prediction and better estimations of resource usage bounds, reducing overprediction and total predicted resources, while avoiding underprediction. These approaches have good runtime performance making them applicable for practitioners.
Description
Keywords
Cloud Computing , Bayesian Neural Network , Workload Prediction , Deep Learning , Time Series Forecasting
Citation
Rossi, A., Visentin, A., Prestwich, S. D. and Brown, K. N. (2022) 'Bayesian Uncertainty Modelling for Cloud Workload Prediction', 2022 IEEE 15th International Conference on Cloud Computing (CLOUD), Barcelona, Spain, 10-16 July. doi: 10.1109/CLOUD55607.2022.00018