Clustering-based numerosity reduction for cloud workload forecasting

Thumbnail Image
Rossi, Andrea
Visentin, Andrea
Prestwich, Steven D.
Brown, Kenneth N.
Journal Title
Journal ISSN
Volume Title
Research Projects
Organizational Units
Journal Issue
Finding smaller versions of large datasets that preserve the same characteristics as the original ones is becoming a central problem in Machine Learning, especially when computational resources are limited, and there is a need to reduce energy consumption. In this paper, we apply clustering techniques for wisely selecting a subset of datasets for training models for time series prediction of future workload in cloud computing. We train Bayesian Neural Networks (BNNs) and state-of-the-art probabilistic models to predict machine-level future resource demand distribution and evaluate them on unseen data from virtual machines in the Google Cloud data centre. Experiments show that selecting the training data via clustering approaches such as Self Organising Maps allows the model to achieve the same accuracy in less than half the time, requiring less than half the datasets rather than selecting more data at random. Moreover, BNNs can capture uncertainty aspects that can better inform scheduling decisions, which state-of-the-art time series forecasting methods cannot do. All the considered models achieve prediction time performance suitable for real-world scenarios.
Cloud computing , Workload prediction , Clustering , Bayesian neural network , Deep learning
Rossi, A., Visentin, A., Prestwich, S. and Brown, K.N. (2024) ‘Clustering-based numerosity reduction for cloud workload forecasting’, in I. Chatzigiannakis and I. Karydis (eds) Algorithmic Aspects of Cloud Computing, Lecture Notes in Computer Science, vol 14503, Cham: Springer Nature Switzerland, pp. 115–132. Available at:
Link to publisher’s version
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG. This version of the contribution has been accepted for publication, after peer review but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use