Performance and energy savings trade-off with uncertainty-aware cloud workload forecasting
| dc.contributor.author | Carraro, Diego | en |
| dc.contributor.author | Rossi, Andrea | en |
| dc.contributor.author | Visentin, Andrea | en |
| dc.contributor.author | Prestwich, Steven D. | en |
| dc.contributor.author | Brown, Kenneth N. | en |
| dc.contributor.funder | Science Foundation Ireland | en |
| dc.contributor.funder | European Regional Development Fund | en |
| dc.contributor.funder | Horizon 2020 Framework Programme | en |
| dc.date.accessioned | 2023-12-04T12:45:53Z | |
| dc.date.available | 2023-12-04T12:45:53Z | |
| dc.date.issued | 2023-10-10 | en |
| dc.description.abstract | Cloud managers typically leverage future workload predictions to make informed decisions on resource allocation, where the ultimate goal of the allocation is to meet customers’ demands while reducing the provisioning cost. Among several workload forecasting approaches proposed in the literature, uncertainty-aware time series analysis solutions are desirable in cloud scenarios because they can predict the distribution of future demand and provide bounds associated with a given service level set by the resource manager. The effectiveness of uncertainty-based workload predictions is normally assessed in terms of accuracy metrics (e.g. MAE) and service level (e.g. Success Rate), but the effect on the resource provisioning cost is under investigated. We propose an evaluation framework to assess the impact of uncertainty-aware predictions on the performance vs cost trade-off, where we express the cost in terms of energy savings. We illustrate the framework’s effectiveness by simulating two real-world cloud scenarios where an optimizer leverages workload predictions to allocate resources to satisfy a desired service level while minimizing energy waste. Offline experiments compare representative uncertainty-aware models and a new model (HBNN++) that we propose, which predict a cluster trace’s GPU demand. We show that more effective uncertainty modelling can save energy without violating desired service level targets and that model performance varies depending on the specific details of the allocation scheme, server and GPU energy costs. | en |
| dc.description.status | Peer reviewed | en |
| dc.description.version | Accepted Version | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | Carraro, D., Rossi, A., Visentin, A., Prestwich, S. and Brown, K. N. (2023) ‘Performance and Energy Savings Trade-Off with Uncertainty-Aware Cloud Workload Forecasting’, The Cloud-Edge Continuum Workshop 2023 (CEC'23), IEEE ICNP'23, the 31st IEEE International Conference on Network Protocols, 10 October, Reykjavik, Iceland. pp. 1–6. Available at: https://doi.org/10.1109/ICNP59255.2023.10355570 | en |
| dc.identifier.doi | https://doi.org/10.1109/ICNP59255.2023.10355570 | en |
| dc.identifier.endpage | 6 | en |
| dc.identifier.startpage | 1 | en |
| dc.identifier.uri | https://hdl.handle.net/10468/15294 | |
| dc.language.iso | en | en |
| dc.publisher | IEEE | en |
| dc.relation.ispartof | The Cloud-Edge Continuum Workshop 2023 (CEC'23) | en |
| dc.relation.ispartof | IEEE ICNP'23, the 31st IEEE International Conference on Network Protocols | en |
| dc.relation.project | info:eu-repo/grantAgreement/SFI/SFI Centres for Research Training Programme::Data and ICT Skills for the Future/18/CRT/6223/IE/SFI Centre for Research Training in Artificial Intelligence/ | en |
| dc.relation.project | info:eu-repo/grantAgreement/SFI/SFI Research Centres Programme::Phase 2/12/RC/2289-P2s/IE/INSIGHT Phase 2/ | en |
| dc.relation.project | info:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/ | en |
| dc.relation.project | info:eu-repo/grantAgreement/EC/HE::HORIZON-AG/101070141/EU/Green responsibLe privACy preservIng dAta operaTIONs/GLACIATION | en |
| dc.relation.project | info:eu-repo/grantAgreement/EC/H2020::RIA/952215/EU/Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization/TAILOR | en |
| dc.rights | © 2023 IEEE | en |
| dc.subject | Cloud computing | en |
| dc.subject | Energy saving | en |
| dc.subject | Deep learning | en |
| dc.subject | Workload prediction | en |
| dc.subject | Uncertainty | en |
| dc.subject | Time series forecasting | en |
| dc.title | Performance and energy savings trade-off with uncertainty-aware cloud workload forecasting | en |
| dc.type | Conference item | en |
