Forecasting workload in cloud computing: towards uncertainty-aware predictions and transfer learning
Bibliographic record
Abstract
Abstract Accurately forecasting workload demand in cloud computing environments is essential for optimizing resource allocation, minimizing costs, and ensuring reliable service quality. As cloud computing scales to meet the needs of diverse applications - from AI and machine learning to data-intensive analytics - predictive models play a critical role in dynamically managing multiple resources. Traditional models provide limited guidance for decision-makers since they are typically univariate models, ignoring the prediction of the interplay between multiple resources, and do not account for the uncertainty of their predictions, preventing resource management from acting promptly according to such uncertainty to ensure specific target service level requirements. To address these limitations, we introduce univariate and bivariate Bayesian deep learning models that predict future workload demand of one and multiple resources respectively, while quantifying the uncertainty of their predictions. In particular, our approach leverages Hybrid Bayesian Neural Networks and probabilistic Long Short-Term Memory models, enhanced with architecture modifications to handle complex, multivariate cloud workload patterns. Moreover, we investigate fine-tuning-based transfer learning methods to enhance their adaptability in real-world cloud scenarios where new data centres with different workload characteristics operate. We validate our models on extensive datasets from Google and Alibaba cloud clusters. Results show that modelling the uncertainty of predictions positively impacts performance, especially on service level metrics, because uncertainty quantification can be tailored to desired target service levels that are critical in cloud applications. Moreover, transfer learning benefits performance in scenarios where models are built on data from the same provider.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".