Forecasting workload in cloud computing: towards uncertainty-aware predictions and transfer learning

Forecasting workload in cloud computing: towards uncertainty-aware predictions and transfer learning

연구 분야: Networking

학회: Cluster Computing

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.