Efficiently managing cloud infrastructure, especially in environments of large cloud providers or hyperscalers, requires optimizing the use of physical resources to minimize costs and maximize performance. Selecting the right virtual machine (VM) sizes is crucial for achieving cost efficiency in these dynamic settings. However, traditional VM allocation and scheduling approaches often fail to account for the fluctuating and unpredictable nature of VM utilization, leading to inefficiencies such as resource over- or under-provisioning. High-quality interval prediction helps accurately capture uncertainty in cloud resource demand, supporting cloud operators in efficient instance provisioning.
As an effective and reliable framework for constructing prediction intervals (PIs), conformal prediction (CP) is utilized for mid- and long-term forecasting tasks in cloud computing environments. This study proposes a new data-driven PI construction approach using bootstrapping conformal prediction for modern, dynamic, data-driven Right-sizing Recommendations (RSR) to enhance provisioning for diverse application workloads on hyperscalers.
By learning workload utilization patterns, identifying correlations across multiple time series, and predicting medium- to long-term utilization trends, this research aims to improve the efficiency of cloud and data center operations through an AI/ML-based provisioning pipeline. Our study demonstrates that AI-driven models, powered by machine learning regression techniques and evaluated using backtesting, achieve promising forecasting results for cloud resource utilization. Additionally, we rank the selected models to identify top-performing approaches for long-life VM candidates. The proposed framework enhances right-sizing recommendations and supports more cost-effective resource allocation in dynamic cloud environments.
Blogger's Review: This paper presents an innovative resource optimization method by combining conformal prediction with machine learning, showcasing practical application potential. Optimizing resource allocation in dynamic cloud environments can reduce costs and enhance performance, making it a topic worth following. Future research could explore combining more models and their applicability in different scenarios.