Modeling Conceptual Characteristics of Virtual Machines for CPU Utilization Prediction

TL;DR

This paper introduces a neural network model called T-ResNet for predicting CPU utilization of virtual machines in the cloud, based on empirical analysis of Azure workloads, capturing key characteristics like locality and periodicity.

Contribution

It proposes a novel deep learning approach that models conceptual characteristics of VM CPU utilization, improving prediction accuracy over baseline methods.

Findings

T-ResNet outperforms baseline models in RMSE, MAE, and MAPE metrics.

Empirical analysis identifies locality, periodicity, and tendency as key CPU utilization features.

The approach demonstrates effectiveness on real Azure VM workload data.

Abstract

Cloud services have grown rapidly in recent years, which provide high flexibility for cloud users to fulfill their computing requirements on demand. To wisely allocate computing resources in the cloud, it is inevitably important for cloud service providers to be aware of the potential utilization of various resources in the future. This paper focuses on predicting CPU utilization of virtual machines (VMs) in the cloud. We conduct empirical analysis on Microsoft Azure's VM workloads and identify important conceptual characteristics of CPU utilization among VMs, including locality, periodicity and tendency. We propose a neural network method, named Time-aware Residual Networks (T-ResNet), to model the observed conceptual characteristics with expanded network depth for CPU utilization prediction. We conduct extensive experiments to evaluate the effectiveness of our proposed method and the results show that T-ResNet consistently outperforms baseline approaches in various metrics including RMSE, MAE and MAPE.