Forecasting virtual machine resource utilization in cloud computing: a hybrid artificial intelligence approach

Abstract

Cloud computing has transformed the management of IT infrastructures by providing scalable, flexible, and cost-effective solutions. However, efficient resource management in cloud environments remains a significant challenge, as over-provisioning or under-provisioning of resources can lead to unnecessary costs or degraded performance. Accurate forecasting of virtual machine (VM) resource utilization is crucial for optimizing resource allocation, reducing operational expenses, and ensuring compliance with service level agreements (SLAs). This study aims to address these challenges by developing a hybrid forecasting model that combines the strengths of auto regressive integrated moving average (ARIMA), linear regression (LR), and long short-term memory (LSTM) techniques. By integrating these methods, our model provides more accurate predictions and better adaptability to various workload patterns, helping cloud service providers and users to make informed decisions about resource allocation, ultimately reducing costs. The data was collected from multiple EC2 instances and processed using amazon web services (AWS) Glue with Spark. The experimental results demonstrate that the hybrid model outperforms individual models such as ARIMA, LR, and LSTM in terms of accuracy for forecasting memory, CPU, and disk utilization, offering a more effective solution for managing cloud resources efficiently.