A Stable Idle Time Detection Platform for Real I/O Workloads

It is important to utilize the idle time of a workload to improve the system performance. In the article, we will explore multiple idle time detection methods to predict the idle time of the real I/O workloads. The objective is to build a stable idle time detection platform by investigating the impact of multiple representative methods to pursue a more stable prediction accuracy. The experimental results show that the prediction accuracy of the proposed platform can be stable between 60% and 80%.