A Cloud QoS-driven Scheduler based on Deep Reinforcement Learning

Abstract

Task scheduling is one of the most challenging issues in cloud management. Because it is a decision-making problem, Reinforcement Learning has been utilized by several works to build an intelligent and efficient cloud task scheduler. However, while resources utilization was used as the key factor to schedule tasks in most studies, another crucial requirement for cloud task scheduling which is tasks' Quality-of-Service (QoS) guarantee has not been approached yet. Therefore, in this paper, we present a Deep Reinforcement Learning-based task scheduler which focuses on QoS guarantee.