Cloud Resource Allocation from the User Perspective: A Bare-Bones Reinforcement Learning Approach

Cloud computing enables effortless access to a seemingly infinite shared pool of resources, on a pay-per-use basis. As a result, a new challenge has emerged: designing control mechanisms to precisely meet the actual workload requirements of cloud applications in an online manner. To this end, a variety of complex resource management issues have to be addressed, because workloads in the cloud are of a dynamic and heterogeneous nature, and traditional algorithms do not cope well within this context. In this work, we adopt the point of view of the user of a cloud infrastructure and focus on the task of controlling leased resources. We formulate this task as a Reinforcement Learning problem and we simulate the decision-making process of a controller implementing the Q-learning algorithm. We conduct an experimental study, the outcomes of which offer valuable insight into the advantages and shortcomings of using Reinforcement Learning to implement such adaptive cloud resource controllers.