Self-Adaptive Capacity Controller: A Reinforcement Learning Approach

Interference between co-located VMs may lead to performance fluctuations and degradation. To limit this problem, VMs access to physical resources needs to be controlled to ensure certain degree of isolation among them. This mapping between virtual and physical resources must be performed in a dynamic way so that it can be adaptive to the changing applications requirements, as well as to the different set of co-located VMs. To address this problem we propose a self-adaptive fuzzy Q-learning capacity controller that proactively readjusts the isolation degree based on applications performance. Our evaluation demonstrates a reduction into VMs interference and an increment on the overall utilization, while still ensuring critical applications performance, and providing more resources to non-critical applications.