Towards a Biologically Inspired Soft Switching Approach for Cloud Resource Provisioning

Abstract

Cloud elasticity augments applications to dynamically adapt to changes in demand by acquiring or releasing computational resources on the fly. Recently, we developed a framework for cloud elasticity utilizing multiple feedback controllers simultaneously, wherein, each controller determines the scaling action with different intensity, and the selection of an appropriate controller is realized with a fuzzy inference system. In this paper, we aim to identify the similarities between cloud elasticity and action selection mechanism in the animal brain. We treat each controller in our previous framework as an action, and propose a novel bioinspired, soft switching approach. The proposed methodology integrates a basal ganglia computational model as an action selection mechanism. Initial experimental results demonstrate the improved potential of the basal ganglia-based approach by enhancing the overall system performance and stability.