Empirical prediction models for adaptive resource provisioning in the cloud

Cloud computing allows dynamic resource scaling for enterprise online transaction systems, one of the key characteristics that differentiates the cloud from the traditional computing paradigm. However, initializing a new virtual instance in a cloud is not instantaneous; cloud hosting platforms introduce several minutes delay in the hardware resource allocation. In this paper, we develop prediction-based resource measurement and provisioning strategies using Neural Network and Linear Regression to satisfy upcoming resource demands.Experimental results demonstrate that the proposed technique offers more adaptive resource management for applications hosted in the cloud environment, an important mechanism to achieve on-demand resource allocation in the cloud.

► We develop prediction models to enable proactive resource scaling in the cloud. ► The prediction models incorporate machine learning and sliding window strategies. ► Future utilization is predicted based on history data and current utilization. ► The prediction models yield >80% prediction accuracy for the evaluated workload. ► Increased sliding window size also improves prediction accuracy of the models.