Scheduling cloud capacity for Time- Varying customer demand
Brian Bouterse, Harry G. Perros · 2012
As utility computing resources become more ubiquitous, service providers increasingly look to the cloud for an in-full or in-part infrastructure to serve utility computing customers on demand. Given the costs associated with cloud infrastructure, dynamic scheduling of cloud resources can significantly lower costs while providing an acceptable service level. We investigated several methods for predicting the required cloud capacity in the presence of time-varying customer demand of application environments. We evaluated and compared their performance, using historical data of the Virtual Computing Laboratory (VCL) at North Carolina State University. We show that a simple heuristic, whereby we continuously maintain a fixed reserve capacity, performs better than the other methods.