BoostPred: An Automatic Demand Predictor for the Cloud

Abstract

As Cloud Computing adoption by enterprise customers grows, so too the need for optimal utilisation of their virtual resources. Likewise, cost pressures on cloud providers with a utility business model e.g. Amazon Web Services, would also need to optimise the utilisation of their physical infrastructure. Clearly, the ability to predict demand would be valuable. We introduce BoostPred, an automatic demand predictor for the cloud. BoostPred's design goals are to require no human expert intervention in making accurate predictions from noisy realworld demand signals. We evaluate the accuracy of BoostPred using noisy real-world signals which reveal its potential and current shortcomings.

Queue Based Q-Learning for Efficient Resource Provisioning in Cloud Data Centers

“…A novel self-adaptive and sensitivity awareness quality of service model using artificial neural network and auto regressive moving average was proposed by Chen & Bahsoon, (2013) using RuBis benchmark and FIFA 1998 workload. BoostPred, an automatic demand predictor for cloud was proposed by Wong & Davis (2011). A model has been designed by the authors to predict the workload demand without any human intervention.…”