Cloud Workload Prediction and Generation Models

• Gilles Madi Wamba LS2N / IMT Atlantique
• Yunbo Li CNRS / IRISA / IMT Atlantique
• Anne-Cécile Orgerie CNRS / IRISA
• Nicolas Beldiceanu IMT Atlantique
• Jean-Marc Menaud IMT Atlantique

Resumo

Cloud computing allows for elasticity as users can dynamically benefit from new virtual resources when their workload increases. Such a feature requires highly reactive resource provisioning mechanisms. In this paper, we propose two new workload prediction models, based on constraint programming and neural networks, that can be used for dynamic resource provisioning in Cloud environments. We also present two workload trace generators that can help to extend an experimental dataset in order to test more widely resource optimization heuristics. Our models are validated using real traces from a small Cloud provider. Both approaches are shown to be complimentary as neural networks give better prediction results, while constraint programming is more suitable for trace generation.

Palavras-chave: Time series analysis, Predictive models, Programming, Cloud computing, Neural networks, Virtual machining, cloud workload, time series, constraint programming, machine learning, neural network, prediction, generation, models