Workload prediction for cloud computing elasticity mechanism
Yazhou Hu, Bo Deng, Fuyang Peng, Dongxia Wang · 2016
Elasticity is the key feature of cloud computing technology, which can automatically reduce and add resources to meet users' need. In order to achieve elasticity, we should find how and when to trigger the elasticity automatic scaling mechanism. Workload analyzing is a popular method to solve this problem. In this paper, we propose three models to predict the workload based on analyzing monitoring data. Firstly, we use time series approach to analyze monitoring data. Then, we propose a Kalman filter model to predict the cloud workload. Next, we put forward a novel pattern matching model to analyze and predict the workload. Based on these predicting, we propose a new trigger strategy for cloud computing elasticity automatic scaling mechanism. Finally, experimental results show that our models not only improve the prediction accuracy, but also reduce the automatic scaling delay.