A WEIGHTED ENSEMBLE OF AUTOMATIC ALGORITHMS FOR VIRTUAL MACHINE PERFORMANCE PREDICTION IN CLOUD
V. Sudha, M Nayak Archana, D Chaithra, G Chethana, S. P. Kavya · International Journal of Current Engineering and Scientific Research · 2019
In cloud computing virtual machines are hosted on a shared computing platform, which compete for resources such as CPU, I/O and Network Storage.Predicting resources usage in cloud environment is a challenging problem due to varying characteristics of workloads running on cloud.Each virtual machine resource usage can be characterized as steady, trend, seasonal, cyclic or bursty pattern.Manually it is not feasible to fit the Predicting models for each of thousands of VMs running on cloud.Further different Predicting models are suitable for different type of workload.Manual selection of best model is will take too much time and complicated.In this manuscript we propose, implement and evaluate an automated technique of combining the Predictions from multiple non-overlapping time series Predicting methods.The objective is to improve accuracy and robustness of the predicting algorithm.The results show that proposed technique is successful in Predicting with better accuracy, irrespective of workload type and without any manual intervention.