ABSTARCT :
Predictive cloud resource management has been widely adopted to overcome the limitations of reactive cloud auto scaling. The predictive resource management is highly relying on workload predictors, which estimate short-/long-term fluctuations of cloud application workloads. These predictors tend to be pre-optimized for specific workload patterns. However, such predictors are still insufficient to handle real-world cloud workloads whose patterns may be unknown a priori, may dynamically change over time and maybe irregular. As a result, these predictors often cause over-/under-provisioning of cloud resources. To address this problem, we create Cloud Insight, a novel cloud workload prediction framework, leveraging the combined power of multiple workload predictors. Cloud Insight creates an ensemble model using multiple predictors to make accurate predictions for real workloads. The weights of the predictors in Cloud Insight are determined at runtime with their accuracy for the current workload using multi-class regression. The ensemble model is periodically optimized to handle sudden changes in the workload. We evaluated Cloud Insight with various real workload traces. The results show that Cloud Insight has 13%–27% higher accuracy than state-of-the-art predictors. Moreover, there sults from trace-based simulations with a cloud resource manager show that Cloud Insighthas 15%–20% less under-/over-provisioning periods, resulting in high cost-efficiency and low SLA violations.