Resource and performance prediction at high utilization for N-Tier cloud-based service systems
Conference
Zhang, W, Shi, Y, Zheng, Y et al. Resource and performance prediction at high utilization for N-Tier cloud-based service systems
. 10.1145/3014812.3014857
Zhang, W, Shi, Y, Zheng, Y et al. Resource and performance prediction at high utilization for N-Tier cloud-based service systems
. 10.1145/3014812.3014857
One of the key objectives of cloud computing systems is to meet the service level agreements (SLAs) under conditions of high resource utilization. Cloud service providers often need to design policies for resource sharing and performance optimization. As a result, being able to predict the performance and resource utilizations prior to implementing these policies is important to the dynamic provisioning of services by cloud providers. It is a significant and diffcult challenge due to the fact that requests for resources often interact with each other in complex ways. Moreover, the dynamics of the cloud environment bring more problems to predicting the performance of a running query or workload. Hence, an accurate situation-aware model which can capture the complex interactions among resource requests is useful for addressing this challenge. To this end, we propose an efficient and highly accurate resource and performance prediction framework which takes into account the interactions among concurrently running resource requests for n-tier service systems. The proposed framework extends the Gaussian process and kernel canonical correlation analysis techniques and is able to dynamically adapt to variations in workload and physical resource usage. The proposed framework has been trained and evaluated extensively with a realistic multi-tier cloud application benchmark - the RUBiS benchmark system. The results demonstrate that the framework yields highly accurate performance and resource usage predictions, especially under high resource utilization conditions.
