Workload characterization and prediction in the cloud: A multiple time series approach

Abstract

Cloud computing promises high scalability, flexibility and cost-effectiveness to satisfy emerging computing requirements. To efficiently provision computing resources in the cloud, system administrators need the capabilities of characterizing and predicting workload on the Virtual Machines (VMs). In this paper, we use data traces obtained from a real data center to develop such capabilities. First, we search for repeatable workload patterns by exploring cross-VM workload correlations resulted from the dependencies among applications running on different VMs. Treating workload data samples as time series, we develop a co-clustering technique to identify groups of VMs that frequently exhibit correlated workload patterns, and also the time periods in which these VM groups are active. Then, we introduce a method based on Hidden Markov Modeling (HMM) to characterize the temporal correlations in the discovered VM clusters and to predict variations of workload patterns. The experimental results show that our method can not only help better understand group-level workload characteristics, but also make more accurate predictions on workload changes in a cloud.

Towards Virtual Machine Energy-Aware Cost Prediction in Clouds

“…The algorithm has shown a good result within 4.8% prediction error. Khan et al [16] proposed a method of characterising and predicting workload based on Hidden Markov Modeling to discover the correlations between VMs workload that can be used to predict the changes of workload patterns. Further, Wood et al [12] focused on estimating the resource requirements when deploying an application into a virtualised environment using a regression-based model to predict future CPU utilisation.…”

Quality-of-service in cloud computing: modeling techniques and their applications

“…Recent works in workload modeling that are relevant to cloud computing include [20][21][22]. Khan et al [20] uses Hidden Markov Models to capture and predict temporal correlations between workloads of different compute clusters in the cloud.…”

“…Khan et al [20] uses Hidden Markov Models to capture and predict temporal correlations between workloads of different compute clusters in the cloud. In this paper, the authors propose a method to characterize and predict workloads in cloud environments in order to efficiently provision cloud resources.…”

Cost-Aware Resource Management for Federated Clouds Using Resource Sharing Contracts

“…The jobs in the queue are processed in a FIFO (First In First Out) manner. We assume that the demand for each time slot τ is λ i (τ ) for CSP i which can be determined by predicting the upcoming workloads through mechanisms such as ARIMA [18] or Hidden Markov Modeling (HMM) [19]. The profit earned by the CSPs is computed as the difference between the sum of the payments from the users and the operating cost and the penalty.…”