Load Balancing for Effective Resource Provisioning in a Heterogeneous Cluster using Machine Learning

Abstract

Compute Clusters are typically installed to increase performance and/or accessibility. Appropriate Resource Provisioning is a key feature in clustered computing environments to avoid provisioning resources lower than the actual requirement and provisioning of resources in excess. In this paper, a load balancing scheme leading to effective provisioning of resources have been proposed. Job History of compute-intensive jobs have been collected by conducting experiments to observe basic parameters of a job in a heterogeneous computing cluster environment. A Machine Learning model using Multi-Layer Perceptron and Support Vector Machine for provisioning of resources has been presented. The prediction model uses the job history collected from the cluster environment to predict the resource that would be appropriate for provisioning in future. The accuracy of the model is computed and the results of experiments show that Multi-Layer Perceptron presents a better performance than Support Vector Machine