Reverse Engineering Technique (RET) to Predict Resource Allocation in a Google Cloud System

摘要

This paper presents a reverse engineering machine learning technique for resource allocation in cloud computing system. Efficient and timely resource allocation is a crucial task for complex operations in a large scale distributed system like cloud computing. Furthermore, to support Service Level Agreement (SLA) like priority, latency, and efficiency, the resource provisioning should be highly influenced by SLA requirements of the system. Therefore in this paper, we propose the Reverse Engineering Technique (RET) which highly influence by priority to improve resource allocation accuracy. The paper used neural network based deep learning and Levenberg-Marquardt training algorithm for resource allocation prediction. The dataset of Google cloud computing system, which is publicly available dataset for research, is used to test the proposed RET. Our experiment shows that the proposed technique improves resource provisioning accuracy for cloud based systems.