Abstract

This paper proposes an optimal dynamic resource allocation method in Internet of Things (IoT) Parking Guidance Systems (PSG). In the proposed method, a resource allocation using a forecasting model based on Q-learning is employed. To demonstrate efficiency of this method, it is verified by Matlab 7. Through simulation results, this paper proves that the proposed method can enhance total throughput, decrease penalty fee issued by Service Level Agreement (SLA) and reduce response time with the dynamic number of users.

Keywords: Internet of Things, Q-learning, Virtual Machine provisioning (VM provisioning), Cloud computing.

Available Online =

https://www.seekdl.org/conferences/paper/details/7413