A load balancing scheme with Loadbot in IoT networks

Abstract

The Internet of Things' contribution lies in the increased value of information created by the number of interconnections among things and the subsequent transformation of processed information into knowledge for the benefit of society. The Internet of Things' sensors are deployed to monitor one or more events in an unattended environment. A large number of event data will be generated over a period of time in the Internet of Things. In the future, hundreds of billions of smart sensors and devices will interact with one another, without human intervention. Also, they will generate a large amount of data and resolutions, providing humans with information and the control of events and objects, even in remote physical environments. However, the demands of the Internet of Things cause heavy traffic or bottlenecks on particular nodes or on the paths of Internet of Things networks. Therefore, to resolve this issue, we propose an agent, Loadbot, that measures network loads and processes structural configurations by analyzing a large amount of user data and network loads. Additionally, in order to achieve efficient load balancing in the Internet of Things, we propose applying Deep Learning's Deep Belief Network method. Finally, using mathematical analysis, we address the key functions of our proposed scheme and simulate the efficiency of our proposed scheme.