A review on offloading in fog-based Internet of Things: Architecture, machine learning approaches, and open issues

Abstract

There is an exponential increase in the number of smart devices, generating helpful information and posing a serious challenge while processing this huge data. The processing is either done at fog level or cloud level depending on the size and nature of the task. Offloading data to fog or cloud adds latency, which is less in fog and more in the cloud. The methods of processing data and tasks at fog level or cloud are mostly machine learning based. In this paper, we will discuss all three levels in terms of architecture, starting from the internet of things to fog and fog to cloud. Specifically, we will describe machine learning-based offloading from the internet of things to fog and fog to cloud. Finally, we will come up with current research directions, issues, and challenges in the IoT–fog–cloud environment.