How Fog Computing Can Support Latency/Reliability‐sensitive IoT Applications: An Overview and a Taxonomy of State‐of‐the‐art Solutions

The Internet of Things (IoT) paradigm is leading to the deployment of an extensive number of smart devices capable of assisting companies and people in their daily activities. For this paradigm to be effective, these devices must exchange a huge amount of information and be coordinated in unpredictable, dynamic, and very complex scenarios. So far, cloud computing has centralized data storage and offered coordination of devices. However, as the number of deployed smart devices increases and the requirements of IoT solutions are more stringent, cloud computing hardly meets them. Fog computing has emerged as a middle layer between end‐devices and cloud environments to support the requirements of IoT applications that cannot be met by the current edge‐cloud model. A great effort has been devoted during the past few years to the development of this fog vision. Most of these solutions focused on improving specific characteristics, but not on supporting all the key requirements of an IoT solution. Thus, a deep investigation of these solutions to understand how they can be connected and coordinated to meet these necessities is essential. In this paper, we distinguish the most vital necessities that IoT solutions present to accomplish a right operation. Also, by analyzing the available solutions, we propose a novel global architectural model for fog computing meeting the recognized demands. We also provide a novel scientific taxonomy for breaking down the overviewed solutions. We conclude by analyzing the most essential recommendations in Fog computing for IoT, thereby distinguishing open issues and research frontiers that must be prioritized in order to have a totally developed fog computing environment, ready to meet the IoT solutions' prerequisites.