Service Placement Problem for IoT Applications on Fog Computing

Every day, there is a significant rise in the number of connected objects, such as smart devices, sensors, and other IoT-enabled devices. Furthermore, many IoT applications heavily rely on real-time data processing, facing substantial latency when communicating with centralized Cloud servers, mainly attributed to the substantial geographical separation between IoT devices and Cloud servers. Therefore, Fog Computing (FC) can be a suitable paradigm to overcome the limitations of Cloud-based solutions and address the challenges posed by the massive growth of IoT devices. In this context, the service placement problem (SPP) pertains to selecting suitable Fog resources and allocating services to these resources. However, providing an efficient solution to this problem is challenging due to difficulties such as the system’s dynamism. This work presents a survey on the SPP for IoT applications on FC. To this end, we first introduce some basic concepts related to the SPP in Fog, emphasizing the importance of this paradigm. Next, we propose a classification for the solutions that have been proposed to solve the SPP for IoT applications over fog nodes and compare these recent works based on performance parameters such as latency, cost, etc. Finally, we conclude this paper with a discussion of future issues and challenges and a suggestion for improvements.