Efficient Data Replication Management in Fog Computing
Benamar Abed Zineeddine, Reguieg Hicham · 2024
IoT devices are increasing in number by each year. These devices are generating a massive amount of data which needs to be processed and stored. For this purpose, cloud computing is used to provide a solution to this problem. Unfortunately, when it comes to time-sensitive applications that require a very short time of response, cloud computing can't meet this requirement. To bring computational power and storage closer to IoT end devices, Fog computing has been introduced in order to improve the systems overall performance and decrease latency. Processing and storing data in IoT mobile environments can be challenging because of the nature of mobile devices, when a node disconnects or powers off, some data can be lost. This work focuses on studying how manage fault tolerance in fog environments and how to ensure data consistency through all fog nodes using data replication mechanisms. For that, we proposed a mobility-aware approach based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN) with a cluster head selection, to replicate new data and achieve eventual consistency in replicas through mobile fog nodes. Experimental results show that our proposed approach was able to manage replica with efficiency, ensuring reliable and optimized performance across various scenarios.