Fault-tolerant fog computing models in the IOT

Abstract

A huge number of devices like sensors are interconnected in the IoT (Internet of Things). In order to reduce the traffic of networks and servers, the IoT is realized by the fog computing model. Here, data and processes to handle the data are distributed to not only servers but also fog nodes. In our previous studies, the tree-based fog computing (TBFC) model is proposed to reduce the total electric energy consumption. However, if a fog node is faulty, some sensor data cannot be processed in the TBFC model. In this paper, we propose a fault-tolerant TBFC (FTBFC) model. Here, we propose non-replication and replication FTBFC models to make fog nodes fault-tolerant. In the non-replication FTBFC model, another operational fog node takes over a faulty fog node. We evaluate the non-replication FTBFC models in terms of the electric energy consumption and execution time.