A Dynamic Network-Based Fog Computing Model for Energy-Efficient IoT

Abstract

In the fog computing model to realize the IoT, each fog node supports application processes to calculate output data on input data received from a fog node and sends the output data to a fog node. In our previous studies, types of the TBFC (Tree-Based Fog Computing) models are proposed to reduce the electric energy consumption and execution time of fog nodes and servers and to be tolerant of node faults. Here, fog nodes are hierarchically structured in a tree. A fog node $f_2$ which can calculate on the output data of a fog node $f_1$ is a target fog node of the fog node $f_1$. Here, if some fog node f is faulty or heavily loaded, the tree structure has to be changed so that another target node can calculate on output data from child nodes of the node f. In this paper, we consider the DNFC (Dynamic Network-based Fog Computing) model. Here, there is one or more than one target fog node for each fog node and there is also one or more than one source node for each target node. We propose a DNFCN (DNFC Negotiation) algorithm to do the negotiation among source nodes and target nodes to decide which source node sends output data to which target node. In the evaluation, we show the energy consumed by target fog nodes can be more reduced in the DNFC model than the TBFC model.