Evaluation of data and subprocess transmission strategies in the tree-based fog computing model

Abstract

In order to increase the performance of the IoT (Internet of Things), the fog computing model is proposed. Here, subprocesses of an application process to handle sensor data are performed on fog nodes in addition to servers. In the TBFC (Tree-Based Fog Computing) model proposed in our previous studies, an application process to handle sensor data is assumed to be a sequence of subprocesses, i.e. linear model. At each level of a TBFC tree, a same subprocess is performed on every node. In this paper, we consider a more general model, GTBFC (General TBFC) model of the IoT where subprocesses of an application process are structured in a tree. Each subprocess in the process tree is performed on fog nodes which are at a same level in the GTBFC tree. Each leaf subprocess is performed on edge nodes which communicate with sensor and actuator devices. We also proposed MEG (Minimum Energy in the GTBFC tree) and SMPRG (Selecting Multiple Parents for Recovery in the GTBFC tree) algorithms to select a new parent node for a child node of a faulty node in the GTBFC tree. In the evaluation, we show the energy consumption of nodes in the SMPRG algorithm as 21 % and 31 % smaller than the MEG and RD (Random) algorithms.