Designed Features for Improving Openness, Scalability and Programmability in the Fog Computing-Based IoT Systems

Abstract

Global-scale Internet of Things (IoT) applications commonly process a huge amount of data and quickly provide useful information (to users) and instructions to monitor or control the physical world; most of these services are required to be of low latency while satisfying resource constraints (computing, storage, networking). In order to reduce communication latency, network load, energy consumption and operational cost which are essential for real-world IoT applications, fog computing is a promising technology as it allows utilizing virtualized resources already available on the network edges which are close to IoT data generators (IoT devices) and consumers (users or actuators). However, there are still many challenges in realizing this computing paradigm as it is still in the infancy stage. This paper investigates and proposes designed features for the “openness,” “scalability” and “programmability” in fog computing to which IoT services/applications can be flexibly implemented in the fog landscape. We apply the proposed mechanism to a real-world application, namely the traffic light optimization problem, to validate its effectiveness and feasibility. The evaluation results reveal the effectiveness of the proposed approach.