Hybrid optimized data aggregation for fog computing devices in internet of things

Abstract

In the recent few years, the applications using Internet of Things (IoT) are becoming extremely important as they facilitate continuous and seamless interactions among humans and devices in order to improve the quality of life. With the increase in the devices used in an application for smooth and efficient operations, the amount of data generated is high. Today, fog computing has been emerging as an extended version of the cloud infrastructure that provides highly scalable services that are latency-aware to the end devices that are geographically distributed. By adding the fog layer to the cloud computing paradigm, Quality of Service (QoS) can be improved in delay-sensitive and in time-critical applications. Owing to the increase in deploying fog networks on a large scale, the efficiency of energy can become a very important issue in the paradigm of fog computing. This can bring down service costs and further protect the environment. There has been plenty of research that was conducted for reducing consumption of energy in Wireless Sensor Network (WSN) and fog computing, primarily focusing on the optimization techniques. This was to enhance energy conservation. In this work, a new and novel hybrid optimization technique based on TABU Search (TS), Particle Swarm Optimization (PSO), and River Formation Dynamics (RFD) algorithms were proposed. The Hybrid RFD-TS, along with a hybrid RFD-PSO technique, was in the solution space search used for the local optimum, which is avoided. The experimental results demonstrated the efficacy of the proposed met.

Keywords

• Cloud Computing, Clustering, Energy Efficient Heterogeneous Clustering Algorithm (EEHCA), Fog Computing, Security, Internet of Things (IoT), Metaheuristic Algorithms, Wireless Sensor Network (WSN)