A HEURISTIC DATA AGGREGATION IN HETEROGENEOUS LOW POWER DEVICES FOR INTERNET OF THINGS

Abstract

Internet of Things (IoT) has been envisioned as smart objects’ (things) communication and integration. The key challenge with regards to IoT is privacy. Within the IoT context, vertically-partitioned data learning is quite an applicable and well-known strategy. The issue happens whenever an event or state has to be predicted or identified, depending on the values assessed features at diverse nodes. An identity may be uncovered due to Quasi-Identifiers (QI), which are an attribute set of the information of a user. Wireless Sensor Network (WSN) is largely used as data collection for IoTs. Energy utilization can be decreased with data aggregation in WSN. In WSNs, an Energy-Efficient Hierarchical Clustering Algorithm (EEHCA) can attain good performance with regards to network lifespan through adjusting the nodal energy load and reducing the usage of energy for communication. Energy usage, load balance, and so on are sensor network performance factors which can be greatly boosted with the Particle Swarm Optimization (PSO) algorithm. In comparison to other mathematical and heuristic methods, this algorithm has better throughput and more efficient. Vertically-partitioned data aggregation that makes use of Quasi-Identifiers (QI) in the Internet of Things (IoT) has been proposed in this work and optimize the WSN using PSO to improve the performance of the entire system.