A Multi-Tier Data Prediction Mechanism for the Internet of Things Networks

In this era, we need to make everything about us more smartly and communicating. Hence, the popularity of Internet of Thing (IoT) is increasing quickly across industries. In such networks, the sensors represent the eyes of the IoT that collect data about different environments and states, while the sink node forms the brain of the network that must analyze the collected data and take decisions. However, the big amount of data collected by the sensors leads, from one hand, to consume the limited energy of the sensor and, from another hand, to complicate the exploitation of the data at the sink for decision making. In this paper, we propose a multi-tier prediction mechanism in order to handle big data collected by sensor networks based on the clustering scheme. The prediction model uses the least squares approximation method which is applied at both tiers of each cluster: sensors and cluster-heads (CHs). At the first tier, each sensor applies the prediction model in order to send a reduced set of data to its appropriate CH; At the second tier, the CH combines data coming from sensors and provides a predictive model to the sink, representing data for all sensors of the cluster. Extensive simulations on real sensor data collected from several applications demonstrated that our mechanism can efficiently reduce the data transmission and save the network energy, while maintaining an acceptable data accuracy level.