A Node Capability Classification in Internet of Things

Abstract

The Internet of Things (IoT) is an advanced paradigm of the Internet, it makes everything and everyone to be connected and interacted from anywhere, at any time, and using any path and network. This new paradigm is characterized by constraint nodes and lossy networks where the available resources are limited and the network structure is unstable. The random execution of requests can lead to the failure of some nodes, as a consequence, the network lifetime will be reduced. In this paper, we proposed a new strategy to classify the nodes into three levels based on their capabilities and using a neural network. The classification allows the nodes to be aware of the best nodes that can execute or process a given service or a task, by predicting the capability of a joined node in the lossy network. The simulation results show that our proposed model has a high accuracy for prediction nodes and makes the network lifetime prolonged.