A new reasoning and learning model for Cognitive Wireless Sensor Networks based on Bayesian networks and learning automata cooperation

Abstract

Adding cognition to existing Wireless Sensor Networks (WSNs) with a cognitive networking approach, which deals with using cognition to the entire network protocol stack to achieve end-to-end goals, brings about many benefits. However cognitive networking may be confused with cognitive radio or cross-layer design, it is a different concept; cognitive radios applies cognition only at the physical layer to overcome the problem of spectrum scarcity, and cross layer design usually focuses on linking at least two non-consecutive specific layers, to achieve a particular goal. Indeed, it can be said that the cognitive radio and the cross layer design are two effective methods in cognitive networking. To the best of our knowledge, almost all of the existing researches on the Cognitive Wireless Sensor Networks (CWSNs) have focused on spectrum allocation and interference reduction in the physical layer. In this paper, we propose a new reasoning and learning model for CWSNs, in which firstly, a team of learning automata is employed to construct a Bayesian Network (BN) model of the parameters of the network protocol stack, and then the constructed BN is used to tune the controllable parameters. The BN represents the dependency relationships between the parameters of the network protocol stack, and the BN-based reasoning is an efficient tool for cross-layer optimization, in order to maximize the perceived network performance. Simulations have been done to evaluate the performance of the proposed model. The results of the simulations show that the proposed model successively adds cognition to a WSN and improves the performance of the communication network.