Quality of Service in Wireless Sensor Networks using Cellular Learning Automata

Wireless Sensor Networks (WSNs) have different Quality of Service (QoS) parameters from those of traditional networks. Several considerations utilized for evaluating QoS include appropriate number of active nodes, network lifetime, network coverage, and resource utilization. One of the features of Cellular Learning Automata (CLA), besides its simple learning structure, is learning in distributed and multi-hop environments with limited communications and incomplete information. CLA benefit show how different problems in WSNs can be overcome. In this paper, the underlying issues of WSNs are discussed, and in order to improve the QoS parameters, efficient solutions have been proposed using CLA. The WSN 's environmental coverage issue is also addressed by turning off redundant nodes and maintaining adequate nodes to conserve resources and enhance network life. In this research, the issue of clustering of WSNs is addressed and the WSNs are clustered by using CLA to efficiently distribute energy to the network and maximize network life. All provided methods are simulated by J-Sim tools showing the overall reduce in WSN energy consumption and also for each node alone. Moreover, we demonstrate the reduce in data communication overhead and maintaining the overall network coverage. Simulation experiments indicate higher performance of the proposed methods than other associated approaches.