Optimisation of energy efficient cellular learning automata algorithm for heterogeneous wireless sensor networks

Abstract

Wireless sensor networks is an effective sensing network consisting of a large number of small sensors and small embedded devices each with sensing, computation and communication capabilities for gathering data in various environments. Energy consumption is considered to be an important issue in the design of wireless sensor networks. To overcome the above limitation, efficient method like cellular learning automata (CLA) and heterogeneous-hybrid energy efficient distributed (H-HEED) technique have been used in distributed dynamic clustering networks. The existing method will be the cellular learning automata in which cluster heads will be selected through several stages by considering various parameters with homogeneous nodes. The proposed method selects the cluster head in a similar way and based on the residual energy of the nodes with heterogenous nodes. Their performance is observed using NS2 simulator and comparison has been made to find the best efficient method.