A review of soft computing based cluster-heads selection algorithms in wireless sensor network

Abstract In the recent past wireless sensor network (WSN) has gained the immense popularity in various fields. The selection of appropriate and optimal cluster-heads (CHs), the energy consumption, bandwidth, selection of optimal route are some of the key problem areas in WSN. In order to improve the network life span of WSN and to provide the solution to the above mentioned issues various soft computing algorithms have been successfully applied and literature review revels that these soft computing approaches contribute best towards in finding out the optimal and appropriate CHs in various routing algorithms in WSN. Fuzzy logic (FL), Ant Colony Optimization (ACO), Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Firefly algorithms, and Neural network are various soft computing approaches which have been proven best and appropriate for the selection of CHs in WSNs. In this article various soft computing based CH selection approaches for WSN have been discussed. The algorithms have also been compared on the basis of various parameters which will help the researcher to find out the best and appropriate soft computing based CH selction algorithm as per their needs and application for further research in this dynamically growing field. After review of various soft computing algorithms it is found that the application of these soft computing based algorithms have made these routing algorithms more adaptive, highly energy efficient with improvement in stability period and data transmission.