Open AccessEEFCM‐DE: energy‐efficient clustering based on fuzzy C means and differential evolution algorithm in WSNs
Author(s) -
Sharma Richa,
Vashisht Vasudha,
Singh Umang
Publication year - 2019
Publication title -
iet communications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.355
H-Index - 62
eISSN - 1751-8636
pISSN - 1751-8628
DOI - 10.1049/iet-com.2018.5546
Subject(s) - cluster analysis , computer science , differential evolution , node (physics) , wireless sensor network , fuzzy logic , cluster (spacecraft) , efficient energy use , data mining , energy (signal processing) , algorithm , distributed computing , artificial intelligence , computer network , mathematics , engineering , statistics , electrical engineering , structural engineering
Efficient energy utilisation is a fundamental challenge that needs to be dealt with while deploying a wireless sensor network (WSN). These networks consist of thousands of small‐sized battery‐operated devices called sensors. Sensors are resource‐constrained devices, and hence have very limited energy available with them. By lessening the energy usage of these nodes, the life span of the whole network can be enhanced up to a great extent. Clustering of WSNs is a speedily flourishing research area. In clustered WSNs, the major concerns are choosing an appropriate number of clusters and then selecting a coordinator node called cluster head (CH) within each formed cluster. This study introduces a hybrid energy‐efficient clustering based on fuzzy C means and differential evolution algorithm (EEFCM‐DE) based on fuzzy clustering and fuzzy‐based evolutionary technique. The idea is to use FCM for the cluster creation and then selecting the best node as a CH within each cluster formed, by using an evolutionary technique DE. For the CH selection, the fitness of each node is calculated through a designed fuzzy inference system. The simulation results validate the energy‐efficient performance of EEFCM‐DE in comparison with the other existing algorithms.