Artificial neural network-based clustering in Wireless sensor Networks to balance energy consumption

The stability of Wireless Sensor Networks (WSNs) is a crucial requirement in real-time applications such as military, defense, and other surveillance systems. Clustering in WSNs is one of the most predominant techniques, offering benefits such as minimizing communication time, optimizing energy util...

Full description

Saved in:
Bibliographic Details
Published in:Cogent engineering 2024-12, Vol.11 (1)
Main Authors: Nayak, Padmalaya, Trivedi, Veena, Gupta, Surbhi, Booba, Phaneendra Babu, O.V, Soloveva, Rozhdestvenskiy, Oleg Igorevich, Joshi, Ankita
Format: Article
Language:English
Subjects:
Algorithms
ANN
Artificial Intelligence
Artificial neural networks
Cluster analysis
Clustering
Computer Engineering
Energy consumption
Energy distribution
Energy utilization
Evolutionary Computing
K-means
LEACH
Machine Learning - Design
Military applications
Neural Networks
Real time
Self organizing maps
SOM
Stability
Surveillance systems
Vector quantization
Wireless sensor networks
WSNs
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The stability of Wireless Sensor Networks (WSNs) is a crucial requirement in real-time applications such as military, defense, and other surveillance systems. Clustering in WSNs is one of the most predominant techniques, offering benefits such as minimizing communication time, optimizing energy utilization, lengthening the network lifespan, and ensuring network stability. Moreover, achieving the balance between energy consumption and maintaining network stability is significantly influenced by the cluster size. This research paper addresses the challenges associated with clustered-based routing and cluster formation paradigm, introducing a novel algorithm employing the principle of Artificial Neural Networks (ANN). In particular, the proposed algorithm integrates a hybrid strategy of Self Organizing Map (SOM) and K-mean clustering to form energy-efficient clusters, even ensuring the energy distribution evenly among them. The validity of the proposed algorithm has been confirmed through experimental analysis conducted using MATLAB. The simulation results demonstrate that the hybrid combination of SOM and K-means clustering is highly efficient in minimizing energy consumption and maintaining network stability. The findings also reveal an average of 80% stable network lifetime and achieve a packet reception ratio (PRR) of 98% which is much higher than two other protocols i.e. LEACH and MODLEACH protocols.
ISSN:2331-1916
2331-1916
DOI:10.1080/23311916.2024.2384652