Optimization of Leach Protocol in Wireless Sensor Network Using Machine Learning

Area of Science:

• Computer Science
• Machine Learning
• Wireless Communication

Background:

• Wireless Sensor Networks (WSNs) are crucial for data collection in inaccessible areas.
• Existing routing protocols, like Low Energy Adaptive Clustering Hierarchy (LEACH), face efficiency limitations.
• Optimizing cluster head selection is vital for improving WSN performance and network longevity.

Purpose of the Study:

• To enhance the efficiency and network lifetime of Wireless Sensor Networks (WSNs).
• To optimize the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol using a modified k-means clustering algorithm.
• To improve the cluster head selection process for more efficient data routing.

Main Methods:

• Integration of a modified k-means clustering algorithm with the LEACH protocol.
• Implementation of a weighted cluster head selection mechanism.
• Utilization of the Euclidean distance formula for cluster formation.

Main Results:

• The proposed modified k-means with LEACH achieved a 48.85% efficiency improvement over existing protocols.
• Demonstrated a higher rate of successful data transfer to the sink node.
• The optimized cluster head selection led to a reduced failure rate and balanced network energy consumption.

Conclusions:

• The modified k-means algorithm significantly enhances WSN performance and network lifetime.
• The proposed approach offers a more robust and energy-efficient solution for WSN data routing.
• This optimization balances energy consumption and ensures successful data transmission in WSNs.