ProLEACH: A Novel LEACH Improved with Multi-Head Attention Mechanism and Graph Convolution Network for Wireless Sensor Network

In today's information age, Wireless Sensor Networks (WSN s) playa crucial and multifaceted role in our daily lives. From the smartphones to various precision instruments and testing equipment, WSNs provide essential support, enabling seamless communication, data collection, and intelligent automation. However, traditional WSN routing strategies, such as the Low-Energy Adaptive Clustering Hierarchy (LEACH), face several significant limitations, including uneven node energy consumption, suboptimal path planning, and weak adaptability to dynamic environments. These shortcomings lead to inefficient energy usage, reduced network lifespan, and poor overall performance. To address these challenges, this paper integrates deep learning techniques into the existing LEACH routing protocol, introducing a novel ProLEACH routing method that leverages both the Multi-Head Attention (MHA) mechanism and Graph Convolutional Network (GCN). Specifically, the proposed approach first employs the MHA mechanism to intelligently select cluster heads based on multiple factors rather than random selection, ensuring a more balanced energy distribution across nodes. Then, GCN is utilized to optimize the data transmission path, allowing for more efficient and reliable communication between cluster heads and the base station. Experimental results demonstrate that the proposed ProLEACH method significantly outperforms traditional LEACH routing in terms of two key performance metrics: node mortality rate and energy decay rate. By mitigating the negative effects of random cluster head selection, ProLEACH ensures a more uniform energy distribution among sensor nodes, effectively prolonging the network's lifespan. Additionally, the optimized transmission path reduces the communication overhead of cluster heads, further enhancing data transmission efficiency while lowering overall energy consumption. These improvements make ProLEACH a promising solution for energy-efficient and intelligent WSN routing in real-world applications.

Authors

Institutions

Publication Details

Published
2025-03-28
DOI
https://doi.org/10.1109/aiita65135.2025.11048133
Primary Topic
Energy Efficient Wireless Sensor Networks
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

ProLEACH: A Novel LEACH Improved with Multi-Head Attention Mechanism and Graph Convolution Network for Wireless Sensor Network

Quan Liu, Wenhao Ruan, Yuang Liu, Kun Chen
Energy Efficient Wireless Sensor Networks
article

ProLEACH: A Novel LEACH Improved with Multi-Head Attention Mechanism and Graph Convolution Network for Wireless Sensor Network

Quan Liu, Wenhao Ruan, Yuang Liu, Kun Chen
article en

Abstract

In today's information age, Wireless Sensor Networks (WSN s) playa crucial and multifaceted role in our daily lives. From the smartphones to various precision instruments and testing equipment, WSNs provide essential support, enabling seamless communication, data collection, and intelligent automation. However, traditional WSN routing strategies, such as the Low-Energy Adaptive Clustering Hierarchy (LEACH), face several significant limitations, including uneven node energy consumption, suboptimal path planning, and weak adaptability to dynamic environments. These shortcomings lead to inefficient energy usage, reduced network lifespan, and poor overall performance. To address these challenges, this paper integrates deep learning techniques into the existing LEACH routing protocol, introducing a novel ProLEACH routing method that leverages both the Multi-Head Attention (MHA) mechanism and Graph Convolutional Network (GCN). Specifically, the proposed approach first employs the MHA mechanism to intelligently select cluster heads based on multiple factors rather than random selection, ensuring a more balanced energy distribution across nodes. Then, GCN is utilized to optimize the data transmission path, allowing for more efficient and reliable communication between cluster heads and the base station. Experimental results demonstrate that the proposed ProLEACH method significantly outperforms traditional LEACH routing in terms of two key performance metrics: node mortality rate and energy decay rate. By mitigating the negative effects of random cluster head selection, ProLEACH ensures a more uniform energy distribution among sensor nodes, effectively prolonging the network's lifespan. Additionally, the optimized transmission path reduces the communication overhead of cluster heads, further enhancing data transmission efficiency while lowering overall energy consumption. These improvements make ProLEACH a promising solution for energy-efficient and intelligent WSN routing in real-world applications.

Wuhan University of Technology (CN)
National Key Research and Development Program of China
Affordable and clean energy
Openalex Percentile: Top 83%
Energy Efficient Wireless Sensor Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.