<p>Wireless Sensor Networks (WSNs) play a vital role in modern digital infrastructure, enabling critical applications in environmental monitoring, industrial automation, healthcare, and smart cities. However, existing WSN clustering approaches suffer from three major limitations: they address optimization objectives in isolation rather than holistically, lack adaptive capabilities to handle dynamic network conditions, and fail to effectively balance trade-offs between energy efficiency, coverage quality, and network lifetime. This research aims to develop a comprehensive clustering optimization framework that simultaneously addresses multiple network performance metrics while providing dynamic adaptation capabilities. We propose the Multi-Objective Genetic Algorithm with Adaptive Parameters (MOGAA), integrating four key components: adaptive parameter control system, predictive energy consumption model, comprehensive fitness evaluation framework, and specialized genetic operators designed for WSN clustering optimization. Experimental results demonstrate significant improvements: 44.44% increase in energy efficiency compared to LEACH, 41.67% extension in network lifetime, and 20.40% improvement in throughput. MOGAA maintains optimal cluster distribution <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$(mean: 9.0 nodes, \sigma : 3.95)$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mo stretchy="false">(</mo> <mi>m</mi> <mi>e</mi> <mi>a</mi> <mi>n</mi> <mo>:</mo> <mn>9.0</mn> <mi>n</mi> <mi>o</mi> <mi>d</mi> <mi>e</mi> <mi>s</mi> <mo>,</mo> <mi>σ</mi> <mo>:</mo> <mn>3.95</mn> <mo stretchy="false">)</mo> </mrow> </math></EquationSource> </InlineEquation> with exceptional coverage stability (coefficient of variation: 0.021) across various network configurations. These results have significant implications for real-world WSN deployments, particularly applications requiring long-term autonomous operation. MOGAA’s ability to maintain balanced performance across multiple objectives while adapting to network dynamics makes it valuable for critical monitoring applications and large-scale sensor networks.</p>

Energy-efficient clustering in wireless sensor networks using multi-objective genetic algorithm with adaptive parameter

期刊论文
发表日期：

2025年11月10日

查看全文

Muhammad Ejaz,
Muhammad Asim,
Gui Jinsong,
Samia Allaoua Chelloug,
Ahmed A. Abd El-Latif

摘要

Wireless Sensor Networks (WSNs) play a vital role in modern digital infrastructure, enabling critical applications in environmental monitoring, industrial automation, healthcare, and smart cities. However, existing WSN clustering approaches suffer from three major limitations: they address optimization objectives in isolation rather than holistically, lack adaptive capabilities to handle dynamic network conditions, and fail to effectively balance trade-offs between energy efficiency, coverage quality, and network lifetime. This research aims to develop a comprehensive clustering optimization framework that simultaneously addresses multiple network performance metrics while providing dynamic adaptation capabilities. We propose the Multi-Objective Genetic Algorithm with Adaptive Parameters (MOGAA), integrating four key components: adaptive parameter control system, predictive energy consumption model, comprehensive fitness evaluation framework, and specialized genetic operators designed for WSN clustering optimization. Experimental results demonstrate significant improvements: 44.44% increase in energy efficiency compared to LEACH, 41.67% extension in network lifetime, and 20.40% improvement in throughput. MOGAA maintains optimal cluster distribution $(mean: 9.0 nodes, \sigma : 3.95)$ $(m e a n : 9.0 n o d e s, σ : 3.95)$ with exceptional coverage stability (coefficient of variation: 0.021) across various network configurations. These results have significant implications for real-world WSN deployments, particularly applications requiring long-term autonomous operation. MOGAA’s ability to maintain balanced performance across multiple objectives while adapting to network dynamics makes it valuable for critical monitoring applications and large-scale sensor networks.