Hybrid African vulture and Aquila optimizer based efficient clustering approach for enhancing network longevity in...

Area of Science:

• Computer Science
• Network Engineering
• Artificial Intelligence

Background:

• Wireless Sensor Networks (WSNs) are crucial for data perception in IoT and IIoT.
• Energy consumption for data communication and processing is a major challenge in WSNs.
• Existing energy-based clustering schemes aim to prolong network lifespan.

Purpose of the Study:

• To develop an energy-efficient clustering mechanism for WSNs.
• To improve network lifetime and performance through optimized Cluster Head (CH) selection.
• To address challenges like premature convergence and solution diversity in metaheuristic algorithms.

Main Methods:

• A Hybrid African Vulture and Aquila Optimization Algorithm (AVOA) was developed for clustering.
• The algorithm prevents premature convergence and balances exploration/exploitation.
• Fitness Function evaluation incorporates balancing, sink distance, Residual Energy (RE), and intra-cluster distance.

Main Results:

• The proposedAVOA-based clustering mechanism achieved superior energy-efficient CHs.
• Demonstrated improvements in mean network stability (23.86%), throughput (26.79%), and RE sustenance (29.32%) compared to baseline methods.
• The hybrid approach enhanced execution time, accuracy, and feature selection in the clustering process.

Conclusions:

• The HybridAVOA-based clustering protocol significantly enhances energy efficiency in WSNs.
• The method effectively prolongs network lifetime and improves overall performance metrics.
• This approach offers a robust solution for energy-constrained WSN applications.