HEOCP: Hybrid Energy-Optimized Clustering Protocol for WSNs Using Analytical Modeling and Deep Learning Integration

Area of Science:

• Computer Science
• Electrical Engineering
• Network Engineering

Background:

• Wireless Sensor Networks (WSNs) are crucial for the Internet of Things (IoT).
• Limited sensor node energy significantly restricts WSN operational lifetime.
• Efficient energy management is essential for sustainable IoT applications.

Purpose of the Study:

• To introduce a Hybrid Energy-Optimized Clustering Protocol (HEOCP) for extending WSN lifetime.
• To enhance energy efficiency and network performance in IoT deployments.
• To develop a sustainable energy management paradigm for WSNs.

Main Methods:

• Developed an analytical framework for distance-constrained cluster-head (CH) eligibility and optimal cluster count.
• Employed a genetic algorithm (GA) for optimal CH configuration.
• Utilized a ResNet-50 deep network for training GA configurations and real-time CH prediction.

Main Results:

• HEOCP extends network lifetime by up to 60% compared to LEACH and GA-based methods.
• Effectively delays first-node death and improves overall energy efficiency.
• The hybrid GA-ResNet framework demonstrates high scalability and computational efficiency.

Conclusions:

• Integrating analytical energy modeling with deep learning offers a powerful approach for intelligent WSN energy management.
• HEOCP provides a sustainable and effective solution for large-scale IoT deployments.
• The proposed protocol significantly enhances the longevity and efficiency of WSNs.