Energy efficient multipath routing in IoT-wireless sensor network via hybrid optimization and deep learning-based...

Area of Science:

• Computer Science
• Network Engineering
• Artificial Intelligence

Background:

• Efficient data transmission is crucial for Wireless Sensor Networks (WSNs).
• Traditional routing protocols often prioritize energy efficiency over other performance metrics.
• Existing methods may not adequately address performance degradation factors in WSNs.

Purpose of the Study:

• To propose a novel Hybrid Beluga Whale-Coati Optimization (HBWCO) algorithm for optimizing energy-efficient data transmission in WSNs.
• To enhance routing reliability and throughput in WSNs by considering multiple factors beyond just energy.
• To introduce a robust route maintenance strategy for link breakages.

Main Methods:

• Initialization of sensor nodes and field dimensions.
• K-means clustering for node grouping and Deep Q-Net for energy level prediction.
• Hybrid Beluga Whale-Coati Optimization (HBWCO) for multipath routing selection based on reliability, residual energy, predicted energy, throughput, and traffic intensity.
• Source Link Breakage Warning (SLBW) strategy for route maintenance.

Main Results:

• The HBWCO algorithm achieved a reliability of 0.948.
• The HBWCO approach demonstrated a throughput of 3496.
• The proposed method offers a comprehensive approach to enhancing network energy efficiency and data transmission.

Conclusions:

• The HBWCO algorithm provides an effective solution for data transmission and routing reliability in WSNs.
• This novel approach surpasses traditional methods in performance.
• The integration of optimization algorithms with deep learning enhances WSN performance.