Machine Learning Driven Energy Efficient Communication in Underwater Sensor Networks

Underwater Sensor Networks (UWSNs) play a pivotal role in marine operations such as environmental monitoring and disaster prevention. However, they encounter challenges including limited battery power, bandwidth constraints, and multipath interference. Here, we develop a comprehensive framework addressing these challenges through a Q-learning based routing protocol and intelligent communication mean selection. Our framework optimizes energy consumption, data transmission efficiency, and network longevity. Extensive simulations demonstrate the effectiveness and scalability of our approach. By significantly enhancing UWSNs, our framework contributes to sustainable marine resource management and protection, aiding environmental monitoring and disaster prevention in marine environments. This approach not only improves UWSNs’ performance but also aligns with broader goals of leveraging technology for sustainable marine resource management.