AI-Based Energy-Efficient Routing Protocol for Large-Scale Underwater Wireless Sensor Networks

UWSNs are essential in a broad area of applications, including monitoring the environment including oceanic details. Sensor nodes still face the problem of energy consumption especially when deployed in large-scale where sensor nodes have to communicate across a large distance in the aquatic environment. This research aims at developing an AI aided optimized energy efficient routing protocol for huge scale of UWSNs. By incorporating reinforcement learning and neural networks into the protocol, the sensor nodes are able to choose the optimal energy efficient routing paths according to environmental conditions, energy levels of the nodes and topology of the network. The performance evaluation of the proposed protocol reveals that it consumes much less energy, increases the packet delivery ratio and increases the lifespan of the network. The protocol also contains the fault-tolerance mechanism that provides the stable connection even if some nodes become non-functioning. The study offers a solution that can be easily implemented and expanded to address the energy issues of UWSNs making way for improvements in underwater sensor networks in the future.