A Comprehensive Study on Routing Protocol for IoT-enabled WSNs using Deep Reinforcement Learning Strategy

Internet of Things enabled Wireless Sensor Networks (IoT-enabled WSNs) rely heavily on routing protocols because of the importance of various system performance parameters, such as end-to-end delay, system capacity, data delivery rate, and energy efficiency. As a result of this, sensor nodes may have a detrimental effect on the routing protocol's reliability and power tolerance when compared to other nodes in the network. As a result, the IoT-enabled WSNs' wide-field applications necessitate a self-driven energy intelligent routing protocol. Reinforcement Learning (RL) strategy has recently been used to support the development of an intelligent routing protocol that has a high potential for energy conservation while also increasing system performance above the typically achieved target. Deep Reinforcement Learning (DRL) routing protocols for IoT-enabled WSNs have been studied in this paper, and the current state-of-the-art algorithms have been compared. It is the purpose of this study to evaluate the operational characteristics and key features of the current DRL algorithms. In addition, the practical difficulties of routing protocol design and implementation were discussed.