Anypath Routing Protocol Design via Q-Learning for Underwater Sensor Networks

As a promising technology in the Internet of Underwater Things, underwater sensor networks (UWSNs) have drawn widespread attention from both academia and industry. However, designing routing protocol for UWSNs is great challenge due to high energy consumption large latency environment. This article proposes Q-learning -based localization-free anypath (QLFR) prolong lifetime as well reduce end-to-end delay UWSNs. Aiming at optimal policies, Q-value calculated by jointly considering residual depth information nodes throughout process. More specifically, we define two reward functions (i.e., depth-related energy-related rewards) with objective reducing extending network lifetime. In addition, new holding time mechanism packet forwarding designed according priority candidate nodes. Furthermore, mathematical analyses are presented analyze performance computational complexity proposed protocol. Extensive simulation results demonstrate superiority terms