Packet Flow Based Reinforcement Learning MAC Protocol for Underwater Acoustic Sensor Networks

Medium access control (MAC) is one of the key requirements in underwater acoustic sensor networks (UASNs). For a MAC protocol to provide its basic function efficient sharing channel access, highly dynamic environment demands protocols be adaptive as well. Q-learning promising techniques employed intelligent solutions, however, due long propagation delay, performance this approach severely limited by reliance on an explicit reward signal function. In paper, we propose restructured and modified two stage process extract implicit for novel protocol: Packet flow ALOHA with (ALOHA-QUPAF). Based simulated pipeline monitoring chain network, results show that outperforms both ALOHA-Q framed at least 13% 148% all scenarios, respectively.