Abstract
Underwater Wireless Sensor Networks (UWSNs) have aroused increasing interest of many researchers in industry, military, commerce and academe recently. Due to the harsh underwater environment, energy efficiency is a significant theme should be considered for routing in UWSNs. Underwater positioning is also a particularly tricky task since the high attenuation of radio-frequency signals in UWSNs. In this paper, we propose an energy-efficient depth-based opportunistic routing algorithm with Q-learning (EDORQ) for UWSNs to guarantee the energy-saving and reliable data transmission. It combines the respective advantages of Q-learning technique and opportunistic routing (OR) algorithm without the full-dimensional location information to improve the network performance in terms of energy consumption, average network overhead and packet delivery ratio. In EDORQ, the void detection factor, residual energy and depth information of candidate nodes are jointly considered when defining the Q-value function, which contributes to proactively detecting void nodes in advance, meanwhile, reducing energy consumption. In addition, a simple and scalable void node recovery mode is proposed for the selection of candidate set so as to rescue packets that are stuck in void nodes unfortunately. Furthermore, we design a novel method to set the holding time for the schedule of packet forwarding base on Q-value so as to alleviate the packet collision and redundant transmission. We conduct extensive simulations to evaluate the performance of our proposed algorithm and compare it with other three routing algorithms on Aqua-sim platform (NS2). The results show that the proposed algorithm significantly improve the performance in terms of energy efficiency, packet delivery ratio and average network overhead without sacrificing too much average packet delay.
Highlights
With the great application prospects in marine environmental protection, underwater exploration, marine disaster monitoring, offshore operations and marine military activities, Underwater WirelessSensor Networks (UWSNs) have drawn a great attention from governments, industry and academia over the course of the past few years [1,2]
The simulation results demonstrate that our proposal can significantly improve terms of energy efficiency, packet delivery ratio and average network overhead
We evaluate the performance of the proposed efficient depth-based opportunistic routing algorithm with Q-learning (EDORQ) algorithm and compare it with vector-based forwarding (VBF) [31], depth-based routing (DBR) [22] and QELAR [26]
Summary
With the great application prospects in marine environmental protection, underwater exploration, marine disaster monitoring, offshore operations and marine military activities, Underwater Wireless. The aforementioned routing algorithms based on reinforcement learning for UWSNs can improve the network performance in some aspects by observing and learning the environment, some of them cannot control the routing overhead well when exchange the related information about Q-values and the others require position information, in which it is a tricky to achieve accurate underwater location. Motivated by the above considerations, in this paper, we propose an energy-efficient depth-based OR algorithm with Q-learning (EDORQ) to further reduce the energy consumption and improve the robustness for UWSNs. Instead of depending on full-dimensional position coordinates for packet delivery, the EDORQ needs only local depth information which can be obtained via an inexpensive pressure sensor.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
