TY - GEN
T1 - Dynamic Data Collection of AUV Based on Deep Reinforcement Learning
AU - Tang, Yongqi
AU - Jing, Lianyou
AU - Shi, Wentao
AU - He, Chengbing
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The Underwater Internet of Things (IoUT) shows great potential in enabling a smart ocean. Underwater sensor network (UWSN) is the main form of IoUT, but it faces the problem of reliable data transmission. To address these issues, this paper considers the use of autonomous underwater vehicles (AUV) as mobile collectors to build a reliable dynamic data collection system, while using Value of Information (VoI) as a primary metric to measure data quality. This paper first builds a realistic model to characterize the behavior of AUV and sensor nodes and challenging environments. Then a method based on deep reinforcement learning is used to dynamically plan the AUV's navigation route by jointly considering the location of nodes, the value of node data information and the state of AUV, with the goal of maximizing the data collection efficiency of AUV. The simulation results show that the dynamic data collection scheme is superior to the traditional path planning scheme which only considers the node location, and can greatly improve the efficiency of AUV data collection.
AB - The Underwater Internet of Things (IoUT) shows great potential in enabling a smart ocean. Underwater sensor network (UWSN) is the main form of IoUT, but it faces the problem of reliable data transmission. To address these issues, this paper considers the use of autonomous underwater vehicles (AUV) as mobile collectors to build a reliable dynamic data collection system, while using Value of Information (VoI) as a primary metric to measure data quality. This paper first builds a realistic model to characterize the behavior of AUV and sensor nodes and challenging environments. Then a method based on deep reinforcement learning is used to dynamically plan the AUV's navigation route by jointly considering the location of nodes, the value of node data information and the state of AUV, with the goal of maximizing the data collection efficiency of AUV. The simulation results show that the dynamic data collection scheme is superior to the traditional path planning scheme which only considers the node location, and can greatly improve the efficiency of AUV data collection.
KW - AUV
KW - Data collection
KW - Deep Reinforcement Learning
KW - Underwater Acoustic Communications
KW - VoI
UR - https://www.scopus.com/pages/publications/85184851969
U2 - 10.1109/ICSPCC59353.2023.10400308
DO - 10.1109/ICSPCC59353.2023.10400308
M3 - 会议稿件
AN - SCOPUS:85184851969
T3 - Proceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023
BT - Proceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023
Y2 - 14 November 2023 through 17 November 2023
ER -