Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning Approach
This paper studies the integration of data collection and offloading for maritime Internet of Things (IoT) systems with multiple unmanned aerial vehicles (UAVs). In the considered multi-UAV maritime IoT system, the UAVs act as the aerial base stations to complete the missions of data collection from...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/2/292 |
_version_ | 1797437518707163136 |
---|---|
author | Ziyi Liang Yanpeng Dai Ling Lyu Bin Lin |
author_facet | Ziyi Liang Yanpeng Dai Ling Lyu Bin Lin |
author_sort | Ziyi Liang |
collection | DOAJ |
description | This paper studies the integration of data collection and offloading for maritime Internet of Things (IoT) systems with multiple unmanned aerial vehicles (UAVs). In the considered multi-UAV maritime IoT system, the UAVs act as the aerial base stations to complete the missions of data collection from buoys and data offloading to the offshore base station (OBS). In this case, the UAVs need to adaptively select the mission mode between data collection and data offloading according to the network resources and mission requirements. In this paper, we aimed to minimize the completion time of data collection and offloading missions for all UAVs by jointly optimizing the UAV trajectories, mission mode selection, transmit power of buoys, and association relationships between the UAVs and buoy/OBS. In order to solve the mixed-integer non-convex minimization problem, we first designed a multi-agent deep reinforcement learning algorithm based on a hybrid discrete and continuous action space to preliminarily obtain the UAV trajectories, mission mode selection, and the transmit power of buoys. Then, we propose an algorithm based on the stable marriage problem to determine the buoy–UAV and UAV–OBS association relationships. Finally, the simulation results show that the proposed algorithms can effectively shorten the total mission completion time of data collection and offloading for the multi-UAV-assisted maritime IoT system. |
first_indexed | 2024-03-09T11:21:30Z |
format | Article |
id | doaj.art-b1e16a2e755c47a7a917f8d610a8d7aa |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T11:21:30Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-b1e16a2e755c47a7a917f8d610a8d7aa2023-12-01T00:18:22ZengMDPI AGRemote Sensing2072-42922023-01-0115229210.3390/rs15020292Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning ApproachZiyi Liang0Yanpeng Dai1Ling Lyu2Bin Lin3School of Information Science and Technology, Dalian Maritime University, Dalian 116026, ChinaSchool of Information Science and Technology, Dalian Maritime University, Dalian 116026, ChinaSchool of Information Science and Technology, Dalian Maritime University, Dalian 116026, ChinaSchool of Information Science and Technology, Dalian Maritime University, Dalian 116026, ChinaThis paper studies the integration of data collection and offloading for maritime Internet of Things (IoT) systems with multiple unmanned aerial vehicles (UAVs). In the considered multi-UAV maritime IoT system, the UAVs act as the aerial base stations to complete the missions of data collection from buoys and data offloading to the offshore base station (OBS). In this case, the UAVs need to adaptively select the mission mode between data collection and data offloading according to the network resources and mission requirements. In this paper, we aimed to minimize the completion time of data collection and offloading missions for all UAVs by jointly optimizing the UAV trajectories, mission mode selection, transmit power of buoys, and association relationships between the UAVs and buoy/OBS. In order to solve the mixed-integer non-convex minimization problem, we first designed a multi-agent deep reinforcement learning algorithm based on a hybrid discrete and continuous action space to preliminarily obtain the UAV trajectories, mission mode selection, and the transmit power of buoys. Then, we propose an algorithm based on the stable marriage problem to determine the buoy–UAV and UAV–OBS association relationships. Finally, the simulation results show that the proposed algorithms can effectively shorten the total mission completion time of data collection and offloading for the multi-UAV-assisted maritime IoT system.https://www.mdpi.com/2072-4292/15/2/292maritime IoTdeep reinforcement learningUAV trajectory optimizationhybrid proximal policy optimization |
spellingShingle | Ziyi Liang Yanpeng Dai Ling Lyu Bin Lin Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning Approach Remote Sensing maritime IoT deep reinforcement learning UAV trajectory optimization hybrid proximal policy optimization |
title | Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning Approach |
title_full | Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning Approach |
title_fullStr | Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning Approach |
title_full_unstemmed | Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning Approach |
title_short | Adaptive Data Collection and Offloading in Multi-UAV-Assisted Maritime IoT Systems: A Deep Reinforcement Learning Approach |
title_sort | adaptive data collection and offloading in multi uav assisted maritime iot systems a deep reinforcement learning approach |
topic | maritime IoT deep reinforcement learning UAV trajectory optimization hybrid proximal policy optimization |
url | https://www.mdpi.com/2072-4292/15/2/292 |
work_keys_str_mv | AT ziyiliang adaptivedatacollectionandoffloadinginmultiuavassistedmaritimeiotsystemsadeepreinforcementlearningapproach AT yanpengdai adaptivedatacollectionandoffloadinginmultiuavassistedmaritimeiotsystemsadeepreinforcementlearningapproach AT linglyu adaptivedatacollectionandoffloadinginmultiuavassistedmaritimeiotsystemsadeepreinforcementlearningapproach AT binlin adaptivedatacollectionandoffloadinginmultiuavassistedmaritimeiotsystemsadeepreinforcementlearningapproach |