In maritime data collection scenarios, achieving the rapid delivery of data from buoy sensor nodes to the shipboard station is a challenging issue. Utilizing unmanned aerial vehicles (UAVs) technology to facilitate the transfer of data from buoy sensor nodes, it becomes feasible to significantly reduce the latency generated in the transmission process. Therefore, we introduce a UAV-assisted maritime Internet of Things (MIoT) data collection mechanism based on relay cooperation. In this mechanism, through relay transmissions among UAVs, it avoids UAVs located distant from the shipboard station from having to traverse extensive distances in order to offload data to the shipboard station. Based on this, we propose a deep reinforcement learning-based cooperative data collection (DCDC) scheme. In this scheme, firstly, we select the convergence node in charge of forwarding the data from buoy sensor nodes to the passing UAVs. Next, to achieve dynamic adaptation of the task areas for UAVs, we propose an adaptive partition algorithm based on virtual moving points. Subsequently, to establish relay transmission links between UAVs, we present a routing algorithm based on matching game theory. Finally, to reduce time costs in delivering collected data to the shipboard station, we utilize a deep reinforcement learning algorithm based on multi-agent deep deterministic policy gradient (MADDPG) plan the flight paths of UAVs. Additionally, we introduce virtual waypoints in the path planning algorithm, which enables that paired UAVs can high-efficiently perform data forwarding through encounter opportunities. Extensive simulation experiments have demonstrated that the proposed scheme outperforms existing schemes in terms of system Age of Information (AoI).

Cooperative Data Collection for UAV-Assisted Maritime IoT Based on Deep Reinforcement Learning

Pace P.;Aloi G.;Fortino G.
2024-01-01

Abstract

In maritime data collection scenarios, achieving the rapid delivery of data from buoy sensor nodes to the shipboard station is a challenging issue. Utilizing unmanned aerial vehicles (UAVs) technology to facilitate the transfer of data from buoy sensor nodes, it becomes feasible to significantly reduce the latency generated in the transmission process. Therefore, we introduce a UAV-assisted maritime Internet of Things (MIoT) data collection mechanism based on relay cooperation. In this mechanism, through relay transmissions among UAVs, it avoids UAVs located distant from the shipboard station from having to traverse extensive distances in order to offload data to the shipboard station. Based on this, we propose a deep reinforcement learning-based cooperative data collection (DCDC) scheme. In this scheme, firstly, we select the convergence node in charge of forwarding the data from buoy sensor nodes to the passing UAVs. Next, to achieve dynamic adaptation of the task areas for UAVs, we propose an adaptive partition algorithm based on virtual moving points. Subsequently, to establish relay transmission links between UAVs, we present a routing algorithm based on matching game theory. Finally, to reduce time costs in delivering collected data to the shipboard station, we utilize a deep reinforcement learning algorithm based on multi-agent deep deterministic policy gradient (MADDPG) plan the flight paths of UAVs. Additionally, we introduce virtual waypoints in the path planning algorithm, which enables that paired UAVs can high-efficiently perform data forwarding through encounter opportunities. Extensive simulation experiments have demonstrated that the proposed scheme outperforms existing schemes in terms of system Age of Information (AoI).
2024
Autonomous aerial vehicles
Data collection
Deep reinforcement learning
Heuristic algorithms
Internet of Things
Maritime Internet of Things
Path planning
Relay cooperation
Relays
Task analysis
Unmanned aerial vehicle
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/366138
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact