UAV-Enabled Maritime IoT D2D Task Offloading: A Potential Game-Accelerated Framework.

Area of Science:

• Maritime technology
• Edge computing
• Wireless networking

Background:

• Maritime Internet of Things (IoT) deployments using unmanned surface vessels (USVs) face significant challenges due to limited onboard computing power and unreliable wireless connectivity.
• Compute-intensive tasks like vision and sensing often surpass latency thresholds, hindering real-time decision-making critical for maritime operations.

Purpose of the Study:

• To propose a novel distributed computation offloading framework tailored for maritime IoT scenarios.
• To address latency issues in USV-based systems by integrating device-to-device (D2D) and unmanned aerial vehicle (UAV)-assisted edge computing.

Main Methods:

• Designed a breadth-first search (BFS)-based distributed computation offloading game leveraging USV resources and UAV mobility.
• Formulated a global latency minimization problem, jointly optimizing UAV hovering coordinates and arrival times.
• Solved the optimization problem using a combined Alternating Direction Method of Multipliers (ADMM) and Successive Convex Approximation (SCA) approach.

Main Results:

• The proposed framework effectively reduces latency in maritime IoT systems.
• Simulations demonstrated a significant latency reduction of up to 49.6% compared to conventional offloading methods.
• The joint optimization of UAV parameters proved effective in minimizing overall system latency.

Conclusions:

• The novel distributed computation offloading framework enhances the efficiency of maritime IoT systems.
• The integration of D2D and UAV-assisted edge computing offers a viable solution for overcoming computational and connectivity limitations of USVs.
• This approach significantly improves timely decision-making capabilities in complex maritime environments.