Harsh Weather-Oriented Edge Intelligence Empowered Maritime Communication-Computing Converged Network Resource Allocation

Unmanned maritime surveillance systems (UMSS), consisting of Unmanned Surface Vessels (USVs) and smart buoys, as a typical application of the maritime Communication-Computing Converged Network (CCCN), play a crucial role in combating illegal fishing, smuggling, and piracy. However, the 2D images on which UMSS relies often lack spatial depth, and although 3D point cloud data can compensate for this limitation, complex and harsh weather degrades their quality and increases data volume. This increases the communication and computational burden, making efficient resource allocation far more complex, impairing UMSS’s responsiveness in dynamic maritime conditions. To address these issues, this paper proposes an edge intelligence-based real-time resource allocation framework for UMSS. Unlike existing works that only consider resource allocation, our framework also accounts for the impact of 3D point cloud data quality on system performance in harsh weather conditions. Specifically, it first leverages 3D point cloud data with a dehazing algorithm to mitigate haze-induced data expansion. Then we formulate an optimization problem to dynamically trade off throughput, latency, and Energy Consumption (EC) under varying maritime conditions. Finally, we utilize Deep Deterministic Policy Gradient (DDPG) methods to solve this problem. Additionally, we design task allocation strategies tailored to different maritime services. Simulation results show that our approach reduces average latency by 13%, lowers EC by 20%, and increases throughput by 10%, to guarantee the timely fulfillment of all tasks and improve the efficiency of UMSS under harsh weather conditions.