Joint Computation Offloading and Resource Allocation for Maritime MEC With Energy Harvesting

In this article, we establish a multiaccess edge computing (MEC)-enabled sea lane monitoring network (MSLMN) architecture with energy harvesting (EH) to support dynamic ship tracking, accident forensics, and anti-fouling through real-time maritime traffic scene monitoring. Under this architecture, the computation offloading and resource allocation are jointly optimized to maximize the long-term average throughput of MSLMN. Due to the dynamic environment and unavailable future network information, we employ the Lyapunov optimization technique to tackle the optimization problem with large state and action spaces and formulate a stochastic optimization program subject to queue stability and energy consumption constraints. We transform the formulated problem into a deterministic one and decouple the temporal and spatial variables to obtain asymptotically optimal solutions. Under the premise of queue stability, we develop a joint computation offloading and resource allocation (JCORA) algorithm to maximize the long-term average throughput by optimizing task offloading, subchannel allocation, computing resource allocation, and task migration decisions. Simulation results demonstrate the effectiveness of the proposed scheme over existing approaches.

I. Introduction

Nowadays, more than 80% of the total international cargo transportation is carried over the sea. The increasing maritime activities, such as maritime transportation, sea lane monitoring, and marine resource extraction, lead to high demand for maritime information exchange [1], [2], [3], [4], [5]. On one hand, the density of marine vessels (especially the ones near big harbors) is increasing tremendously, which puts forward higher requirements for intervessel connections through advanced wireless communication technologies [e.g., long term evolution (LTE)] for information dissemination. On the other hand, the information sharing from diversified applications to realize the “smart ocean” often requires high-data rates and low-transmission latency. For example, in the sea lane monitoring scenario, it is necessary to quickly analyze and process the collected images/videos of sea lanes, to make real-time prediction on vessel behaviors and provide accurate navigation assistance and efficient navigation services for vessels. Generally, to achieve more intelligent and responsive event monitoring, video perception, and dynamic tracking, a large amount of data needs to be sensed/collected and processed promptly which inevitably increases the on-vessel computation burden. However, due to geographical restrictions, the allocation of communication and computing resources from terrestrial networks to support maritime services is often limited, which poses significant challenges when supporting massive communication and computing demands. It is imperative to develop a more efficient networking and computing solution to achieve better performance for massive maritime data transmission and task processing.