Cooperative Computing Offloading Scheme via Artificial Neural Networks for Underwater Sensor Networks

Abstract

Aiming at the problem of being unable to meet some high computing power, high-precision applications due to the limited capacity of underwater sensor nodes, and the difficulty of low computation power, in this paper, we introduce the edge servers, known as base stations for underwater sensor nodes, and propose a scheme to process the computational tasks based on coalition game theory. This scheme provides functions such as cooperation among different base stations within the coalition, the smart division of tasks, and efficient computational offloading. In order to reduce the complexity of the algorithm, the artificial neural network model is introduced into the method. Each task is divided into sub-parts and fed to an artificial neural network for training, testing, and validation. In addition, the scheme delivers the computed task from base stations back to sink nodes via a shortened path to enhance the service reliability. Due to the mobility of the base station in the ocean, our proposed scheme takes into account the dynamic environment at the same time. The simulation results show that, compared with the existing state-of-the-art methods, the success rate of our proposed approach improves by 30% compared with the Greedy method. The total service time of our proposed approach decreases by 12.6% compared with the Greedy method and 31.2% compared with the Always-Migrate method.

Game theory based maritime area detection for cloud-edge collaboration satellite network

“…An efficient computation offloading and resource allocation scheme in edge computing networks for the Internet of Vehicles is proposed to achieve low complexity and significantly improve system performance [10]. A collaborative computation offloading scheme is proposed to shorten the total service time for the problem of limited computation capability of underwater sensor nodes [11]. The authors in the paper [12] proposed a heterogeneous edge-cloud computing framework, in which a novel collaborative offloading scheme was designed to minimize the task execution latency.…”

PPO-Based Joint Optimization for UAV-Assisted Edge Computing Networks

“…Moreover, a two-stage joint optimization scheme was proposed for mobile edge computing using federated learning in [13]. Similar to federated learning, the work in [14] presents an edge computing collaboration and offloading optimization problem for underwater sensor networks. The study designed an artificial neural network model to solve this issue.…”

“…At the same time, UAVs are highly maneuverable, and by adjusting the hovering position of UAVs, the latency of the computation task can also be effectively reduced. Compared to the existing work [13][14][15], this scenario focuses on possible problems with the wireless link and compensates for the degradation of the channel quality by means of UAVs. The proposed scheme can be adapted to application scenarios such as large cities with heavy building occlusion and mountains with geographic occlusion.…”

A Dynamic Trust Model for Underwater Sensor Networks Fusing Deep Reinforcement Learning and Random Forest Algorithm

“…The unique attributes of underwater acoustic channels, including substantial transmission delays, constrained bandwidth, Doppler frequency shifts, node mobility, and pronounced multipath effects, present a formidable challenge to the security of underwater acoustic sensor networks. Ensuring the dependability and security of underwater data transmission stands as a pressing issue demanding attention [5,6].…”