Predictive Analytics Integrated Multi-level Optimization of Offshore Connectivity in Ocean Network

Abstract

One of the primary difficulties of fishermen engaged in deep-sea fishing is the lack of effective communication systems to the shore. The Offshore Communication Network(OCN) resolves this problem by providing Internet over the ocean through a fishing vessel network. OCN is a multi-layered architecture with heterogeneous connectivity ranges, directionality, resources, and mobility patterns. Connectivity maintenance is challenging due to the lack of infrastructure, expanded mobility, network sparsity, and sea-wave-induced movements. This paper discusses a framework to improve OCN connectivity with a multi-level optimization strategy. We propose a predictive model to generate real-time forecasts of link status. At the physical level, node position re-orientations to higher connectivity locations are suggested. The transmission queue management and prioritized scheduling in the link-layer minimize the queuing delay. A reinforcement routing strategy in the network layer determines the best next-hop for message dissemination. The proposed threelevel optimization approach facilitates communication capability enhancement in OCN.

Link Characterization and Edge-Centric Predictive Modeling in an Ocean Network

“…Figure 1 presents the architecture. A comprehensive description of the communication architecture and the routing schemes of OCN can be found in companion papers [1], [3], [4], [5], [6].…”

“…and then H 0 corresponds to ξ (4) = ξ (5) = 0. which admits a coefficient test in a multilinear regression model…”