Machine learning-driven cellular–satellite multi-connectivity for monitoring livestock transport in rural areas

Emerging domains such as wireless industrial control, vehicular communications, smart grids, and augmented reality demand low latency, high throughput, and high reliability from wireless communication systems. Unfortunately, single connectivity (SC) communications frequently fail to fulfill these stringent requirements. To address these challenges, employing a multi-connectivity (MC) solution appears to be a promising technique. In this paper, in the context of Horizon Europe COMMECT project, we seek to develop a multi-connectivity solution that intelligently integrates cellular and satellite networks for the purpose of monitoring livestock transport in rural regions where 5G coverage is limited. Multi-connectivity can be helpful for meeting EU regulations requiring seamless communication between transport units and the operational center to ensure animal welfare during transit. To achieve this, we employ machine learning (ML) models within a Classification and Regression framework in the proposed multi-connectivity solution. The ML models process radio-related key performance indicators (KPIs) as inputs to estimate network throughput and latency. The outputs of the model are used to decide whether to continue with the cellular link or activate the backup satellite link in the multi-connectivity setup, ensuring an almost uninterrupted connection. This capability is particularly crucial in regions where 5G coverage is limited, and maintaining a reliable connection is essential. To evaluate the proposed framework, we used a hybrid emulation setup based on experimental data collected in the northern part of Denmark. The emulation results demonstrate that the MC solution significantly outperforms the cellular SC. Although our solution is designed for livestock transport monitoring, it can be adapted for other applications, such as precision farming, in areas with insufficient 5G availability.