Prediction of Received Power in Low-Power Networks Deployed on the Surface of Rough Waters

• DOI: 10.48550/arxiv.2502.14107
• Publication Date: 2025-02-19
• Authors: Waltenegus Dargie; Christian Poellab...; Abiy Tasissa
• Keywords: Rough surface

Low-power and cost-effective IoT sensing nodes enable scalable monitoring of different environments. Some these environments impose rough extreme operating conditions, requiring continuous adaptation reconfiguration physical link layer parameters. In this paper, we closely investigate the stability wireless links established between deployed on surface water bodies propose a model to predict received power. Our is based Minimum Mean Square Estimation (MMSE) relies statistics power motion experience during communication. One drawbacks MMSE its reliance matrix inversion, which at once computationally expensive difficult implement with resource constrained devices. We forgo stage by estimating parameters using gradient-descent approach, much simpler implement. The achieves prediction accuracy 91% even small number iterations.