Model-based vs. Data-driven Approaches for Predicting Rain-induced Attenuation in Commercial Microwave Links: A Comparative Empirical Study

The analysis and forecasting of the real-time rain-induced attenuation patterns in terrestrial microwave links have gained increasing attraction in communications and meteorological fields, allowing pre-planning for upcoming occurrences. This paper presents an empirical study of model-based and data-driven techniques applied for multistep predictions of rain attenuation in terrestrial microwave links. Data-driven approach was recently adopted in many research fields, including in the time series forecasting tasks, allowing the modeling of complex data patterns without assuming a specific model representation. The superiority of such algorithms over traditional time series methods has yet to be resolved for the rain attenuation predictions. We provide a comprehensive evaluation through empirical analysis using real-world measurements by comparing the performances of six main state-of-the-art algorithms involving two dimensions: the available training dataset and forecast horizon.