Automated Modeling Method for Pathloss Model Discovery

TL;DR

<3-5 sentence high-level summary> The paper tackles automated discovery of pathloss models to enable accurate and interpretable propagation modeling for 5G and beyond. It introduces two AI-driven approaches—Kolmogorov-Arnold Networks (KANs) for high-accuracy, spline-based interpretable mappings, and Deep Symbolic Regression (DSR) for compact, explicit expressions—applied to ABG/CI analytical models and indoor/outdoor empirical data. Across synthetic and real datasets, KANs deliver near-perfect fits while DSR yields concise, interpretable formulas; in several cases automated methods outperform traditional PL models by substantial margins. The work provides open-source AutoPL workflows and highlights trade-offs between accuracy and interpretability, guiding future development of automated, explainable PL models for next-generation wireless systems.

Abstract

Modeling propagation is the cornerstone for designing and optimizing next-generation wireless systems, with a particular emphasis on 5G and beyond era. Traditional modeling methods have long relied on statistic-based techniques to characterize propagation behavior across different environments. With the expansion of wireless communication systems, there is a growing demand for methods that guarantee the accuracy and interpretability of modeling. Artificial intelligence (AI)-based techniques, in particular, are increasingly being adopted to overcome this challenge, although the interpretability is not assured with most of these methods. Inspired by recent advancements in AI, this paper proposes a novel approach that accelerates the discovery of path loss models while maintaining interpretability. The proposed method automates the formulation, evaluation, and refinement of the model, facilitating the discovery of the model. We examine two techniques: one based on Deep Symbolic Regression, offering full interpretability, and the second based on Kolmogorov-Arnold Networks, providing two levels of interpretability. Both approaches are evaluated on two synthetic and two real-world datasets. Our results show that Kolmogorov-Arnold Networks achieve the coefficient of determination value R^2 close to 1 with minimal prediction error, while Deep Symbolic Regression generates compact models with moderate accuracy. Moreover, on the selected examples, we demonstrate that automated methods outperform traditional methods, achieving up to 75% reduction in prediction errors, offering accurate and explainable solutions with potential to increase the efficiency of discovering next-generation path loss models.

Figures (11)

• Figure 1: The flow diagram of AutoPL modeling method.
• Figure 2: The flow diagram of developing a pathloss model using KANs.
• Figure 3: The flow diagram of developing a pathloss model using DSR.
• Figure 4: The predicted values by the KAN model vs the actual generated by $PL^{ABG}$ according to Eq. (\ref{['eq:abg']}) as per parameters in Table \ref{['tab:ABG_CI_parameters']}.
• Figure 5: The learned KAN [6,6,1] network for approximating $PL^{ABG}$.