Physics inspired network improves wireless signal loss prediction accuracy
HankelKANet: Lightweight Path Loss Estimation via Physics-Inspired Hankel Convolution
Machine LearningNetworking and Internet Architecture
Summary
Wireless signals weaken as they travel through cities, and knowing exactly how much they weaken helps with planning networks. The authors designed HankelKANet, a lightweight AI that mimics physical laws of wave travel to predict this weakening more accurately and efficiently. This model uses special math functions to represent distances, which helps it avoid learning unrealistic patterns and improves its usefulness in the real world. Tests show HankelKANet beats previous methods, needing fewer resources while giving better predictions on both fake and real data.
What this means in practice
- •For wireless network planners: Improve accuracy and efficiency of urban wireless signal coverage predictions to optimize network design and deployment.
- •For smart city infrastructure teams: Use robust path loss estimates that generalize well across different city layouts to enhance communication system reliability.
Authors
Yue Ruan, Xiaoxiao Cheng, Yunan Zhu, Wenlong Huang, Meng Hua
Abstract
Accurate path loss (PL) estimation is essential for wireless network planning and optimization. This paper proposes HankelKANet, a lightweight physics-inspired network for PL estimation that structurally embeds electromagnetic propagation characteristics into the neural architecture. Built on a single residual UNet backbone, the proposed model integrates urban layout features with a convolutional Kolmogorov-Arnold network(KAN). Specifically, the convolutional kernels are parameterized by the radial amplitudes of the zeroth- and first-order Hankel functions. This formulation acts as a physics-inspired nonlinear distance encoding, enabling the network to capture dominant attenuation characteristics directly without requiring additional physics-based loss terms. Experimental results demonstrate that HankelKANet achieves state-of-the-art accuracy and efficiency on both the simulated RadioMapSeer dataset and the real-world Huawei RSRPSet. Compared with the leading baseline, PEFNet, it reduces the parameter count by 78% and lowers the RMSE by 16.96% on the simulated data, while further exhibiting robust cross-dataset transferability and high data efficiency during target-domain adaptation. To interpret these empirical gains, we mathematically establish a parameter-conditional spatial gradient bound. Using discrete Dirichlet energy (DDE) and Jacobian sensitivity heatmaps, we empirically verify that this physical encoding intrinsically constrains the network's spatial derivatives. This structural smoothness effectively eliminates non-physical spatial ripples, preventing overfitting to simulator artifacts and serving as the fundamental driver for robust real world generalization.