Hybrid modeling improves wireless signal maps with accurate physics
Hybrid Ray-Tracing and Physics-Embedded Neural Modeling for High-Fidelity Channel Reconstruction in Wireless Digital Twins
Networking and Internet Architecture
Summary
Wireless signals can be hard to predict accurately indoors, especially when signals bend or bend around objects. The authors show how combining traditional ray-tracing methods with special neural networks that understand physics can create better maps of wireless signals. Their method focuses computing power only where it matters most, making it both accurate and efficient. This helps build realistic digital models of wireless environments for better network planning.
What this means in practice
- •For wireless network planners: Improve indoor radio coverage maps by combining hybrid ray-tracing and neural modeling for more accurate signal prediction where bending and diffraction occur.
- •For antenna designers: Use the hybrid modeling approach to simulate realistic wave interactions with complex materials and geometries during antenna placement and tuning processes.
Authors
Huiwen Zhang, Chu Ma, Feng Ye
Abstract
Many existing wireless digital twins (DTs) rely heavily on ray-tracing (RT)-based channel simulators to achieve scalability in large-scale environments. However, the geometric-optics (GO) approximations underlying RT become inaccurate in propagation regimes dominated by diffraction and refraction, which are prevalent at sub-6 GHz carrier frequencies. This paper presents a hybrid RT and physics-embedded physics-informed neural network (PE-PINN) framework that enhances site-specific wireless DTs with physics-consistent full-wave accuracy. Building on prior PE-PINN work, we introduce targeted architectural extensions, including a finite-length edge diffraction kernel and a lossy dielectric formulation based on complex wavenumbers, to accurately model electromagnetic wave interactions with realistic objects and materials. To balance accuracy and efficiency, we further propose a localized tunnel strategy that deploys PE-PINN models only along dominant propagation paths, selectively replacing or augmenting RT predictions in regions where GO assumptions break down. Comprehensive evaluations against full-wave COMSOL simulations demonstrate that the proposed framework closely matches reference solutions and significantly outperforms RT-only approaches in diffraction- and refraction-dominated scenarios. We further demonstrate seamless integration of the proposed approach into a realistic indoor wireless DT, highlighting its practicality and scalability for next-generation wireless network design.