C-GRBFnet: A Physics-Inspired Generative Deep Neural Network for Channel Representation and Prediction

TL;DR

This paper introduces C-GRBFnet, a physics-inspired deep neural network that accurately predicts wireless channel responses from user location data, leveraging a combination of neural and basis function models for improved efficiency and robustness.

Contribution

The paper proposes a novel physics-inspired generative neural network combining DNN, GRBF, and SIREN for efficient channel prediction from minimal data, extending to MIMO channels.

Findings

Higher prediction accuracy compared to existing models

Faster convergence and smaller network scale

Enhanced robustness to channel estimation errors

Abstract

In this paper, we aim to efficiently and accurately predict the static channel impulse response (CIR) with only the user's position information and a set of channel instances obtained within a certain wireless communication environment. Such a problem is by no means trivial since it needs to reconstruct the high-dimensional information (here the CIR everywhere) from the extremely low-dimensional data (here the location coordinates), which often results in overfitting and large prediction error. To this end, we resort to a novel physics-inspired generative approach. Specifically, we first use a forward deep neural network to infer the positions of all possible images of the source reflected by the surrounding scatterers within that environment, and then use the well-known Gaussian Radial Basis Function network (GRBF) to approximate the amplitudes of all possible propagation paths. We further incorporate the most recently developed sinusoidal representation network (SIREN) into the proposed network to implicitly represent the highly dynamic phases of all possible paths, which usually cannot be well predicted by the conventional neural networks with non-periodic activators. The resultant framework of Cosine-Gaussian Radial Basis Function network (C-GRBFnet) is also extended to the MIMO channel case. Key performance measures including prediction accuracy, convergence speed, network scale and robustness to channel estimation error are comprehensively evaluated and compared with existing popular networks, which show that our proposed network is much more efficient in representing, learning and predicting wireless channels in a given communication environment.