Context-Aware CSI Prediction for Access Point Selection Utilizing Conditional VAEs

TL;DR

This paper introduces a conditional variational autoencoder-based method for predicting channel state information in indoor wireless environments, enabling proactive access point selection without continuous CSI estimation.

Contribution

The novel approach models the relationship between user/object positions and CSI using cVAE, trained on noisy data, to infer channel statistics for AP selection.

Findings

The method accurately predicts CSI from position data in simulations.

It does not require ground-truth CSI for training.

Proactive AP selection improves network performance.

Abstract

Indoor wireless communication environments are strongly influenced by dynamic conditions, which affect channel state information (CSI) and, consequently, the precoding strategy and the selection of the access point (AP). Device-free sensing and localization functionalities can provide information about these conditions, including, for example, the user's position and the position of mobile blocking objects. To model the statistical relationship between the CSI and the provided conditions, we employ a conditional variational autoencoder (cVAE). We treat the user and object positions - referred to as context information - as conditional inputs to the cVAE. The proposed model does not rely on ground-truth CSI and is trained directly on noisy data. Once trained, the framework can infer channel statistics solely from user and blocking object positions, enabling proactive AP selection based on inferred statistical CSI without requiring continuous CSI estimation. Extensive simulations with the state-of-the-art ray-tracing tool Sionna validate the proposed method.