User-Centric Stream Sensing for Grant-Free Access: Deep Learning with Covariance Differencing

TL;DR

This paper introduces a deep learning-based covariance differencing method for user-centric stream sensing in grant-free access, effectively detecting new streams in overloaded scenarios to improve massive connectivity.

Contribution

It presents a novel differential sensing framework that combines covariance differencing with deep learning to enhance detection in overloaded grant-free access environments.

Findings

Outperforms non-DL baseline methods in simulations.

Robust in overloaded scenarios with more streams than antennas.

Provides a theoretical bound for sensing window size based on channel correlation.

Abstract

Grant-free (GF) access is essential for massive connectivity but faces collision risks due to uncoordinated transmissions. While user-side sensing can mitigate these collisions by enabling autonomous transmission decisions, conventional methods become ineffective in overloaded scenarios where active streams exceed receive antennas. To address this problem, we propose a differential stream sensing framework that reframes the problem from estimating the total stream count to isolating newly activated streams via covariance differencing. We analyze the covariance deviation induced by channel variations to establish a theoretical bound based on channel correlation for determining the sensing window size. To mitigate residual interference from finite sampling, a deep learning (DL) classifier is integrated. Simulations across both independent and identically distributed flat Rayleigh fading and standardized channel environments demonstrate that the proposed method consistently outperforms non-DL baselines and remains robust in overloaded scenarios.