Clustering-based Joint Channel Estimation and Signal Detection for Grant-free NOMA

TL;DR

This paper introduces an unsupervised clustering method for joint channel estimation and signal detection in uplink NOMA, achieving near-optimal SER performance without requiring channel state information by leveraging Gaussian mixture models.

Contribution

It presents a novel clustering-based approach for joint channel estimation and detection in uplink NOMA that does not rely on channel state information at the receiver.

Findings

Achieves SER performance comparable to maximum likelihood detection with full CSI.

Performance depends on the number of data points, offering a tradeoff between accuracy and block length.

Effective when user received powers are sufficiently different.

Abstract

We propose a joint channel estimation and signal detection technique for the uplink non-orthogonal multiple access using an unsupervised clustering approach. We apply the Gaussian mixture model to cluster received signals and accordingly optimize the decision regions to enhance the symbol error rate (SER). We show that when the received powers of the users are sufficiently different, the proposed clustering-based approach with no channel state information (CSI) at the receiver achieves an SER performance similar to that of the conventional maximum likelihood detector with full CSI. Since the accuracy of the utilized clustering algorithm depends on the number of the data points available at the receiver, the proposed technique delivers a tradeoff between the accuracy and block length.