End-to-End Autoencoder Design for MU-MIMO Systems With Low Pilot Overhead

View Full Paper

Ask AI

Bookmark

Authors

Discussion

An end-to-end autoencoder design achieves robust channel estimation in MU-MIMO systems, suggesting improved efficiency in data transmission.

Accurate channel estimation is achieved with less than 3% pilot overhead, reducing communication delays.
The proposed system outperforms traditional least-squares estimation by 6.6 dB in mean square error under the 3GPP TR 38.901 model.
The end-to-end architecture optimizes transmitter and receiver through supervised learning, enhancing overall system efficiency.
Simulation results indicate improved symbol error rate by up to 3 dB compared to the zero-forcing equalization baseline.

Velloso et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

An end-to-end autoencoder design achieves robust channel estimation in MU-MIMO systems, suggesting improved efficiency in data transmission.

Accurate channel estimation is achieved with less than 3% pilot overhead, reducing communication delays.
The proposed system outperforms traditional least-squares estimation by 6.6 dB in mean square error under the 3GPP TR 38.901 model.
The end-to-end architecture optimizes transmitter and receiver through supervised learning, enhancing overall system efficiency.
Simulation results indicate improved symbol error rate by up to 3 dB compared to the zero-forcing equalization baseline.

Velloso et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark