# Phase-Aware CNN for Real-Time 5G/6G Channel Estimation with Hardware-in-the-loop Validation

arXiv: https://arxiv.org/abs/2608.14676 · HTML: https://mlsanity.com/paper/2608.14676/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Deep Learning-Based Channel Estimation](https://mlsanity.com/paper/1810.05893/) (2018)
- [Learning to Decode Linear Codes Using Deep Learning](https://mlsanity.com/paper/1607.04793/) (2016)
- [An Attention-Aided Deep Learning Framework for Massive MIMO Channel Estimation](https://mlsanity.com/paper/2108.09430/) (2021)
- [Massive MIMO Channel Prediction Via Meta-Learning and Deep Denoising: Is a Small Dataset Enough?](https://mlsanity.com/paper/2210.08770/) (2022)
- [Deep Learning Based Channel Estimation in High Mobility Communications Using Bi-RNN Networks](https://mlsanity.com/paper/2305.00208/) (2023)
- [Channel Estimation under Hardware Impairments: Bayesian Methods versus Deep Learning](https://mlsanity.com/paper/2208.04033/) (2022)
- [Uncertainty Aware Deep Learning Model for Secure and Trustworthy Channel Estimation in 5G Networks](https://mlsanity.com/paper/2305.02741/) (2023)
- [Uplink OFDM Channel Prediction with Hybrid CNN-LSTM for 6G Non-Terrestrial Networks](https://mlsanity.com/paper/2502.09326/) (2025)

## Abstract (arXiv)

In 5G/6G wireless systems, accurate and timely channel estimation is critical to ensure reliable communication under complex, fast-changing radio conditions. This work focuses on pilot-based channel estimation using deep learning to reconstruct both magnitude and phase across the full subcarrier grid, with particular emphasis on evaluation using emulated data collected from an end-to-end O-RAN testbed. The testbed includes hardware in the loop and controlled channel emulation to better reflect deployment conditions beyond pure software simulation. It addresses major limitations in classical estimators such as LS and MMSE, as well as deep learning-based approaches that struggle with phase prediction due to discontinuities at ± π, poor generalization to different UE and antenna configurations, and computational inefficiency for real-time deployment. The proposed system combines a phase-aware input encoding using sine and cosine representations with a lightweight Convolutional Neural Network (CNN) architecture. This design achieves high accuracy, stable phase reconstruction, strong generalization across testbed-derived datasets, and real-time inference suitable for edge devices.