Semantic Scholar Open Access 2017 1056 sitasi

Deep Learning for Massive MIMO CSI Feedback

Chao-Kai Wen Wan-Ting Shih Shi Jin

Lihat Sumber DOI

Abstrak

In frequency division duplex mode, the downlink channel state information (CSI) should be sent to the base station through feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However, such a transmission is hindered by excessive feedback overhead. In this letter, we use deep learning technology to develop CsiNet, a novel CSI sensing and recovery mechanism that learns to effectively use channel structure from training samples. CsiNet learns a transformation from CSI to a near-optimal number of representations (or codewords) and an inverse transformation from codewords to CSI. We perform experiments to demonstrate that CsiNet can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.

Topik & Kata Kunci

Computer Science Mathematics

Penulis (3)

Chao-Kai Wen

Wan-Ting Shih

Shi Jin

Format Sitasi

APA MLA BibTeX

Wen, C., Shih, W., Jin, S. (2017). Deep Learning for Massive MIMO CSI Feedback. https://doi.org/10.1109/LWC.2018.2818160

Akses Cepat

Lihat di Sumber doi.org/10.1109/LWC.2018.2818160

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Total Sitasi: 1056×
Sumber Database: Semantic Scholar
DOI: 10.1109/LWC.2018.2818160
Akses: Open Access ✓