AI/ML无线通信

3GPP RAN #94e会议上确定了28项R18研究项目，其中有两项AI与通信结合的项目，分别是AI/ML for NR air interface和AI/ML for NG-RAN。

在3GPP标准化立项之前，关于AI与无线通信相结合的学术研究已经有很多，主要几种在几个方面：

信道估计Channel Estimation:利用深度学习算法获得比传统信道估计算法更好的性能。

• 《Deep Learning-Based Channel Estimation》
• 《Power of deep learning for channel estimation and signal detection in ofdm systems》
• 《Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system》

信道状态反馈CSI feedback：利用深度学习算法在降低overhead的同时保持并提升性能。

• 《Deep learning for massive mimo csi feedback》
• 《Deep learning-based CSI feedback approach for time-varying massive MIMO channels》

波束管理Beam Management：利用深度学习算法提升mmWave网络的覆盖

• 《Deep learning-based beam management and interference coordination in dense mmWave networks》

在2022年MWC上，高通展示了新一代X70 5G基带芯片，号称世界第一款Modem-RF 5G AI处理器。通过AI提升5G性能，其中包括AI-based channel-state feedback and optimization，AI-based mmWave beam management，AI-based network selection，AI-based adaptive antenna tuning四个主要的方面。

从高通所公开的信息中，可以看到，通过AI-based mmWave beam management技术可以提升28%的覆盖。通过AI-based channel-state feedback and optimization技术可以在小区边缘提升26%吞吐量，在小区中间可以提升12%吞吐量。

参考：

1. SOLTANI, MEHRAN, POURAHMADI, VAHID, MIRZAEI, ALI, et al. Deep Learning-Based Channel Estimation[J]. IEEE communications letters: A publication of the IEEE Communications Society,2019,23(4):652-655. DOI:10.1109/LCOMM.2019.2898944.
2. Ye H ,  Li G Y ,  Juang B H . Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems[J]. IEEE Wireless Communications Letters, 2017.
3. Huang H , Yang J , Song Y , et al. Deep Learning for Super-Resolution Channel Estimation and DOA Estimation Based Massive MIMO System[J]. IEEE Transactions on Vehicular Technology, 2018, PP:1-1.
4. Wen C K , Shih W T , Jin S . Deep Learning for Massive MIMO CSI Feedback[J]. IEEE Wireless Communications Letters, 2017:1-1.
5. Wang T , Wen C K , Jin S , et al. Deep Learning-based CSI Feedback Approach for Time-varying Massive MIMO Channels[J]. IEEE Wireless Communications Letters, 2018:1-1.
6. Pei, Zhou, Xuming, et al. Deep Learning-Based Beam Management and Interference Coordination in Dense mmWave Networks[J]. IEEE Transactions on Vehicular Technology, 2018.
7. https://www.qualcomm.com/media/documents/files/mwc-2022-enabling-the-5g-ai-era.pdf