Deep Learning for joint channel estimation and feedback in massive MIMO systems(1)
1.Introduction
In this paper, a comprehensive research is carried out to establish a joint channel estimation and feedback framework for the FDD massive MIMO systems based on DL techniques. The main contributions of this paper are summarized as follows.
- The DL based joint channel estimation and feedback framework of downlink channels in FDD massive MIMO systems is proposed in this paper, which is the first to the best of our knowledge. Two networks are constructed to perform explicit and implicit channel estimation and feedback, respectively. The channel estimation and feedback network (CEFnet) employs a lightweight CNN structure to explicitly obtain the refined estimate of channels and utilizes a denoising autoencoder structure (DAE) to compress and reconstruct the noisy channel matrices. The other pilot compression and feedback network (PFnet) compresses and sends back the pilot information directly to the BS without estimating the channels.
第一次在FDD的模式下設計了基於DL的聯合通道估計和通道資訊反饋，之前的paper大多數只做feedback。提出了顯式和隱式的網路架構，使用了輕量級的CNN架構，使用了去噪模組。 - A multi-signal-to-noise-ratios (SNRs) training technique is proposed to cope with multiple SNR cases so that the construction of multiple individual models for each single SNR can be avoided, which significantly reduces the storage space and makes the trained network robust to channel noise. Moreover, quantization module is enrolled into the whole network to generate data-bearing bitstreams and observe the robustness of the two networks to the quantization distortion.
使網路適應了不同訊雜比的情況（這還是很重要的），同時測試了量化噪聲的影響 - Performance analysis of the proposed two networks is provided. Both proposed networks demonstrate excellent reconstruction capacity while the CEFnet works a little better than PFnet but PFnet generates less parameters that needs storing than CEFnet. Moreover, the two networks are also proved to be robust to the quantization errors and noise.
提供了效能分析
2.System model
2.1 Massive MIMO system
主要考慮FDD的下行鏈路，第
i
i
i根天線的下行鏈路
y
i
=
X
i
h
i
~
y_i=X_i\tilde{h_i}
yi=Xihi~其中，
X
i
∈
C
k
^
×
k
^
X_i\in C^{\hat k\times \hat k}
Xi∈Ck^×k^是一個對角陣，
h
i
~
∈
C
K
^
×
1
\tilde{h_i}\in C^{\hat K\times 1}
hi~∈CK^×1是通道頻域響應,這麼建模的原因詳見關於Y=HX的一些思考，看懂這篇這樣寫公式就好理解了。
總的建模可以寫為
y
=
∑
i
=
1
N
t
X
i
h
i
~
+
n
y=\sum_{i=1}^{N_t}X_i\tilde{h_i}+n
y=i=1∑NtXihi~+n其中
H
~
=
[
h
1
~
,
h
2
~
,
.
.
.
,
h
N
t
~
]
\tilde{H}=[\tilde{h_1},\tilde{h_2},...,\tilde{h_{N_t}}]
H~=[h1~,h2~,...,hNt~]
相關文章
- 閱讀文獻《SCNet：Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System》
- 閱讀文獻《DCRNet：Dilated Convolution based CSI Feedback Compression for Massive MIMO Systems》
- 「Wide & Deep Learning for Recommender Systems」- 論文摘要IDE
- 通道估計（channel estimation）圖解——從SISO到MIMO原理介紹圖解
- Spatio-Temporal Representation With Deep Neural Recurrent Network in MIMO CSI Feedback閱讀筆記筆記
- Deep learning - note 1
- 遷移學習（JDDA） 《Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation》遷移學習AIAPT
- A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation 論文解讀（SIGMOD 2021）Nifi
- Deep Upsupervised Cardinality Estimation 解讀（2019 VLDB）
- Deep Learning with Differential Privacy
- 《DEEP LEARNING·深度學習》深度學習
- 深度學習（Deep Learning）深度學習
- 論文閱讀：Sequence to sequence learning for joint extraction of entities and relations
- 《深度學習》PDF Deep Learning: Adaptive Computation and Machine Learning series深度學習APTMac
- 為行動通訊爭一先：Massive MIMO的進化三部曲
- 5G網路能力領先。創新技術方面，廣泛使用Massive MIMO
- COMP9444 Neural Networks and Deep Learning
- DEEP LEARNING WITH PYTORCH: A 60 MINUTE BLITZ | TENSORSPyTorch
- Join Query Optimization with Deep Reinforcement Learning AlgorithmsGo
- Manning.Deep.Learning.with.Python.2017.11.pdfPython
- 【Coursera GenAI with LLM】 Week 3 Reinforcement Learning from Human Feedback Class NotesAI
- 深度學習（Deep Learning）優缺點深度學習
- DEEP LEARNING WITH PYTORCH: A 60 MINUTE BLITZ | NEURAL NETWORKSPyTorch
- DEEP LEARNING WITH PYTORCH: A 60 MINUTE BLITZ | TRAINING A CLASSIFIERPyTorchAI
- Deep Embedding Learning for Text-Dependent Speaker Verification
- Fauce：Fast and Accurate Deep Ensembles with Uncertainty for Cardinality Estimation 論文解讀（VLDB 2021）ASTAI
- Deep Transfer Learning綜述閱讀筆記筆記
- Paper Reading:A Survey of Deep Learning-based Object DetectionObject
- 貝葉斯深度學習（bayesian deep learning）深度學習
- Deep Learning with Python.pdf 免費下載Python
- Ranked List Loss for Deep Metric Learning | 論文分享
- 深度學習 DEEP LEARNING 學習筆記（一）深度學習筆記
- 深度學習 DEEP LEARNING 學習筆記（二）深度學習筆記
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation3DSegmentation
- 論文解讀（GRACE）《Deep Graph Contrastive Representation Learning》AST
- 【論文筆記】A Survey on Deep Learning for Named Entity Recognition筆記
- DQN（Deep Q-learning）入門教程（四）之Q-learning Play Flappy BirdAPP
- 《A Discriminative Feature Learning Approach for Deep Face Recognition》閱讀筆記APP筆記