這項研究提出了一種基於深度學習的協同式預編碼器設計。考慮在多細胞下行鏈路系統下，在基地台之間進行速率有限的通道資訊（channel state information）交換。本研究提出了兩種通道資訊壓縮技術，一種基於二元化卷積神經網絡（convolutional neural network），另一種基於深度學習型向量量化（vector-quantization）碼本。前者利用基於卷積神經網絡的通道資訊特徵提取器直接計算要與其他基地台交換的二元化特徵向量。後者利用基於深度學習的向量量化碼本對在特徵提取器輸出處獲得的通道資訊特徵向量進行編碼。在這兩種情況下，每個基地台將從其他基地台接收量化後的通道資訊特徵用作預編碼器網絡的輸入，該預編碼器網絡使用多任務學習結構生成標準化的預編碼向量和發射功率。通過使用加權最小均方誤差（weighted-MMSE）演算法的解作為訓練標記(label)，可以在所有基地台上聯合執行通道資訊壓縮和發射預編碼器網絡的端到端訓練。通過這樣做，通道資訊壓縮網絡將能夠提取對於基地台處的預編碼器計算最有效的通道資訊特徵。此外，為了實現模型良好擴充性的機制，我們考慮了一種環繞機制，使得所有細胞都具有對稱行為。模型中考慮了監督式和非監督式的訓練方案。在監督式的訓練方案中，一樣是使用加權最小均方誤差演算法的解作為訓練標記，而在非監督的訓練方案中，負的最大化總和傳輸速率直接作為反向傳播的損失函數。我們的模擬結果表明，即使在交換的比特數很小的情況下，所提出的方案也可以實現接近全通道資訊情況下的總和傳輸速率，並且優於現有的隨機向量量化方法。

This work proposes a deep-learning (DL) based coordinated precoder design for multicell downlink systems with rate-limited exchange of channel state information (CSI) among base-stations (BSs). Two CSI compression techniques are proposed, one based on a binarized convolutional neural network (CNN) and one based on a learned vector-quantization (VQ) codebook. The former utilizes a CNN-based CSI feature extractor to directly compute the binary feature vector that is to be exchanged with other BSs. The latter utilizes a DL-based VQ codebook to encode the CSI feature vector that is obtained at the output of the feature extractor. In both cases, each BS takes the rate-limited CSI received from other BSs as input to a precoder network that produces the normalized precoding vectors and the transmit powers using a multitask learning architecture. By using solutions of the weighted minimum mean square error (WMMSE) algorithm as the output labels, end-to-end training of both the CSI compression and transmit precoder networks is performed jointly at all BSs. By doing so, the CSI compression networks will be able to extract the CSI features that are most effective for precoder computation at the BSs. Furthermore, to achieve the scalability of our model, we consider a wrap-around mechanism in which the network is extended to include six additional copies of the original cell, such that all cells have symmetric behavior. Both supervised and unsupervised learning scenarios are considered in the model. In the supervised learning scenario, the label also uses the solution of the WMMSE algorithm whereas, in the unsupervised learning scenario, the negative weighted sum rate is used directly as the loss function for backpropagation. Our simulation results show that the proposed schemes can achieve weighted sum rates close to that in the full CSI scenario, even when the number of exchanged bits is small, and outperform existing random VQ methods.

[1] D. Gesbert, S. Hanly, H. Huang, S. Shamai Shitz, O. Simeone, andW. Yu, “Multi-cell MIMO cooperative networks: A new look at interference,” IEEE Trans. Commun., vol. 28, pp. 1380–1408, Dec 2010.
[2] J. Zhang, R. Chen, J. G. Andrews, A. Ghosh, and R. W. Heath, “Networked MIMO with clustered linear precoding,” IEEE Trans. Wireless Commun., vol. 8, pp. 1910–1921, Apr 2009.
[3] R. Zhang, “Cooperative multi-cell block diagonalization with per-base-station power constraints,” IEEE Journal on Selected Areas in Communications, vol. 28, pp. 1435–1445, Dec2010.
[4] J. Zhao, T. Q. S. Quek, and Z. Lei, “Coordinated multipoint transmission with limited backhaul data transfer,” IEEE Transactions on Wireless Communications, vol. 12, pp. 2762–2775, June 2013.
[5] S. He, Y. Huang, S. Jin, F. Yu, and L. Yang, “Max-Min energy efficient beamforming for multicell multiuser joint transmission systems,” IEEE Communications Letters, vol. 17, pp. 1956–1959, October 2013.
[6] M. Li, I. B. Collings, S. V. Hanly, C. Liu, and P. Whiting, “Multicell coordinated scheduling with multiuser zero-forcing beamforming,” IEEE Transactions on Wireless Communications, vol. 15, no. 2, pp. 827–842, 2016.
[7] S. S. Christensen, R. Agarwal, E. De Carvalho, and J. M. Cioffi, “Weighted sum-rate maximization using weighted MMSE for MIMO-BC beamforming design,” IEEE Transactions on Wireless Communications, vol. 7, pp. 4792–4799, Dec. 2008.
[8] H. Dahrouj and W. Yu, “Coordinated beamforming for the multicell multi-antenna wireless system,” IEEE Trans. Wireless Commun., vol. 9, pp. 1748–1759, May 2010.
[9] Y. Liu, Y. Dai, and Z. Luo, “Coordinated beamforming for MISO interference channel: Complexity analysis and efficient algorithms,” IEEE Trans. Signal Process., vol. 59, pp. 1142–1157, Mar 2011.
[10] S. He, Y. Huang, S. Jin, and L. Yang, “Coordinated beamforming for energy efficient transmission in multicell multiuser systems,” IEEE Trans. Commun., vol. 61, pp. 4961–4971, Dec 2013.
[11] Q. Shi, M. Razaviyayn, Z. Luo, and C. He, “An iteratively weighted MMSE approach to distributed sum-utility maximization for a MIMO interfering broadcast channel,” IEEE Trans. Signal Process., vol. 59, pp. 4331–4340, Sept 2011.
[12] M. Sadek, A. Tarighat, and A. H. Sayed, “A leakage-based precoding scheme for downlink multi-user MIMO channels,” IEEE Transactions on Wireless Communications, vol. 6, pp. 1711–1721, May 2007.
[13] P. Patcharamaneepakorn, S. Armour, and A. Doufexi, “Coordinated beamforming schemes based on modified signal-to-leakage-plus-noise ratio precoding designs,” IET Communications, vol. 9, no. 4, pp. 558–567, 2015.
[14] L. Dong, G. Wu, H. Feng, and S. Li, “Leakage-based power allocation for relaxed SLNR beamforming in multi-cell MU-MIMO systems,” in in Proceedings of IEEE International Conference on Communication Systems, pp. 512–516, Nov 2014. [15] L. Sanguinetti, R. Couillet, and M. Debbah, “Base station cooperation for power minimization in the downlink: Large system analysis,” in Proceedings of IEEE Global Communications Conference, pp. 1–6, Dec. 2015.
[16] R. Bhagavatula and R.W. Heath, “Adaptive limited feedback for sum-rate maximizing beamforming in cooperative multicell systems,” IEEE Trans. Signal Process., vol. 59, pp. 800–811, Feb 2011.
[17] Y. Huang, G. Zheng, M. Bengtsson, K. Wong, L. Yang, and B. Ottersten, “Distributed multicell beamforming with limited intercell coordination,” IEEE Trans. Signal Process., vol. 59, pp. 728–738, Feb 2011.
[18] S. Lakshminarayana, M. Assaad, and M. Debbah, “Coordinated multicell beamforming for massive MIMO: A random matrix approach,” IEEE Trans. Inf. Theory, vol. 61, pp. 3387–3412, Jun 2015.
[19] C. Shen, T. Chang, K. Wang, Z. Qiu, and C. Chi, “Distributed robust multicell coordinated beamforming with imperfect CSI: An ADMM approach,” IEEE Transactions on Signal Processing, vol. 60, no. 6, pp. 2988–3003, 2012.
[20] H. Sun, X. Chen, Q. Shi, M. Hong, X. Fu, and N. D. Sidiropoulos, “Learning to optimize: Training deep neural networks for interference management,” IEEE Trans. Signal Process., vol. 66, pp. 5438–5453, Oct 2018.
[21] J. Guo, C. Wen, S. Jin, and G. Y. Li, “Convolutional neural network-based multiple-rate compressive sensing for massive mimo csi feedback: Design, simulation, and analysis,” IEEE Transactions on Wireless Communications, vol. 19, no. 4, pp. 2827–2840, 2020.
[22] Y. Liao, H. Yao, Y. Hua, and C. Li, “CSI feedback based on deep learning for massive MIMO systems,” IEEE Access, vol. 7, pp. 86810–86820, 2019. [23] Q. Yang, M. B. Mashhadi, and D. G¨und¨uz, “Deep convolutional compression for massive MIMO CSI feedback,” in 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1–6, 2019.
[24] A. M. Elbir, “A deep learning framework for hybrid beamforming without instantaneous CSI feedback,” IEEE Transactions on Vehicular Technology, vol. 69, no. 10, pp. 11743–11755, 2020.
[25] H. Ye, F. Gao, J. Qian, H.Wang, and G. Y. Li, “Deep learning-based denoise network for CSI feedback in FDD massive MIMO systems,” IEEE Communications Letters, vol. 24, no. 8, pp. 1742–1746, 2020.
[26] W. Xia, G. Zheng, Y. Zhu, J. Zhang, J. Wang, and A. P. Petropulu, “A deep learning framework for optimization of MISO downlink beamforming,” IEEE Transactions on Communications, vol. 68, no. 3, pp. 1866–1880, 2020.
[27] S. Moon, H. Kim, and I. Hwang, “Deep learning-based channel estimation and tracking for millimeter-wave vehicular communications,” Journal of Communications and Networks, vol. 22, no. 3, pp. 177–184, 2020.
[28] F. Liang, C. Shen, W. Yu, and F. Wu, “Towards optimal power control via ensembling deep neural networks,” IEEE Transactions on Communications, vol. 68, no. 3, pp. 1760–1776, 2020.
[29] H. Huang, Y. Peng, J. Yang, W. Xia, and G. Gui, “Fast beamforming design via deep learning,” IEEE Transactions on Vehicular Technology, vol. 69, no. 1, pp. 1065–1069, 2020.
[30] F. B. Mismar, B. L. Evans, and A. Alkhateeb, “Deep reinforcement learning for 5G networks: Joint beamforming, power control, and interference coordination,” IEEE Transactions onCommunications, vol. 68, no. 3, pp. 1581–1592, 2020. [31] H. Huang, W. Xia, J. Xiong, J. Yang, G. Zheng, and X. Zhu, “Unsupervised learning-based fast beamforming design for downlink MIMO,” IEEE Access, vol. 7, pp. 7599–7605, 2019.
[32] I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, “Binarized neural networks,” in Advances in neural information processing systems, 2016.