使用深度神經學習於正交分頻多址系統之子載之子載波配置設計波配置設計

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳薇任 Wei-Jen Chen
論文名稱：	使用深度神經學習於正交分頻多址系統之子載之子載波配置設計波配置設計 Subcarrier Allocation for OFDMA Systems by Using Deep Neural Networks
指導教授：	陳永芳 Yung-Fang Chen
口試委員:
學位類別：	碩士 Master
系所名稱：	資訊電機學院 - 通訊工程學系 Department of Communication Engineering
論文出版年：	2019
畢業學年度：	107
語文別：	英文
論文頁數：	46
中文關鍵詞：	正交分頻多址系統、深度學習、深度神經學習、子載波分配
外文關鍵詞：	orthogonal frequency division multiple access, deep learning, deep neural networks, subcarrier allocation
相關次數：	點閱：14 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本論文將深度神經學習(DNN)結合於正交分頻多址(OFDMA)系統的子載波配置中，透過適當的學習來提升分配的效率。在正交分頻多址系統中，假設通道增益為已知的，分給不同數量的人數，比較其所需的傳送功率。論文中提出的方法可以大幅地提升效率和減少運算複雜度，我們將一組通道增益分給使用者視為一個批量去學習，透過一定數量的迭代及重複學習，成本函數會收斂至一穩定的數值，並且在滿足位元錯誤率的限制下最小化與ESA演算法的均方誤差差異。我們同時也比較不同的最佳化演算法的收斂速度，最後透過驗證來設定任何可能的控制參數，使用測試集來評估分配的精確度與效能。本論文提出的方法提供了更高的效率於分配子載波中，效能也與ESA演算法相近。

In this paper, we propose a deep neural networks (DNN) structure to allocate subcarrier for orthogonal frequency-division multiple access (OFDMA). Assuming that the channel gains of all subcarriers are known, and allocate to different number of users respectively. The proposed method can be dramatically increased the efficiency. We trying to minimize the mean squared error (MSE) between ESA algorithm while satisfying the bit error rate constraint. We suggest a deep learning architecture in which each group of allocation as a batch, after an appropriate number of iterations and epochs, the loss will tend to converge to a constant value. We also discuss different optimizer to compare their convergence rate. The proposed scheme offers better efficiency of allocating subcarrier and the performance is close to ESA algorithm.

論文摘要    IV
Abstract    V
致謝    VI
List of Figure    IX
List of Tables    X
Chapter 1. Introduction    1
1.1 Deep Learning    1
1.2 Organization    4
1.3 Abbreviations    5
1.4 Notation    5
Chapter 2. Deep Neural Networks and System Model    7
2.1 Deep Neural Networks (DNN)    7
2.2 DNN Structure    8
2.3 Training data    9
2.4 Subcarrier, bit, power allocation strategy    11
Chapter 3. Proposed Scheme    15
3.1 Training Process    15
3.2 Weight and Bias    17
3.3 Dropout    17
3.4 Optimizer    18
3.4.1 Stochastic Gradient Decent    18
3.4.2    Adam Optimizer    20
3.5 Epoch, batch size, iterations    21
3.6 Bit allocation    23
Chapter 4. Simulation Result    25
4.1 Result    25
4.2 Computer equipment:    30
4.3 Algorithm    30
Chapter 5. Conclusion and Future Work    33
Reference    34


                                

A. L. Samuel, "Some Studies in Machine Learning Using the Game of Checkers," IBM Journal of Research and Develpoment, 3(3), pp.211-229, 1959.
[2] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, "Caffe: Convolutional Architecture for Fast Feature Embedding," arXiv preprint arXiv:1408.5093, 2014.
[3] T. Chen, M. Li, Y. Li, M. Lin, N, Wang, T. Xiao, B. Wu, C. Zhang, and Z. Zhang, "MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems," arXiv preprint arXiv:1512.01274, 2015.
[4] M. Abadi et al., "TensorFlow: Large-scale machine learning on heterogeneous systems," 2015, software available from tensorflow.org.[Online]. Available: http://tensorflow.org/.
[5] R. Al-Rfou, G. Alain, A. Almahairi et al., "Theano: A Python framework for fast computation of mathematical expressions," arXiv preprint arXiv:1605.02688, 2016.
[6] R. Collobert, K. Kavukcuoglu, and C. Farabet, "Torch7: A matlab-like environment for machine learning," in Biglearn, NIPS Workshop, 2011.
[7] S. Dörner, et al., "Deep Learning Based Communication Over the Air," IEEE Journal of Selected Topics in Signal Processing, 2017
[8] T. J. O'shea and J. Hoydis, "An Introduction to Deep Learning for the Physical Layer," IEEE Transactions on Cognitive Communications and Networking, 2017.
[9] T. J. O'Shea, T. Erpek, and T.C. Clancy, "Deep Learning-Based MIMO Communications," arXiv preprint arXiv:1707.07980, 2017.
[10] Z. Xu, Y. Wang, J. Tang, J. Wang, and M. C. Gursoy, "A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs," in Proc. IEEE Int. Conf. Communications (ICC), May 2017, pp. 1-6.
[11] J. Kim, J. Park, J. Noh, S. Cho, "Completely Distributed Power Allocation using Deep Neural Network for Device to Device communication Underlaying LTE," arXiv preprint arXiv:1802.02736v2, 2018.
[12] Y. F. Chen, and J. W. Chen, "A Fast Subcarrier, Bit, and Power Allocation Algorithm for Multiuser OFDM-Based Systems," IEEE Transactions on Vehicular Technology, Vol. 57, NO.2, March, 2018.
[13] Nair, V. and G.E. Hinton, Rectified linear units improve restricted boltzmann machines, in Proceedings of the 27th International Conference on International Conference on Machine Learning. 2010, Omnipress: Haifa, Israel. p. 807-814.
[14] N. Srivastava, et al., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting," Journal of Machine Learning Research,15(1), 1929-1958, 2014.
[15] J. M Torrance, and L. Hanzo, "Optimisation of switching levels for adaptive modulation in slow Rayleigh fading," Electronics Lett, vol. 32, no. 13, p.p. 1167-1168, 1996.

簡易檢索 / 詳目顯示

相關論文