[1]何春龙,周月华,钱恭斌,等.基于机器学习的集群双向DAS能效技术[J].深圳大学学报理工版,2020,37(6):567-575.[doi:10.3724/SP.J.1249.2020.06567]
 HE Chunlong,ZHOU Yuehua,QIAN Gongbin,et al.Machine learning generated clusters-based energy efficient power allocation for bidirectional DAS[J].Journal of Shenzhen University Science and Engineering,2020,37(6):567-575.[doi:10.3724/SP.J.1249.2020.06567]
点击复制

基于机器学习的集群双向DAS能效技术()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第37卷
期数:
2020年第6期
页码:
567-575
栏目:
电子与信息科学
出版日期:
2020-11-09

文章信息/Info

Title:
Machine learning generated clusters-based energy efficient power allocation for bidirectional DAS
文章编号:
202006003
作者:
何春龙周月华钱恭斌丁雪
深圳大学电子与信息工程学院,广东深圳 518060
Author(s):
HE Chunlong ZHOU Yuehua QIAN Gongbin and DING Xue
College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China
关键词:
无线通信技术机器学习频谱效率能量效率k均值高斯混合模型分布式天线系统
Keywords:
wireless communication technology machine learning spectral efficiency energy efficiency k-means Gaussian mixture model distributed antenna system
分类号:
TN92
DOI:
10.3724/SP.J.1249.2020.06567
文献标志码:
A
摘要:
双向分布式天线系统(bidirectional distributed antenna system, BDAS)是构建未来绿色通信的重要技术之一,但其在提高能效和降低能耗的同时,也给小区中的远程接入单元(remote access unit, RAU)与用户带来严重干扰.本研究提出在BDAS中构建基于机器学习的集群通信模式.首先,通过对BDAS中的用户进行聚类分析,将每个用户都归属一个集群;然后,根据集群中心与每个RAU的距离为集群中的用户选择通信所需的唯一服务基站;最后,在加入机器学习的集群BDAS中,对以最大化系统能量效率(energy efficiency, EE)和频谱效率(spectral efficiency, SE)为优化目标的功率分配方案进行求解.仿真结果表明,相比单一的BDAS,基于机器学习的集群双向分布式天线系统(BDAS based on machine learning generated clusters, BDAS-MLGC)能更有效地提高系统的SE和EE.
Abstract:
The bidirectional distributed antenna system (BDAS) is one of the important technologies for building the green communication system in the future. However, BDAS also causes serious interference to the remote access units (RAU) and users while bringing the improvement of energy efficiency and reduction of energy consumption. In this paper, we propose a communication mode based on machine learning generated clusters. Firstly, each user belongs to a cluster through clustering analysis of users in BDAS. And then, according to the distance between the cluster center and each RAU, we chose the only serving base station for users in the cluster, and finally we solve out the power allocation scheme with the optimization objectives of maximizing the system energy efficiency (EE) and spectral efficiency (SE). Simulation results show that the BDAS-MLGC, which is called the bidirectional distributed antenna system based on machine learning generated clusters, can improve SE and EE of the system more effectively than single BDAS.

参考文献/References:

[1] WEI Zhongxiang, SUN Sumei, ZHU Xu, et al. Energy-efficient hybrid duplexing strategy for bidirectional distributed antenna systems[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6): 5096-5110.
[2] HE Anqi, WANG Lifeng, CHEN Yue, et al. Spectral and energy efficiency of uplink D2D underlaid massive MIMO cellular networks[J]. IEEE Transactions on Communications, 2017, 65(9): 3780-3793.
[3] MARKO H. The bidirectional communication theory: a generalization of information theory[J]. IEEE Transactions on Communications, 1973, 21(12): 1345-1351.
[4] XIN Yuanxue, WANG Dongming, ZHANG Rongqing, et al. Spectral efficiency of bidirectional dynamic networks with massive MIMO[C]// IEEE Global Communications Conference. Washington D C: IEEE, 2016. doi:10.1109/GLOCOM.2016.7842288
[5] XIN Yuanxue, YANG Liuqing, WANG Dongming, et al. Bidirectional dynamic networks with massive MIMO: performance analysis[J]. IET Communications, 2017, 11(4): 468-476.
[6] XIN Yuanxue, ZHANG Rongqing, WANG Dongming, et al. Antenna clustering for bidirectional dynamic network with large-scale distributed antenna systems[J]. IEEE Access, 2017, 5: 4037-4047.
[7] 尤肖虎,张川,谈晓思,等.基于AI的5G技术——研究方向与范例[J].中国科学:信息科学,2018,48(12):1589-1602.
YOU Xiaohu, ZHANG Chuan, TAN Xiaosi, et al. AI for 5G: research directions and paradigms[J]. Scientia Sinica Informations, 2018, 48(12): 1589-1602.(in Chinese)
[8] XIA Ming, OWADA Y, INOUE M, et al. Optical and wireless hybrid access networks: design and optimization[J]. Journal of Optical Communications and Networking, 2012, 4(10): 749-759.
[9] LIANG Hanwen, CHUNG W H, KUO S Y. Coding-aided k-means clustering blind transceiver for space shift keying MIMO systems[J]. IEEE Transactions on Wireless Communications, 2016, 15(1): 103-115.
[10] ALBAKAY N, HEMPEL M, ALAHMAD M, et al. Novel frequency offset estimation scheme for reliable wireless communication using modified k-means clustering[C]// The 15th International Wireless Communications & Mobile Computing Conference (IWCMC). Tangier, Morocco: IEEE, 2019: 826-829.
[11] ANDREAS W, MICHAEL K, JI Lianghai., et al. Physical layer authentication for mission critical machine type communication using Gaussian mixture model based clustering[C]// Proceedings of IEEE 85th Vehicular Technology Conference (VTC-Spring). Sydney, Australia: IEEE, 2017: 1-5.
[12] LI Haihan, LI Yunzhou, ZHOU Shidong, et al. Wireless channel feature extraction via GMM and CNN in the tomographic channel model[J]. Journal of Communications & Information Networks, 2017, 2(1): 41-51.
[13] YOU Xiaohu, WANG Dongming, SHENG Bin, et al. Cooperative distributed antenna systems for mobile communications[J]. IEEE Wireless Communications, 2010, 17(3): 35-43.
[14] HE Chunlong, SHENG Bin, ZHU Pengcheng, et al. Energy- and spectral-efficiency tradeoff for distributed antenna systems with proportional fairness[J]. IEEE Journal on Selected Areas in Communications, 2013, 13(5): 894-902.
[15] POLLARD D. Quantization and the method of k-means[J]. IEEE Transaction Information Theory, 2003, 28(2): 199-205.
[16] BRADLEY P S, FAYYAD U M. Defining initial points for k-means clustering[C]// Proceedings of the 15th International Conference on Machine Learning. San Francisco, USA: Morgan Kaufmann Publishers Inc, 1998: 91-99.
[17] BISHOP C M. Pattern recognition and machine learning[M]. New York, USA: Springer-Verlag, 2016.
[18] DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society: Series B (Methodological), 1977, 39(1): 1-22.
[19] NG D W K, LO E S, SCHOBER R. Energy-efficient resource allocation in OFDMA systems with large numbers of base station antennas[J]. IEEE Transaction Wireless Communication, 2012, 11(9): 3292-3304.
[20] WU Jiang, LIU Jianwei, LI Wanlin, et al. Low-complexity power allocation for energy efficiency maximization in DAS[J]. IEEE Communications Letters, 2015, 19(6): 925-928.
[21] AN L T H, TAO P D. The DC (difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems[J]. Annals of Operations Research, 2005, 133(4): 23-46.
[22] LANCKRIET R G, SRIPERUMBUDUR B K. On the convergence of the concave-convex procedure[C]// Proceedings in of the 22nd International Conference on Neural Information Processing Systems. New York, USA: Curran Associates Inc, 2009: 1759-1767.
[23] LI Xinquan, HE Chunlong, ZHANG Jihong. Spectral efficiency and energy efficiency of bidirectional distributed antenna systems with user centric virtual cells[J]. IEEE Access, 2018, 6: 49886-49895.
[24] DINKELBACH W. On nonlinear fractional programming[J]. Management Sciences, 1967, 13(7): 492-498.
[25] YOU Xiaohu, WANG Dongming, ZHU Pengcheng, et al. Cell edge performance of cellular mobile systems[J]. IEEE Journal on Selected Areas in Communications, 2011, 29(6): 1200-1213.
[26] HE Chunlong, LI G Y, ZHENG Fuchun, et al. Power allocation criteria for distributed antenna systems[J]. IEEE Transactions on Vehicular Technology, 2015, 64(11): 5083-5090.
[27] HE Xiaofei, CAI Deng, SHAO Yuanlong, et al. Laplacian regularized Gaussian mixture model for data clustering[J]. IEEE Transactions on Knowledge and Data Engineering, 2011, 23(9): 1406-1418.
[28] OLIVA G, SETOLA R, HADJICOSTIS C N. Distributed k-means algorithm[EB/OL]. (2013-12-15)[2014-11-10]. http: //arxiv.org/abs/1312.4176.

相似文献/References:

[1]林春漪,尹俊勋,高 学,等.基于统计学习的多层医学图像语义建模方法[J].深圳大学学报理工版,2007,24(2):138.
 LIN Chun-yi,YIN Jun-xun,GAO Xue,et al.A multi-level medical image semantic modeling approach based on statistical learning[J].Journal of Shenzhen University Science and Engineering,2007,24(6):138.
[2]潘长城,徐晨,李国.解全局优化问题的差分进化策略[J].深圳大学学报理工版,2008,25(2):211.
 PAN Chang-cheng,XU Chen,and LI Guo.Differential evolutionary strategies for global optimization[J].Journal of Shenzhen University Science and Engineering,2008,25(6):211.
[3]罗雪晖,李霞,张基宏.支持向量机及其应用研究[J].深圳大学学报理工版,2003,20(3):40.
 LUO Xue-hui,LI Xia and ZHANG Ji-hong.Introduction to Support Vector Machine and Its Applications[J].Journal of Shenzhen University Science and Engineering,2003,20(6):40.
[4]杨舰,谢广智.电梯召唤通信系统的无线化处理与设计[J].深圳大学学报理工版,2016,33(5):517.[doi:10.3724/SP.J.1249.2016.05517]
 Jian and Xie Guangzhi.Wireless processing and design of hall-call communication system of elevatorYang[J].Journal of Shenzhen University Science and Engineering,2016,33(6):517.[doi:10.3724/SP.J.1249.2016.05517]
[5]李婵,王俊杰,邬国锋,等.基于叶片光谱特征的农业区域植物分类[J].深圳大学学报理工版,2018,35(3):307.[doi:10.3724/SP.J.1249.2018.03307]
 LI Chan,WANG Junjie,WU Guofeng,et al.Classification of agricultural plants based on leaf spectral features[J].Journal of Shenzhen University Science and Engineering,2018,35(6):307.[doi:10.3724/SP.J.1249.2018.03307]
[6]张峰,钱辉,董春茹,等.随机状态下基于期望经验回放的Q学习算法[J].深圳大学学报理工版,2020,37(2):202.[doi:10.3724/SP.J.1249.2020.02202]
 ZHANG Feng,QIAN Hui,DONG Chunru,et al.An expected experience replay based Q-learning algorithm with random state transition[J].Journal of Shenzhen University Science and Engineering,2020,37(6):202.[doi:10.3724/SP.J.1249.2020.02202]
[7]岳琴,魏巍,冯凯,等.自适应稀疏表示引导的无监督降维[J].深圳大学学报理工版,2020,37(4):425.[doi:10.3724/SP.J.1249.2020.04425]
 YUE Qin,WEI Wei,FENG Kai,et al.Adaptive sparse representation guided unsupervised dimensionality reduction[J].Journal of Shenzhen University Science and Engineering,2020,37(6):425.[doi:10.3724/SP.J.1249.2020.04425]
[8]赵朋亚,傅湘玲,仵伟强,等.基于标签传播的协同分类欺诈检测方法[J].深圳大学学报理工版,2020,37(5):482.[doi:10.3724/SP.J.1249.2020.05482]
 ZHAO Pengya,FU Xiangling,et al.Collective classification method based on label propagation for fraud detection[J].Journal of Shenzhen University Science and Engineering,2020,37(6):482.[doi:10.3724/SP.J.1249.2020.05482]

备注/Memo

备注/Memo:
Received:2020-05-07;Accepted:2020-08-07
Foundation:National Natural Science Foundation of China (61601300); Shenzhen Overseas High-level Talents Innovation and Entrepreneurship Project (KQJSCX20180328093835762); Shenzhen Basic Research Project (JCYJ20190808122409660)
Corresponding author:Associate professor QIAN Gongbin. E-mail: qiangb@szu.edu.cn
Citation:HE Chunlong, ZHOU Yuehua, QIAN Gongbin, et al. Machine learning generated clusters-based energy efficient power allocation for bidirectional DAS[J]. Journal of Shenzhen University Science and Engineering, 2020, 37(6): 567-575.(in Chinese)
基金项目:国家自然科学基金资助项目(61601300);深圳市海外高层次人才创新创业专项资助项目 (KQJSCX20180328 093835762);深圳市基础研究计划资助项目(JCYJ2019 0808122409660)
作者简介:何春龙(1984—),深圳大学副教授、博士.研究方向:分布式天线能效、机器学习及信道估计等.E-mail:hclong@szu.edu.cn
引文:何春龙,周月华,钱恭斌,等.基于机器学习的集群双向DAS能效技术[J]. 深圳大学学报理工版,2020,37(6):567-575.
更新日期/Last Update: 2020-11-26