无蜂窝大规模MIMO网络下基于联邦学习的用户接入策略及能耗优化

doi:10.11959/j.issn.1000-436x.2023188

通信学报 ›› 2023, Vol. 44 ›› Issue (10): 112-123.doi: 10.11959/j.issn.1000-436x.2023188

• 学术论文 • 上一篇

无蜂窝大规模MIMO网络下基于联邦学习的用户接入策略及能耗优化

姚媛媛¹^,², 刘忆秋¹^,², 黄赛³, 潘春雨¹^,², 李学华¹^,², 袁昕⁴

¹ 北京信息科技大学信息与通信系统信息产业部重点实验室，北京 100101
² 北京信息科技大学现代测控技术教育部重点实验室，北京 100101
³ 北京邮电大学泛网无线通信教育部重点实验室，北京 100876
⁴ 悉尼科技大学电气与数据工程学院，悉尼 NSW 2007

修回日期:2023-08-07 出版日期:2023-10-01 发布日期:2023-10-01
作者简介:姚媛媛（1988− ），女，河南驻马店人，博士，北京信息科技大学副教授、硕士生导师，主要研究方向为无蜂窝大规模MIMO、智能反射面辅助通信、无人机通信等
刘忆秋（1998− ），女，河南安阳人，北京信息科技大学硕士生，主要研究方向为无蜂窝大规模MIMO、边缘计算、联邦学习等
黄赛（1989− ），男，河北保定人，博士，北京邮电大学副教授、博士生导师，主要研究方向为基于机器学习的智能信号处理、通用无线信号快速检测与深度识别等
潘春雨（1989− ），女，河南南阳人，博士，北京信息科技大学副教授、硕士生导师，主要研究方向为无蜂窝网络、无人机通信，资源管理、边缘计算、人工智能等
李学华（1977− ），女，湖北荆州人，博士，北京信息科技大学教授、硕士生导师，主要研究方向为无线通信物理层关键技术等
袁昕（1990− ），女，江苏扬州人，博士，澳洲联邦科学与工业研究组织研究科学家，悉尼科技大学访问学者，主要研究方向为机器学习和优化及其在无人机网络和智能系统中的应用
基金资助:
国家自然科学基金资助项目(62301059);北京市属高等学校优秀青年人才培育计划基金资助项目(BPHR202203228);泛网无线通信教育部重点实验室（BUPT）基金资助项目(KFKT-2020105);北京市自然科学基金-海淀联合基金资助项目(L212026);北京市自然科学基金-海淀联合基金资助项目(L222004)

Federated learning-based user access strategy and energy consumption optimization in cell-free massive MIMO network

Yuanyuan YAO¹^,², Yiqiu LIU¹^,², Sai HUANG³, Chunyu PAN¹^,², Xuehua LI¹^,², Xin YUAN⁴

¹ Key Laboratory of Information and Communication Systems, Ministry of Information Industry, Beijing Information Science and Technology University, Beijing 100101, China
² Key Laboratory of Modern Measurement ＆Control Technology , Ministry of Education, Beijing Information Science and Technology University Beijing 100101, China
³ Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China
⁴ School of Electrical and Data Engineering, University of Technology Sydney, Sydney NSW 2007, Australia

Revised:2023-08-07 Online:2023-10-01 Published:2023-10-01
Supported by:
The National Natural Science Foundation of China(62301059);The Project of Cultivation for Young Top-Motch Talents of Beijing Municipal Institutions(BPHR202203228);The Key Laboratory of Universal Wireless Communications (BUPT), Ministry of Education(KFKT-2020105);Beijing Natural Science Foundation-Haidian Original Innovation Joint Fund(L212026);Beijing Natural Science Foundation-Haidian Original Innovation Joint Fund(L222004)

摘要/Abstract

摘要：

针对无蜂窝大规模多输入多输出（CF-mMIMO）网络中用户如何选择接入点的问题，提出了一种基于信道排序的较差用户优先接入策略。首先，用户进行信道感知后对其信道质量和稳定性进行评估和排序，用户按照信道状态信息的顺序依次选择合适的接入点；其次，考虑到用户的能耗与数据安全等问题，采用联邦学习框架以增强用户的数据隐私安全，并提出一种基于能耗优化的交替优化变量算法，对多维变量进行优化，使系统总能耗最小化。仿真结果表明，相较于传统的大规模MIMO中用户为中心的接入策略，所提接入策略可使用户平均上行可达速率提升20%，信道较差用户的上行速率可提升2倍；在能耗优化方面，优化后的总能耗可降低50%以上。

关键词: 无蜂窝大规模MIMO, 用户接入, 智能感知, AP选择, 能耗优化

Abstract:

To solve the problem that how users choose access points in cell-free massive multiple-input multiple-output (CF-mMIMO) network, a prioritized access strategy for poorer users based on channel coefficient ranking was proposed.First, users were evaluated and ranked for their channel quality and stability after channel sensing, and suitable access points were selected in sequence according to the order of the channel state information.Second, considering issues such as users' energy consumption and data security, a federal learning framework was used to enhance user's data privacy and security.Meanwhile, an alternating optimization variables algorithm based on energy consumption optimization was proposed to optimize the multi-dimensional variables, for the purpose of minimizing the total energy consumption of the system.Simulation results show that compared with the traditional user-centric in massive MIMO, the proposed access strategy can improve the average uplink reachable rate of users by 20%, and the uplink rate of users with poor channels can be double improved; in terms of energy consumption optimization, the total energy consumption can be reduced by much more than 50% after optimization.

Key words: cell-free massive MIMO, user access, intelligent sensing, AP selection, energy consumption optimization

中图分类号:

TN929.5

姚媛媛, 刘忆秋, 黄赛, 潘春雨, 李学华, 袁昕. 无蜂窝大规模MIMO网络下基于联邦学习的用户接入策略及能耗优化[J]. 通信学报, 2023, 44(10): 112-123.

Yuanyuan YAO, Yiqiu LIU, Sai HUANG, Chunyu PAN, Xuehua LI, Xin YUAN. Federated learning-based user access strategy and energy consumption optimization in cell-free massive MIMO network[J]. Journal on Communications, 2023, 44(10): 112-123.

图/表 11

图1

图2

图3

表1

仿真参数"

参数	数值
路径损耗因子L^[25]/ dB	140.7
带宽W/ MHz	20
路径损耗模型参数d₀/ m	10
路径损耗模型参数d₁/ m	50
载波频率f/ GHz	1.9
计算所需CPU周期数C_k	2×10⁴
芯片有效电容系数φ	10^-28
用户最大发射功率 $p_{k}^{\max}$ /dBm	40
用户本地数据规模d/ (kbit·s^-1)	28.1
全局学习精度θ	10^-3
用户数据规模D_k	500
AIEO算法精度P	10^-2
用户数量UE	10
仿真圆形区域半径R_s/ m	100

表1

图4

图5

图6

图7

图8

图9

图10

参考文献 25

[1]	李文风 . 去蜂窝大规模MIMO系统中导频分配及AP选择技术研究[D]. 北京:北京邮电大学, 2021.
	LI W F . Research on pilot assignment and AP selection technology in cell-free massive MIMO system[D]. Beijing:Beijing University of Posts and Telecommunications, 2021.
[2]	NGO H Q , ASHIKHMIN A , YANG H ,et al. Cell-free massive MIMO versus small cells[J]. IEEE Transactions on Wireless Communications, 2017,16(3): 1834-1850.
[3]	NGO H Q , ASHIKHMIN A , YANG H ,et al. Cell-free massive MIMO:uniformly great service for everyone[C]// Proceedings of IEEE 16th International Workshop on Signal Processing Advances in Wireless Communications. Piscataway:IEEE Press, 2015: 201-205.
[4]	BUZZI S , DANDREA C . User-centric communications versus cell-free massive MIMO for 5G cellular networks[C]// Proceedings of 21th International ITG Workshop on Smart Antennas. Berlin:VDE, 2017: 187-192.
[5]	BUZZI S , DANDREA C . Cell-free massive MIMO:user-centric approach[J]. IEEE Wireless Communications Letters, 2017,6(6): 706-709.
[6]	CHEN S F , ZHANG J Y , BJ?RNSON E , ,et al. Structured massive access for scalable cell-free massive MIMO systems[J]. IEEE Journal on Selected Areas in Communications, 2021,39(4): 1086-1100.
[7]	NGO H Q , TRAN L N , DUONG T Q ,et al. On the total energy efficiency of cell-free massive MIMO[J]. IEEE Transactions on Green Communications and Networking, 2018,2(1): 25-39.
[8]	DAO H T , KIM S . Effective channel gain-based access point selection in cell-free massive MIMO systems[J]. IEEE Access, 2020,8: 108127-108132.
[9]	BISWAS S , VIJAYAKUMAR P . AP selection in cell-free massive MIMO system using machine learning algorithm[C]// Proceedings of 2021 Sixth International Conference on Wireless Communications,Signal Processing and Networking (WiSPNET). Piscataway:IEEE Press, 2021: 158-161.
[10]	MOZAFFARI M , SAAD W , BENNIS M ,et al. Mobile unmanned aerial vehicles (UAVs) for energy-efficient Internet of things communications[J]. IEEE Transactions on Wireless Communications, 2017,16(11): 7574-7589.
[11]	LI T , SAHU A K , TALWALKAR A ,et al. Federated learning:challenges,methods,and future directions[J]. IEEE Signal Processing Magazine, 2020,37(3): 50-60.
[12]	XU J , WANG H Q , CHEN L X . Bandwidth allocation for multiple federated learning services in wireless edge networks[J]. IEEE Transactions on Wireless Communications, 2022,21(4): 2534-2546.
[13]	BEHMANDPOOR P , PATRINOS P , MOONEN M . Federated learning based resource allocation for wireless communication networks[C]// Proceedings of 30th European Signal Processing Conference (EUSIPCO). Piscataway:IEEE Press, 2022: 1656-1660.
[14]	VU T T , NGO D T , TRAN N H ,et al. Cell-free massive MIMO for wireless federated learning[J]. IEEE Transactions on Wireless Communications, 2020,19(10): 6377-6392.
[15]	YANG Z H , CHEN M Z , SAAD W ,et al. Energy efficient federated learning over wireless communication networks[J]. IEEE Transactions on Wireless Communications, 2021,20(3): 1935-1949.
[16]	TANG A , SUN J X , GONG K . Mobile propagation loss with a low base station antenna for NLoS street microcells in urban area[C]// Proceedings of IEEE VTS 53rd Vehicular Technology Conference. Piscataway:IEEE Press, 2002: 333-336.
[17]	WANG Z Y , TAMEH E K , NIX A R . Joint shadowing process in urban peer-to-peer radio channels[J]. IEEE Transactions on Vehicular Technology, 2008,57(1): 52-64.
[18]	WANG S Q , TUOR T , SALONIDIS T ,et al. When edge meets learning:adaptive control for resource-constrained distributed machine learning[C]// Proceedings of IEEE INFOCOM 2018 - IEEE Conference on Computer Communications. Piscataway:IEEE Press, 2018: 63-71.
[19]	WANG S Q , TUOR T , SALONIDIS T ,et al. Adaptive federated learning in resource constrained edge computing systems[J]. IEEE Journal on Selected Areas in Communications, 2019,37(6): 1205-1221.
[20]	AHN S , LEE J , PARK S ,et al. Competitive partial computation offloading for maximizing energy efficiency in mobile cloud computing[J]. IEEE Access, 2017,6: 899-912.
[21]	MAO Y Y , ZHANG J , LETAIEF K B . Dynamic computation offloading for mobile-edge computing with energy harvesting devices[J]. IEEE Journal on Selected Areas in Communications, 2016,34(12): 3590-3605.
[22]	TRAN N H , BAO W , ZOMAYA A ,et al. Federated learning over wireless networks:optimization model design and analysis[C]// Proceedings of IEEE Conference on Computer Communications. Piscataway:IEEE Press, 2019: 1387-1395.
[23]	MA C X , KONE?NY J , JAGGI M ,et al. Distributed optimization with arbitrary local solvers[J]. Optimization Methods and Software, 2017,32(4): 813-848.
[24]	KONE?NY J , QU Z , RICHTáRIK P . Semi-stochastic coordinate descent[J]. Optimization Methods and Software, 2017,32(5): 993-1005.
[25]	ZHANG J Y , CHEN S F , LIN Y ,et al. Cell-free massive MIMO:a new next-generation paradigm[J]. IEEE Access, 2019,7: 99878-99888.

无蜂窝大规模MIMO网络下基于联邦学习的用户接入策略及能耗优化

Federated learning-based user access strategy and energy consumption optimization in cell-free massive MIMO network

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 25

相关文章 4

Metrics

推荐阅读 0

[1]	余雪勇, 邱礼翔, 宋家宁, 朱洪波. 无人机辅助边缘计算中安全通信与能效优化策略[J]. 通信学报, 2023, 44(3): 45-54.
[2]	刘桂岐, 钱志鸿, 李华亮, 孙佳妮, 冯一诺, 王雪. 基于有效AP选择和多分类LDA的室内定位算法[J]. 通信学报, 2021, 42(11): 109-120.
[3]	毛艳艳,程大鹏,冯烟利,窦全胜,李大社. C3S：基于相长干涉的智能传感系统并发传输策略研究[J]. 通信学报, 2019, 40(1): 180-194.
[4]	宋健,张宝杰,孙为,车嵘,王伟. HMIPv6中基于节点特征的快速切换算法研究[J]. 通信学报, 2006, 27(11A): 168-172.