MIMO-NOMA系统中基于深度学习CCDNN框架的传输速率提高和能量效率优化算法

doi:10.13229/j.cnki.jdxbgxb.20240719

摘要/Abstract

摘要：

多输入多输出非正交多址接入技术（MIMO-NOMA）将NOMA理念融入MIMO系统，能有效提高系统的能量效率和吞吐量，但是MIMO-NOMA系统复杂的空间结构和快速变化的空间信道会导致系统吞吐量下降，进而限制其广泛应用。为了解决这一问题，提出了一种基于深度学习的MIMO-NOMA系统框架，该系统采用一种适用于MIMO-NOMA的高效深度学习通信卷积方法（CCDNN）。该方法包括多个卷积层和隐藏层，能够通过特定算法解决功率分配问题，从而提高MIMO-NOMA系统的传输速率和能量效率。最后通过数值仿真进行验证，仿真结果表明，本文提出的CCDNN框架相较于传统方法具有更优的性能，为提高MIMO-NOMA功率分配性能提供了可行方案，并为该领域的进一步研究奠定了一定的理论基础。

关键词: MIMO-NOMA系统, 深度学习, 能效, 功率分配

Abstract:

Multiple-input-multiple-output non-orthogonal multiple access（MIMO-NOMA） technique involves the NOMA idea into MIMO systems， which can effectively improve the system energy efficiency and throughput. Nevertheless， complex spatial structures and rapidly varying spatial channels of the MIMO-NOMA system decrease the system's throughput and block its application. To address this issue， this paper proposes a deep-learning-based framework for MIMO-NOMA systems that employs an efficient Convolutional Deep Neural Network（CCDNN） tailored to MIMO-NOMA communications. The method comprises multiple convolutional and hidden layers and is able to solve the power-allocation problem through a dedicated algorithm， thereby improving both the transmission rate and energy efficiency of the MIMO-NOMA system. Numerical simulations are conducted for validation， and the results demonstrate that the proposed CCDNN framework outperforms conventional approaches， offering a viable solution for enhancing MIMO-NOMA power-allocation performance and laying a theoretical foundation for future research in this area.

Key words: MIMO-NOMA system, deep learning, energy efficiency, power allocation

中图分类号:

TG115.28

王金鹏,窦顺瑶,王珏,赵昕. MIMO-NOMA系统中基于深度学习CCDNN框架的传输速率提高和能量效率优化算法[J]. 吉林大学学报(工学版), 2026, 56(3): 830-842.

Jin-peng WANG,Shun-yao DOU,Jue WANG,Xin ZHAO. Optimization algorithm for transmission rate improvement and energy efficiency in MIMO-NOMA system based on a deep learning CCDNN framework[J]. Journal of Jilin University(Engineering and Technology Edition), 2026, 56(3): 830-842.

图/表 13

图1

图2

表1

MIMO-NOMA系统参数设置"

发射机	空间信息	the angles> $- π ~ + π$
	射频（RF）链路的功耗	$P R F = 300 ? m W$
	误码率阈值	$σ = 10 - 7$
	基带功耗	$P B B = 200 ? m W$
	基站BS 覆盖面积	a 500 m circle area
	移相器的功耗	$P S = 5 ? m W$
	像素距离Pixel Distance	d=λ/2
	信噪比SNR	10 dB
	莱斯Rician信道因子	k=8 dB
信道衰落类型	高斯白噪声AWGN信道
	瑞利Rayleigh信道
	莱斯Rician信道
	纳科拉米Nakagami信道（m=3）

表1

表2

CCDNN网络框架参数选取"

训练序列长度	L=16 bits， L=8 bits
序列批处理尺寸	1 000 batch sizes， 500 batch sizes
学习速率	0.1、0.02、0.01、0.001
每簇用户数	K=4
用户总数	$M = 128$
初始信噪比 SNR	25 dB
缩放参数 $ζ$ 和 $ρ$	学习训练动态调整

表2

表3

实验中的变量或参数说明"

	变量或参数名称	含义
仿真图3	L=16 bits，L=8 bits	序列训练长度
仿真图3	Sum data rate/ （bit·Hz^-1·s^-1）	系统速率总和/ （bit·Hz^-1·s^-1）
仿真图4	Learning rate	网络学习速率分别为0.1、0.01、0.02及0.001
仿真图4	SNR/dB	信噪比/dB
仿真图5	Data rate per user/ （bit·Hz^-1·s^-1）	每个用户的速率/ （bit·Hz^-1·s^-1）
	Retraining time duration T/s	再训练时间/s
	k=12 dB， $?$ =3.8	分解因子，超参数
仿真图6	Spectrum efficiency	系统频谱效率
仿真图7	Energy efficiency/ （bps·Hz^-1·W^-1）	系统能效/ （bps·Hz^-1·W^-1）
仿真图7	Data Rate/bps	系统速率/bps
仿真数据表4~6	L²	二维范数正则化项
	DNN	深度学习网络
	MAC/Million	乘法累加计数/百万次

表3

图3

图4

图5

图6

图7

表4

表5

表6

参考文献 26

[1]	Saad W, Bennis M, Chen M Z. A vision of 6G wireless systems: applications, trends, technologies, and open research problems[J]. IEEE Netw, 2020, 34(3): 134-142.
[2]	Zhang H Z, Zhou T, Xu T H, et al. Remote interference discrimination testbed employing AI ensemble algorithms for 6G TDD networks[J]. Sensors, 2023, 23(4): No.2264.
[3]	Akyildiz I F, Kak A, Nie S T. 6G and beyond: the future of wireless communications systems[J]. IEEE Access, 2020, 8: 133995-134030.
[4]	Zhu L P, Xiao Z Y, Xia X G, et al. Millimeter-wave communications with non-orthogonal multiple access for B5G/6G[J]. IEEE Access, 2019, 7: 116123-116132.
[5]	Jiao R C, Dai L L.On the max-min fairness of beam space MIMO-NOMA[J]. IEEE Transactions on Signal Processing, 2020, 68: 4919-4932.
[6]	Huang H J, Guo S, Gui G, et al. Deep learning for physical-layer 5G wireless techniques: opportunities, challenges and solutions[J]. IEEE Wireless Commun-ications, 2020, 27(1): 214-222.
[7]	Kaur J, Singh M L.User assisted cooperative relaying in beam space massive MIMO NOMA based systems for millimeter wave communications[J]. China Communications, 2019, 16(6): 103-113.
[8]	He H T, Wen C K, Jin S, et al. Deep learning-based channel estimation for beamspace mmwave massive MIMO systems[J]. IEEE Wireless Communication letters, 2018, 7(5): 852-855.
[9]	Wu J Y, Xu T H, Zhou T, et al. Feature-based spectrum sensing of NOMA system for cognitive IoT networks[J]. IEEE Internet of Things Journal, 2023, 10(1): 801-814.
[10]	Wang J P, Cao F, He X Y, et al. Multi carrier system joint receiving method based on MAI and ICI[J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 41(6):1793-1797.
[11]	廖勇, 杨植景, 李雪. 人工智能在 6G 空口物理层的潜在应用研究进展[J]. 北京邮电大学学报,2022,45(6):21-30.
	Liao Yong, Yang Zhi-jing, Li Xue. Research progress of potential applications of AI in 6G air interface physical layer[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(6): 21-30.
[12]	Tweneboah-Koduah S, Affum E A, Agyekum K A P, et al. Performance of cooperative relay NOMA with large antenna transmitters[J]. Electronics, 2022, 11(21): No.3482.
[13]	Alraddady F, Ahmed I, Habtemicail F. Robust hybrid beam-forming for non-orthogonal multiple access in massive MIMO downlink[J]. Electronics, 2022, 11(1): No.75.
[14]	Tang S Y, Ma Z, Xiao M, et al. Hybrid transceiver design for beamspace MIMO-NOMA in code-domain for mmWave communication using lens antenna array[J]. IEEE Journal on Selected Areas in Communications, 2020, 38(9): 2118-2127.
[15]	胡相格, 吴广富, 李涛,等. 基于QoE的 MIMO-NOMA系统功率分配方案[J].北京邮电大学学报,2021, 44(4):62-67.
	Hu Xiang-ge, Wu Guang-fu, Li Tao, et al. Power allocation scheme for MIMO-NOMA system based on QoE[J]. Journal of Beijing Unirersity of Posts and Telecommunications, 2021, 44(4): 62-67.
[16]	Wang J P, Zou N Y, Zhang Y C, et al. Study on downlink performance of multiple access algorithm based on antenna diversity[J]. ICIC Express Letters, 2015, 9(4): 1221-1225.
[17]	Alimo D, Saito M. Beam selection for mm-wave massive MIMO systems using ACO & combined digital precoding under hybrid transceiver architecture[J]. IEICE Communications Express, 2020, 9(6): 170-175.
[18]	Qian L P, Wu Y, Yu N N, et al. Learning driven NOMA assisted vehicular edge computing via underlay spectrum sharing[J]. IEEE Transactions on Vehicular Techndogy, 2021, 70(1): 977-992.
[19]	Lu Y X, Cheng P, Chen Z, et al. Deep autoencoder learning for relay-assisted cooperative communication systems[J]. IEEE Transactions on Communications, 2020, 68(9): 5471-5488.
[20]	Ye N, Li X M, Yu H X, et al. Deep NOMA: A unified framework for NOMA using deep multi-task learning[J]. IEEE Transactions on Wireless Communications, 2020, 19(4): 2208-2225.
[21]	Saad M, Bennis M, Chen M. A vision of 6G wireless systems: applications, trends, technologies, and open research problems[J]. IEEE Network, 2020, 34(3): 134-142.
[22]	Lu Y X, Cheng P, Chen Z, et al. Deep multi-task learning for cooperative NOMA: system design and principles[J]. IEEE Journal on Selected Areas in Communications, 2021, 39(1): 61-78.
[23]	Sabuj S R, Asiedu D K P, Lee K J, et al. Delay optimization in mobile edge computing: Cognitive UAV-assisted eMBB and mMTC services[J]. IEEE Transactions on Cognitive Communications and Networking, 2022, 8(2): 1019-1033.
[24]	Corgnati L, Berta M, Kokkini Z. Assessment of OMA gap-filling performances for multiple and single coastal HF radar systems: validation with drifter data in the ligurian sea[J]. Remote Sensing, 2024, 16(13): 2458-2471.
[25]	Wang X, Wang H T, Dong Z L. A NOMA-VLC power allocation scheme for multi-user based on sparrow search algorithm[J]. Optoelectronics Letters, 2023, 7: 1327-1336.
[26]	Tan Y Z, Chen B. Joint channel estimation and power allocation for the CRS-NOMA[J]. Chinese Journal of Electronics, 2020, 29(1): 177-182.

相关文章 15

[1]	蔡晓东,龙顺宏,梁焜峻. 基于增强对象学习和注意力网络的视频描述方法[J]. 吉林大学学报(工学版), 2026, 56(2): 516-522.
[2]	岳丹,王崇帅,杨亚廷,聂海涛,揣雅惠. 一种简单自适应光学系统高分辨计算成像技术[J]. 吉林大学学报(工学版), 2026, 56(2): 543-554.
[3]	姚宗伟,陈辰,高振云,靳鸿鹏,荣浩,李学飞,黄虹溥,毕秋实. 基于合成图像数据集的挖掘机关键点识别[J]. 吉林大学学报(工学版), 2026, 56(1): 76-85.
[4]	王琳虹,刘宇阳,刘子昱,鹿应佳,张宇恒,黄桂树. 基于YOLOv5的轻量化桥梁缺陷识别[J]. 吉林大学学报(工学版), 2025, 55(9): 2958-2968.
[5]	廉敬,张继保,刘冀钊,张家骏,董子龙. 基于文本引导的人脸图像修复[J]. 吉林大学学报(工学版), 2025, 55(8): 2732-2740.
[6]	刘元宁,王星喆,黄子彧,张家晨,刘震. 基于多模态数据融合的胃癌患者生存预测模型[J]. 吉林大学学报(工学版), 2025, 55(8): 2693-2702.
[7]	袁靖舒,李武,赵兴雨,袁满. 基于BERTGAT-Contrastive的语义匹配模型[J]. 吉林大学学报(工学版), 2025, 55(7): 2383-2392.
[8]	徐慧智,郝东升,徐小婷,蒋时森. 基于深度学习的高速公路小目标检测算法[J]. 吉林大学学报(工学版), 2025, 55(6): 2003-2014.
[9]	张汝波,常世淇,张天一. 基于深度学习的图像信息隐藏方法综述[J]. 吉林大学学报(工学版), 2025, 55(5): 1497-1515.
[10]	李健,刘欢,李艳秋,王海瑞,关路,廖昌义. 基于THGS算法优化ResNet-18模型的图像识别[J]. 吉林大学学报(工学版), 2025, 55(5): 1629-1637.
[11]	文斌,丁弈夫,杨超,沈艳军,李辉. 基于自选择架构网络的交通标志分类算法[J]. 吉林大学学报(工学版), 2025, 55(5): 1705-1713.
[12]	李振江,万利,周世睿,陶楚青,魏巍. 基于时空Transformer网络的隧道交通运行风险动态辨识方法[J]. 吉林大学学报(工学版), 2025, 55(4): 1336-1345.
[13]	赵孟雪,车翔玖,徐欢,刘全乐. 基于先验知识优化的医学图像候选区域生成方法[J]. 吉林大学学报(工学版), 2025, 55(2): 722-730.
[14]	金虎,申玉生,方勇,于丽,周佳媚. 基于深度学习SSD算法的公路隧道衬砌细小裂缝识别[J]. 吉林大学学报(工学版), 2025, 55(11): 3653-3659.
[15]	蔡晓东,黄业洋,董丽芳. 基于增强正例与层间负例的语义相似性模型[J]. 吉林大学学报(工学版), 2025, 55(11): 3705-3714.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

卷积层数	算法	测试精度/%
8	DNN	96.004
8	DNN+L²正则运算	97.179 6
9	DNN	97.460
9	DNN+L²正则运算	98.271
10	DNN	98.332
10	DNN+L²正则运算	98.331
11	DNN	98.334
11	DNN+L²正则运算	98.335

隐藏层数	算法	测试精度/%
8	DNN	95.596
8	DNN+L²正则运算	96.223
9	DNN	97.511
9	DNN+L²正则运算	97.730
10	DNN	98.194
10	DNN+L²正则运算	98.205
11	DNN	98.331
11	DNN+L²正则运算	98.332

算法	MAC性能/百万	运算时间/s
OMA^［24］	0.54	43 921
NOMA^［25］	0.52	43 921
CRS-NOMA^［26］	0.09	9 894
本文算法	0.50	36 997