基于遲滯噪聲混沌神經(jīng)網(wǎng)絡(luò)的導(dǎo)頻分配

邵凱; 李述棟; 王光宇; 付天飛

doi:10.11999/JEIT190748

基于遲滯噪聲混沌神經(jīng)網(wǎng)絡(luò)的導(dǎo)頻分配

doi: 10.11999/JEIT190748

邵凱^{1, 2, 3, ,},
李述棟^{1, 2},
王光宇^{1, 2, 3},
付天飛^{1, 2}

1.
重慶郵電大學(xué)通信與信息工程學(xué)院重慶 400065
2.
移動(dòng)通信技術(shù)重慶市重點(diǎn)實(shí)驗(yàn)室重慶 400065
3.
移動(dòng)通信教育部工程研究中心重慶 400065

詳細(xì)信息

作者簡(jiǎn)介:
邵凱：男，1977年生，副教授，研究方向?yàn)樾滦投噍d波調(diào)制技術(shù)、新型多址接入技術(shù)

李述棟：男，1994年生，碩士，研究方向?yàn)锳I在無線通信中的應(yīng)用

王光宇：男，1964年生，教授，研究方向?yàn)樾滦投噍d波調(diào)制技術(shù)、新型多址接入技術(shù)

付天飛：男，1992年生，碩士，研究方向?yàn)榇笠?guī)模MIMO導(dǎo)頻污染抑制技術(shù)

通訊作者:
邵凱　shaokai@cqupt.edu.cn

中圖分類號(hào): TN911
計(jì)量
- 文章訪問數(shù): 1794
- HTML全文瀏覽量: 735
- PDF下載量: 52
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-09-27
- 修回日期: 2020-05-29
- 網(wǎng)絡(luò)出版日期: 2020-06-24
- 刊出日期: 2020-10-13

Hysteretic Noisy Chaotic Neural Networks Based Pilot Assignment

Kai SHAO^{1, 2, 3
, ,},
Shudong LI^{1, 2},
Guangyu WANG^{1, 2, 3},
Tianfei FU^{1, 2}

1.
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
2.
Chongqing Key Laboratory of Mobile Communications Technology, Chongqing 400065, China
3.
Engineering Research Center of Mobile Communications, Ministry of Education, Chongqing 400065, China

摘要

摘要: 在多小區(qū)大規(guī)模多輸入多輸出(MIMO)系統(tǒng)中，導(dǎo)頻污染已經(jīng)成為制約整個(gè)系統(tǒng)的瓶頸。合理地使用導(dǎo)頻資源能減輕導(dǎo)頻污染的影響，為了尋找使邊緣用戶和容量最大的導(dǎo)頻分配方式，該文首次提出了基于遲滯噪聲混沌神經(jīng)網(wǎng)絡(luò)(HNCNN)的導(dǎo)頻分配方案。遲滯噪聲混沌神經(jīng)網(wǎng)絡(luò)作為良好的優(yōu)化工具，其優(yōu)化能力與所設(shè)計(jì)的能量函數(shù)相關(guān)。該方案結(jié)合導(dǎo)頻資源使用的特點(diǎn)以及最大化邊緣用戶和容量的計(jì)算方式，設(shè)計(jì)了新的能量函數(shù)。仿真結(jié)果表明，網(wǎng)絡(luò)能在一定迭代次數(shù)后收斂到較優(yōu)的導(dǎo)頻分配方式。與其它文獻(xiàn)方案相比，采用以HNCNN為框架求取導(dǎo)頻分配方式，可以更有效減輕導(dǎo)頻污染的影響，使系統(tǒng)性能得到改善。
- 大規(guī)模多輸入多輸出 /
- 導(dǎo)頻污染 /
- 導(dǎo)頻分配 /
- 遲滯噪聲混沌神經(jīng)網(wǎng)絡(luò)
Abstract: In multi-cell massive Multiple Input Multiple Output (MIMO) systems, pilot contamination has become the bottleneck which restricts the performance of the whole system, so the reasonable usage of pilot resources can mitigate the pilot contamination of the system. In order to find the pilot allocation method that maximizes the total transmission capacity of edge users, a pilot allocation scheme based on Hysteretic Noise Chaotic Neural Network (HNCNN) is proposed for the first time. HNCNN is a famous optimization tool, and its optimization ability is related to the designed energy function. This scheme combines the characteristics of pilot resource usage and the calculation method of maximizing the total transmission capacity of edge users to design a new energy function. The simulation results show that the proposed network can converge to a better pilot allocation mode after a certain number of iterations. Compared with other literature pilot allocation solution, the pilot allocation method based on HNCNN can further reduce the influence of pilot contamination and improve the system performance.
- Massive Multiple Input Multiple Output(MIMO) /
- Pilot contamination /
- Pilot assignment /
- Hysteretic Noise Chaotic Neural Network (HNCNN)

HTML全文

圖 1 導(dǎo)頻分配示意圖($L$=3，$K$=4)

下載: 全尺寸圖片幻燈片

圖 2 用戶分組門限示意圖

下載: 全尺寸圖片幻燈片

圖 3 導(dǎo)頻分配矩陣示例

下載: 全尺寸圖片幻燈片

圖 4 基于HNCNN的導(dǎo)頻分配流程框圖

下載: 全尺寸圖片幻燈片

圖 5 多小區(qū)多用戶場(chǎng)景

下載: 全尺寸圖片幻燈片

圖 6 不同算法的邊緣用戶上行傳輸容量對(duì)比

下載: 全尺寸圖片幻燈片

圖 7 不同算法的用戶上行傳輸容量對(duì)比

下載: 全尺寸圖片幻燈片

表 1 大規(guī)模MIMO參數(shù)

參數(shù)	取值
小區(qū)數(shù)$L$	7
每小區(qū)天線數(shù)	256
小區(qū)半徑	1.6 km
小區(qū)服務(wù)數(shù)	12
上下行發(fā)射功率	15 dBm, 43 dBm
路徑衰落指數(shù)$\alpha $	3.8
用戶分組門限F	0.33
對(duì)數(shù)陰影衰落	8 dB

下載: 導(dǎo)出CSV

表 2 HNCNN仿真分析

場(chǎng)景	隨機(jī)平均$\Sigma $	算法	有效次數(shù)	平均$\varSigma$	提升比例(%)
1	58.38	HNCNN-C	981/1000	78.73	34.86
1	58.38	HNCNN-A	1000/1000	79.90	36.86
2	65.43	HNCNN-C	982/1000	84.98	29.88
2	65.43	HNCNN-A	990/1000	85.86	31.22
3	78.26	HNCNN-C	964/1000	97.07	24.04
3	78.26	HNCNN-A	982/1000	97.49	24.57
4	54.47	HNCNN-C	982/1000	65.65	20.53
4	54.47	HNCNN-A	1000/1000	67.13	23.24
5	59.04	HNCNN-C	946/1000	82.20	39.23
5	59.04	HNCNN-A	958/1000	83.66	41.70
6	62.81	HNCNN-C	984/1000	73.14	16.45
6	62.81	HNCNN-A	993/1000	74.80	19.09

下載: 導(dǎo)出CSV

參考文獻(xiàn)(15)

NGO H Q, LARSSON E G, and MARZETTA T L. Energy and spectral efficiency of very large multiuser MIMO systems[J]. IEEE Transactions on Communications, 2013, 61(4): 1436–1449. doi: 10.1109/TCOMM.2013.020413.110848

RUSEK R, PERSSON D, LAU B K, et al. Scaling up MIMO: Opportunities and challenges with very large arrays[J]. IEEE Signal Processing Magazine, 2013, 30(1): 40–60. doi: 10.1109/MSP.2011.2178495

LEE T, PARK S, KIM H S, et al. Sounding resource management for QoS support in massive MIMO systems[J]. Computer Networks, 2014, 70: 142–153. doi: 10.1016/j.comnet.2014.05.001

MUPPIRISETTY L S, CHARALAMBOUS T, KAROUT J, et al. Location-aided pilot contamination avoidance for massive MIMO systems[J]. IEEE Transactions on Wireless Communications, 2018, 17(4): 2662–2674. doi: 10.1109/TWC.2018.2800038

ZHOU Zhichao, WANG Dong, and Wang Zhenchao. Asynchronous pilots scheduling in massive MIMO systems[C]. 2017 IEEE International Conference on Communications (ICC), Paris, France, 2017: 1–6.

方昕, 張建鋒, 曹海燕, 等. 大規(guī)模MIMO系統(tǒng)中動(dòng)態(tài)導(dǎo)頻分配[J]. 電子與信息學(xué)報(bào), 2016, 38(8): 1901–1907. doi: 10.11999/JEIT151091

FANG Xin, ZHANG Jianfeng, CAO Haiyan, et al. Dynamic pilot allocation in massive MIMO system[J]. Journal of Electronics &Information Technology, 2016, 38(8): 1901–1907. doi: 10.11999/JEIT151091

XU Yaohua and WU Yong. An approach of pilot contamination reduction based on power control and orthogonal identification[C]. The 3rd IEEE International Conference on Cloud Computing and Big Data Analysis (ICCCBDA), Chengdu, China, 2018: 476–480.

ZHANG Xiaoqing, LIU Ju, WU Shangbin, et al. Uplink pilot power control with genetic algorithm for massive MIMO networks[C]. The 9th International Conference on Wireless Communications and Signal Processing (WCSP), Nanjing, China, 2017: 1–6.

李夢(mèng)婉, 景小榮, 莫林琳. 多小區(qū)大規(guī)模MIMO系統(tǒng)中基于部分導(dǎo)頻交替復(fù)用的導(dǎo)頻污染減輕方法[J]. 信號(hào)處理, 2017, 33(8): 1104–1114. doi: 10.16798/j.issn.1003-0530.2017.08.011

LI Mengwan, JING Xiaorong, and MO Linlin. Pilot contamination reduction method with alternately fractional pilot reuse for multi-cell massive MIMO Systems[J]. Journal of Signal Processing, 2017, 33(8): 1104–1114. doi: 10.16798/j.issn.1003-0530.2017.08.011

ZHU Xudong, DAI Linglong, WANG Zhaocheng, et al. Weighted-Graph-Coloring-Based pilot decontamination for multicell massive MIMO systems[J]. IEEE Transactions on Vehicular Technology, 2017, 66(3): 2829–2834. doi: 10.1109/TVT.2016.2572203

AHN C W, RAMAKRISHNA R S, KANG C G, et al. Shortest path routing algorithm using Hopfield neural network[J]. Electronics Letters, 2001, 37(19): 1176–1178. doi: 10.1049/el:20010800

SUN Ming, ZHAO Lin, CAO Wei, et al. Novel hysteretic noisy chaotic neural network for broadcast scheduling problems in packet radio networks[J]. IEEE Transactions on Neural Networks, 2010, 21(9): 1422–1433. doi: 10.1109/TNN.2010.2059041

SUN Ming, LEE K Y, XU Yaoqun, et al. Hysteretic noisy chaotic neural networks for resource allocation in OFDMA system[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(2): 273–285. doi: 10.1109/TNNLS.2016.2618898

MARZETTA T L. Noncooperative cellular wireless with unlimited numbers of base station antennas[J]. IEEE Transactions on Wireless Communications, 2010, 9(11): 3590–3600. doi: 10.1109/TWC.2010.092810.091092

周鵬, 趙春明, 盛彬. MIMO-OFDM系統(tǒng)中基于導(dǎo)頻輔助的信道估計(jì)[J]. 電子與信息學(xué)報(bào), 2007, 29(1): 133–137.

ZHOU Peng, ZHAO Chunming, and SHENG Bin. Channel estimation based on pilot-assisted for MIMO-OFDM systems[J]. Journal of Electronics &Information Technology, 2007, 29(1): 133–137.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)