5G channel state information signal quality and positioning performance analysis
-
摘要: 5G信道状态信息(channel state information，CSI)具有丰富的特征信息，是一种理想的指纹定位信号，但信号质量易受环境干扰，对定位性能影响较大. 为了分析不同因素对5G信号质量和定位性能的影响程度，本文首先阐述了5G信号特征和基于支持向量回归(support vector regression，SVR)的定位算法，分析了数据采集时终端的高度、方向、人体遮挡等因素对信号质量的影响，测试了廊厅、小办公室和中型会议室三种场景下的定位性能. 结果表明：5G信号质量受周围环境影响较大，在干扰较小的情况下，基于5G CSI的位置指纹定位算法在三种场景下的定位精度分别为0.93 m、1.46 m和1.94 m，能够满足大多数室内定位应用需求.
-
关键词:
- 5G /
- 信道状态信息(CSI) /
- 位置指纹 /
- 室内定位 /
- 支持向量回归(SVR)
Abstract: 5G channel state information (CSI) has rich feature information, but it is greatly affected by environmental information , which directly affects the fingerprint positioning performance. In order to analyze the degree of influence of different factors on 5G signal quality and positioning performance, this paper first expounds the 5G signal characteristics and positioning algorithm based on support vector regression (SVR), analyzes the influence of terminal height, direction, human body occlusion and other factors on signal quality during data acquisition, and tests the positioning performance in three scenarios: hallway, small office and medium-sized conference room. The results show that the 5G signal is greatly affected by the surrounding environment, and the positioning accuracy of the location fingerprint localization algorithm based on 5G channel state information has positioning accuracy of 0.93 m, 1.46 m and 1.94 m respectively in three scenarios, which can meet the needs of most indoor positioning applications.-
Key words:
- 5G /
- channel state information /
- location fingerprint /
- indoor localization /
- support vector regression
-
[1] XUE W S, QIU W N, HUA X H, et al. Improved Wi-Fi RSSI measurement for indoor localization[J]. IEEE sensors journal, 2017, 17(7): 2224-2230. DOI: 10.1109/JSEN.2017.2660522 [2] AL-TAHMEESSCHI A, TALVITIE J, LOPEZ–BENITEZ M, et al. Deep learning-based fingerprinting for outdoor UE positioning utilising spatially correlated RSSs of 5G networks[C]//IEEE International Conference on Localization and GNSS (ICL-GNSS), 2022. DOI: 10.1109/ICL-GNSS54081.2022.9797017 [3] HAN S, LI Y, MENG W X, et al. Indoor localization with a single Wi-Fi access point based on OFDM-MIMO[J]. IEEE systems journal, 2019, 13(1): 964-972. DOI: 10.1109/JSYST.2018.2823358 [4] ZIMAGLIA E, RIVIELLO D G, GARELLO R, et al. A novel deep learning approach to CSI feedback reporting for NR 5G cellular systems[C]//IEEE Microwave Theory and Techniques in Wireless Communications (MTTW), 2020. DOI: 10.1109/MTTW51045.2020.9245055 [5] NASIR Y S, GUO D N. Multi-Agent deep reinforcement learning for dynamic power allocation in wireless networks[J]. IEEE journal on selected areas in communications, 2019, 37(10): 2239-2250. DOI: 10.1109/JSAC.2019.2933973 [6] 刘帅, 王旭东, 吴楠. 一种基于卷积神经网络的CSI指纹室内定位方法[J]. 工程科学学报, 2021, 43(11): 1512-1521. [7] 丁昭, 高同跃, 张忠超, 等. 基于CSI与IMU的室内行人导航定位系统研究[J]. 工业控制计算机, 2022, 35(5): 9-12. [8] GAO K X, WANG H Q, LV H G, et al. Toward 5G NR high-precision indoor positioning via channel frequency response: a new paradigm and dataset generation method[J]. IEEE journal on selected areas in communications, 2022, 40(7): 2233-2247. DOI: 10.1109/JSAC.2022.3157397 [9] KIA G, RUOTSALAINEN L, TALVITIE J. A CNN approach for 5G mm wave positioning using beamformed CSI measurements[C]//International Conference on Localization and GNSS (ICL-GNSS), 2022. DOI: 10.1109/ICL-GNSS54081.2022.9797028 [10] GUO C, YU J, GUO W F, et al. Intelligent and ubiquitous positioning framework in 5G edge computing scenarios[J]. IEEE access, 2020(8): 83276-83289. DOI: 10.1109/ACCESS.2020.2990639 [11] 李芬芳, 汝春瑞, 党小超, 等. 基于CSI和加权混合回归的室内定位方法[J]. 传感技术学报, 2022, 35(5): 667-675. [12] 张千坤, 陈任翔, 钟志刚, 等. 基于机器学习的5G室内定位方法[J]. 邮电设计技术, 2022(7): 50-55. [13] LI Q, LIAO X W, LIU M M, et al. Indoor localization based on CSI fingerprint by siamese convolution neural network[J]. IEEE transactions on vehicular technology, 2021, 70(11): 12168-12173. DOI: 10.1109/TVT.2021.3107936 [14] 张会清, 王宇桐. 基于堆叠稀疏自动编码器和SVM的CSI室内定位方法[J]. 北京工业大学学报, 2021, 47(12): 1321-1329. [15] 胡灏, 陈亮, 刘钊良, 等. 基于5G信号的室内用户行为感知[C]//第十三届中国卫星导航年会论文集—S09PNT体系与PNT新技术, 2022. -
下载:
点击查看大图
图(9) / 表(3)
计量
- 文章访问数: 271
- HTML全文浏览量: 38
- PDF下载量: 24
- 被引次数: 0
