《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (3): 855-862.DOI: 10.11772/j.issn.1001-9081.2023030292

• 网络与通信 • 上一篇    下一篇

面向城区的基于图去噪的小区级RSRP估计方法

郑毅, 廖存燚, 张天倩, 王骥, 刘守印()   

  1. 华中师范大学 物理科学与技术学院,武汉 430079
  • 收稿日期:2023-03-22 修回日期:2023-06-09 接受日期:2023-06-14 发布日期:2023-08-01 出版日期:2024-03-10
  • 通讯作者: 刘守印
  • 作者简介:郑毅(1993—),男,湖北武汉人,博士,主要研究方向:智能通信、深度学习
    廖存燚(1998—),男,四川成都人,博士研究生,主要研究方向:深度学习、自动驾驶
    张天倩(2000—),女,河南南阳人,博士研究生,主要研究方向:智能通信、深度学习
    王骥(1987—),男,湖北襄阳人,副教授,博士,主要研究方向:超大规模MIMO、智能通信;
  • 基金资助:
    国家自然科学基金资助项目(62101205);湖北省自然科学基金资助项目(2021CFB248);湖北省重点研发计划项目(2021BAA170)

Image denoising-based cell-level RSRP estimation method for urban areas

Yi ZHENG, Cunyi LIAO, Tianqian ZHANG, Ji WANG, Shouyin LIU()   

  1. College of Physical Science and Technology,Central China Normal University,Wuhan Hubei 430079,China
  • Received:2023-03-22 Revised:2023-06-09 Accepted:2023-06-14 Online:2023-08-01 Published:2024-03-10
  • Contact: Shouyin LIU
  • About author:ZHENG Yi, born in 1993, Ph. D. His research interests include intelligent communication, deep learning.
    LIAO Cunyi, born in 1998, Ph. D. candidate. His research interests include deep learning, automatic driving.
    ZHANG Tianqian, born in 2000, Ph. D. candidate. Her research interests include intelligent communication, deep learning.
    WANG Ji, born in 1987, Ph. D., associate professor. His research interests include ultra-large-scale MIMO, intelligent communication.
  • Supported by:
    National Natural Science Foundation of China(62101205);Natural Science Foundation of Hubei Province(2021CFB248);Key Research and Development Program of Hubei Province(2021BAA170)

摘要:

移动通信系统网络的规划、部署和优化都不同程度依赖于参考信号接收功率(RSRP)估计的准确性。传统上,基站覆盖小区内某信号接收点的RSRP可由对应的无线传播模型估计。在城市环境中,不同小区的无线传播模型需要使用大量RSRP实测数据校正。由于不同小区环境存在差异,经过校正后的模型只适用于对应小区,且小区内的RSRP估计精度低。针对上述问题,将RSRP估计问题转化为图去噪问题,并通过图像处理与深度学习技术得到小区级无线传播模型,不仅能实现小区整体的RSRP估计,且能适用于相似环境小区。首先,通过随机森林回归器逐点预测每个接收点的RSRP,得到整个小区的RSRP估计图;然后,将RSRP估计图和实测RSRP分布图之间的损失视为RSRP噪声图,提出基于条件生成对抗网络(CGAN)的图去噪RSRP估计方法,通过电子环境地图反映小区的环境信息,有效地降低不同小区的RSRP。实验结果表明,在无实测数据的跨小区RSRP预测场景下,所提方法预测RSRP的均方根误差(RMSE)为6.77 dBm,相较于基于卷积神经网络的RSRP估计方法EFsNet下降2.55 dBm;在同小区RSRP预测场景下,相较于EFsNet,模型参数量减小80.3%。

关键词: 条件生成对抗网络, 机器学习, 参考信号接收功率, 无线传播模型, 图去噪

Abstract:

The planning, deployment and optimization of mobile communication system networks all depend to varying degrees on the accuracy of the Reference Signal Receiving Power (RSRP) estimation. Traditionally, the RSRP of a signal receiver in a cell covered by a base station can be estimated by the corresponding wireless propagation model. In an urban environment, the wireless propagation models for different cells need to be calibrated using a large number of RSRP measurements. Due to the environment differences of different cells, the calibrated model is only applicable to the corresponding cell, and has low accuracy of RSRP estimation within the cell. To address these issues, the RSRP estimation problem was transformed into an image denoising problem and a cell-level wireless propagation model was obtained through image processing and deep learning techniques, which not only enabled RSRP estimation for the cell as a whole, but also was suitable to cells in similar environments. Firstly, the RSRP estimation map of the whole cell was obtained by predicting the RSRP of each receiver point by point through a random forest regressor. Then, the loss between the RSRP estimation map and the measured RSRP distribution map was regarded as the RSRP noise map, and a image denoising RSRP estimation method based on Conditional Generative Adversarial Network (CGAN) was proposed to reflect the environmental information of the cell through an electronic environmental map, which effectively reduced the RSRP of different cell. Experimental results show that the root mean square error of the proposed method is 6.77 dBm in predicting RSRP in a new cross-cell RSRP scenario without measured data, which is 2.55 dBm lower than that of the convolutional neural network-based RSRP estimation method EFsNet; in the same-cell RSRP prediction scenario, the number of model parameters is reduced by 80.3% compared with EFsNet.

Key words: Conditional Generative Adversarial Network (CGAN), machine learning, Reference Signal Receiving Power (RSRP), wireless propagation model, image denoising

中图分类号: