Integration of Multi-Source Heterogeneous Data for Value Assessment and Optimization Methods of 5G Network Coverage in Complex Urban Environments

LIU Shaowei; WANG Yingchun; QI Yong; CHENG Lijie; LI Yin; HUANG Long; LI Wu

doi:10.11959/j.issn.1000-0801.DXKX260016

您当前的位置：

首页 >

文章列表页 >

Integration of Multi-Source Heterogeneous Data for Value Assessment and Optimization Methods of 5G Network Coverage in Complex Urban Environments

更新时间：2026-05-11

- Integration of Multi-Source Heterogeneous Data for Value Assessment and Optimization Methods of 5G Network Coverage in Complex Urban Environments
- Telecommunications Science (2026)
- 作者机构：
  
  1.重庆市信息通信咨询设计院有限公司，重庆市，400039
  2.中国电信集团有限公司重庆分公司，重庆市，401120
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.DXKX260016
  CLC： TN929.5
- Received：07 January 2026，
  
  Revised：2026-04-10，
  
  Accepted：11 May 2026，
- 稿件说明：
移动端阅览
LIU Shaowei, WANG Yingchun, QI Yong, et al. Integration of Multi-Source Heterogeneous Data for Value Assessment and Optimization Methods of 5G Network Coverage in Complex Urban Environments[J/OL]. Telecommunications Science, 2026.
DOI：

LIU Shaowei, WANG Yingchun, QI Yong, et al. Integration of Multi-Source Heterogeneous Data for Value Assessment and Optimization Methods of 5G Network Coverage in Complex Urban Environments[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260016.

摘要

5G网络建设进入精细化运营阶段后，城区居民区的5G覆盖质量成为影响用户体验的关键指标。针对传统评估方法在多维度关联性分析、问题定位精度上的不足，以及难以适配精细化规划需求等短板，提出一种基于地理空间大数据融合的城区居民区5G覆盖评估模型。该模型整合楼宇POI、小区级网管数据、栅格级用户感知数据等多源异构信息，构建四大协同子模型，实现从场景细分到投资优先级量化的全流程评估；其中，引入LambdaMART算法作为核心排序机制，有效支撑多维指标融合下的精准价值排序。实验结果显示，模型的弱覆盖识别准确率达92.5%，决策质量与专家判断高度吻合（NDCG>0.9）。该模型可有效提升覆盖评估的效率与精度，为5G网络的精细化规划优化提供科学的决策支持。

Abstract

As 5G network construction progresses into the stage of refined operation

the quality of 5G coverage in urban residential areas has become a critical indicator influencing user experience. To overcome the limitations of traditional evaluation methods—such as insufficient multi-dimensional correlation analysis

low problem localization accuracy

and poor adaptability to refined planning requirements—this paper proposes a 5G coverage evaluation model for urban residential areas based on geospatial big data fusion. The model integrates multi-source heterogeneous information

including building points of interest (POI)

cell-level network management data

and grid-level user perception data

and constructs four collaborative sub-models to enable full-process evaluation ranging from scenario segmentation to investment priority quantification. The LambdaMART algorithm is introduced as the core ranking mechanism

effectively supporting precise value ranking under the fusion of multi-dimensional indicators. Experimental results demonstrate that the model achieves a weak coverage identification accuracy of 92.5%

and its decision quality is highly consistent with expert judgment (NDCG>0.9). The proposed model significantly improves the efficiency and accuracy of coverage evaluation

providing scientific decision support for the refined planning and optimization of 5G networks.

关键词

Keywords

references

Hossain E , Hasan M . 5G cellular: key enabling technologies and research challenges [J ] . IEEE Instrumentation & Measurement Magazine , 2015 , 18 ( 3 ): 11 - 21 . [LinkOut ]

Suryanto S , Ningsih Y K . Overview of 5G services and spectrum deployment in urban regions [J ] . Jurnal Sains , Teknologi dan Informatika, 2024 , 11 ( 1 ): 91 - 102 . [LinkOut ]

周灿 , 史文祥 , 王森 , 等 . 基于OTT MR数据的规建维优营分析体系研究 [J ] . 邮电设计技术 , 2024 ( 10 ): 42 - 48 .

Zhou C , Shi W X , Wang S , et al . Research on analysis system of PCMOM(planning, construction, maintenance, optimization, marketing)based on OTT MR data [J ] . Designing Techniques of Posts and Telecommunications , 2024 ( 10 ): 42 - 48 . [万方 ]

陈玲 , 张鹏 , 龙青良 , 等 . 基于多维价值评估的楼宇分类体系及场景化解决方案 [J ] . 邮电设计技术 , 2023 ( 2 ): 54 - 57 .

Chen L , Zhang P , Long Q L , et al . Building classification system and scenario solution based on multi-dimensional valuation [J ] . Designing Techniques of Posts and Telecommunications , 2023 ( 2 ): 54 - 57 . [万方 ]

Usa D E , Vasdev K . GIS for 5G network deployment: optimizing coverage and capacity with spatial analysis [J ] . Journal of Artificial Intelligence & Cloud Computing , 2022 , 1 ( 3 ): 1 - 3 . [LinkOut ]

Wen L , Tan H , Li W H , et al . Evaluating the coverage of 5G signals: coupling spatial autocorrelation and 3D sight lines based on GIS [C ] // Mobile Networks and Management . Cham : Springer , 2023 : 255 - 264 . [LinkOut ]

孟炜谱 , 刘旭东 , 苗二龙 , 等 . 基于众筹模式的5G网络评估与优化 [J ] . 邮电设计技术 , 2023 ( 10 ): 50 - 53 .

Meng W P , Liu X D , Miao E L , et al . 5G network evaluation and optimization based on crowdfunding model [J ] . Designing Techniques of Posts and Telecommunications , 2023 ( 10 ): 50 - 53 . [知网 ] [知网英文 ]

Martínez Abuabara R , Robles C A , Camargo L L . A multicriteria model for prioritizing 5G network deployment with Monte Carlo stability analysis: a case study in Magdalena, Colombia [J ] . PLoS One , 2025 , 20 ( 10 ): e0334781 . [LinkOut ]

Liu B L , Li Q , Zheng Z H , et al . A review of multi-source data fusion and analysis algorithms in smart city construction: facilitating real estate management and urban optimization [J ] . Algorithms , 2025 , 18 ( 1 ): 30 . [LinkOut ]

Heintz F . DyKnow: A Stream-Based Knowledge Processing Middleware Framework [J ] . Linköping University Electronic Press , 2009 .

Hoffman D D , Singh M , Prakash C . The interface theory of perception [J ] . Psychonomic Bulletin & Review , 2015 , 22 ( 6 ): 1480 - 1506 . [LinkOut ]

Zhang W Q , Zhao K , Li P , et al . A closed-loop perception, decision-making and reasoning mechanism for human-like navigation [C ] // Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence . International Joint Conferences on Artificial Intelligence Organization , 2022 : 4717 - 4724 . [LinkOut ]

Mugglin A S , Carlin B P , Gelfand A E . Fully model-based approaches for spatially misaligned data [J ] . Journal of the American Statistical Association , 2000 , 95 ( 451 ): 877 - 887 . [LinkOut ]

Chaves-Villota A , Viteri-Mera C A . DeepREM: deep-learning-based radio environment map estimation from sparse measurements [J ] . IEEE Access , 2023 , 11 : 48697 - 48714 . [LinkOut ]

Li P Z , Wang X Y , Piechocki R , et al . Variational autoencoder assisted neural network likelihood RSRP prediction model [C ] // Proceedings of the 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) . Piscataway : IEEE Press , 2022 : 554 - 559 . [LinkOut ]

Ma L , Jin N D , Zhang Y L , et al . RSRP difference elimination and motion state classification for fingerprint-based cellular network positioning system [J ] . Telecommunication Systems , 2019 , 71 ( 2 ): 191 - 203 . [LinkOut ]

Wegner T . Applied Business Statistics: Methods and Excel-Based Applications [J ] . 2010 .

Kupper L L , Hafner K B . How appropriate are popular sample size formulas? [J ] . The American Statistician , 1989 , 43 ( 2 ): 101 - 105 . [LinkOut ]

Greenland S . On sample-size and power calculations for studies using confidence intervals [J ] . American Journal of Epidemiology , 1988 , 128 ( 1 ): 231 - 237 . [LinkOut ]

Kyrgyzov I O . Mining satellite image database of landscapes and application for urban zones: clustering, consensus and categorisation [J ] . 2008 .

Zhang S J , Xia Y , Li Z J , et al . An assessment of urban residential environment quality based on multi-source geospatial data: a case study of Beijing, China [J ] . Land , 2024 , 13 ( 6 ): 823 . [LinkOut ]

Xia Z X , Chong S . WiFi-based indoor passive fall detection for medical Internet of Things [J ] . Computers and Electrical Engineering , 2023 , 109 : 108763 . [Li nkOut ]

Bergstra J , Bardenet R , Bengio Y , et al . Algorithms for Hyper-Parameter Optimization [J ] . Advances in Neural Information Processing Systems , 2011 : 2546 - 2554 .

Li X , Guo H , Xie W L , et al . A 5G coverage calculation optimization algorithm based on multifrequency collaboration [J ] . Electronics , 2023 , 12 ( 19 ): 4044 . [LinkOut ]

Fauzan A , Fadillah G , Fitria A , et al . Cluster mapping of waste exposure using DBSCAN approach: study of spatial patterns and potential distribution in bantul regency [J ] . International Journal on Informatics Visualization , 2024 , 8 ( 2 ): 751 . [LinkOut ]

夏鲁宁 , 荆继武 . SA-DBSCAN: 一种自适应基于密度聚类算法 [J ] . 中国科学院研究生院学报 , 2009 , 26 ( 4 ): 530 - 538 .

Xia L N , Jing J W . SA-DBSCAN: a self-adaptive density-based clustering algorithm [J ] . Journal of the Graduate School of the Chinese Academy of Sciences , 2009 , 26 ( 4 ): 530 - 538 . [万方 ]

Monko G J , Kimura M . Optimized DBSCAN parameter selection: stratified sampling for epsilon and gridsearch for minimum samples [C ] // Proceedings of the Software Engineering and Automation . Academy & Industry Research Collaboration Center , 2023 : 43 - 61 . [LinkOut ]

Karami A , Johansson R . Choosing DBSCAN parameters automatically using differential evolution [J ] . International Journal of Computer Applications , 2014 , 91 ( 7 ): 1 - 11 . [LinkOut ]

Matsumoto N , Hamakawa Y , Tatsumura K , et al . Distance-based clustering using QUBO formulations [J ] . Scientific Reports , 2022 , 12 : 2669 . [LinkOut ]

Zhang X L , Zhou S B . WOA-DBSCAN: application of whale optimization algorithm in DBSCAN parameter adaption [J ] . IEEE Access , 2023 , 11 : 91861 - 91878 . [LinkOut ]

方洪鹰 . 数据挖掘中数据预处理的方法研究 [D ] . 重庆 : 西南大学 , 2009 . [知网硕士中文 ]

王满 , 徐朝军 . 网络课程资源自动量化评价研究 [J ] . 现代图书情报技术 , 2010 ( 1 ): 88 - 93 .

Wang M , Xu C J . Study on automatic quantitative evaluation of web course resources [J ] . New Technology of Library and Information Service , 2010 ( 1 ): 88 - 93 . [知网 ] [知网英文 ]

唐懿芳 , 钟达夫 . 主成分分析方法对数据进行预处理 [J ] . 广西师范大学学报(哲学社会科学版) , 2002 , 38 ( S1 ): 223 - 225 .

Tang Y F , Zhong D F . Principal component analysis is used to preprocess the data [J ] . Journal of Guangxi Normal University (Philosophy and Social Sciences Edition) , 2002 , 38 ( S1 ): 223 - 225 . [知网 ] [Sogou标题中译英 ]

Burges C J C . From RankNet to LambdaRank to LambdaMART: An Overview [J ] . learning , 2010 .

Haenelt K . Ranking with Boosted Decision Trees [J ] . 2012 .

Fu Y J , Ge Y , Zheng Y , et al . Sparse real estate ranking with online user reviews and offline moving behaviors [C ] // Proceedings of the 2014 IEEE International Conference on Data Mining . Piscataway : IEEE Press , 2014 : 120 - 129 . [LinkOut ]

Zhang X , Ren Z , Li X , et al . Phocus: Picking Valuable Research from a Sea of Citations [J ] . 2022

Munir M S , Kim K T , Adhikary A , et al . Neuro-symbolic explainable artificial intelligence twin for zero-touch IoE in wireless network [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 24 ): 22451 - 22468 . [LinkOut ]

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Solutions for 5G high-speed railway dedicated network optimization based on mobile user profiling

Smart CAPEX wireless network planning method integrating multi-source data and machine learning

Research on optimization of low-altitude communication networks

Research on the application of 5G air interface dual-transmit and selective reception technology for industrial Internet

Application of the RFA-XGBoost model in predicting potential complaint users in mobile network

Related Author

Xu Ming

Shi Yuanyuan

Li Dan

Li Aihua

Wei Bin

Zhang Chong

Li Huihui

Guo Hongfeng

Related Institution

China Mobile Research Institute

China Mobile Communications Group Co., Ltd.

China Mobile Group Guangdong Co., Ltd.

China Telecom Global Limited

Branch Four, China International Telecommunication Construction GroupDesign Institute Co., Ltd.

⁰