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

Dou Zhongzhao; Zhou Hong; Yang Mingshuai

doi:10.11959/j.issn.1000-0801.2026027

您当前的位置：

首页 >

文章列表页 >

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

Engineering and Application | 更新时间：2026-03-05

- Smart CAPEX wireless network planning method integrating multi-source data and machine learning
- Telecommunications Science Vol. 42, Issue 2, Pages: 187-194(2026)
- 作者机构：
  
  中国电信国际有限公司，北京100010
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2026027
  CLC： TN929.5
- Received：30 July 2025，
  
  Accepted：29 August 2025，
  
  Published：20 February 2026
- 稿件说明：
移动端阅览
窦中兆,周宏,杨明帅.融合多源数据与机器学习的Smart CAPEX无线网络规划方法[J].电信科学,2026,42(02):187-194.

Dou Zhongzhao,Zhou Hong,Yang Mingshuai.Smart CAPEX wireless network planning method integrating multi-source data and machine learning[J].Telecommunications Science,2026,42(02):187-194.
窦中兆,周宏,杨明帅.融合多源数据与机器学习的Smart CAPEX无线网络规划方法[J].电信科学,2026,42(02):187-194. DOI： 10.11959/j.issn.1000-0801.2026027.

Dou Zhongzhao,Zhou Hong,Yang Mingshuai.Smart CAPEX wireless network planning method integrating multi-source data and machine learning[J].Telecommunications Science,2026,42(02):187-194. DOI： 10.11959/j.issn.1000-0801.2026027.

摘要

如何灵活实施分期建设、如何确保网络投资落在高经济回报区域、如何以网络差异化赢得市场竞争优势，这是新进入的运营商在绿地建网规划中面临的一系列难题。为解决这些问题，提出一种融合多源数据和机器学习的无线网络规划方法。首先，根据多源数据建立多维因子体系，通过机器学习得到各因子权重，据此建立区域综合评分体系；然后，引入多象限矩阵策略，校正不同区域优先级与目标覆盖率，确定区域优先级排序；最后，在实践中应用和验证。研究表明，相较传统网络规划方法，该方法具有更好的投资回报导向，可有效提升网络覆盖率和投资收益率。对应3个典型时点第3年、第5年和第10年，该方法可分别提升商用区域覆盖率14%、16%和17%，投资收益率分别提高21%、19 %和16%。

Abstract

How to ensure that network investment is directed to high return areas

how to achieve flexible deployment in phases

and how to quickly establish differentiated network advantages are key challenges faced by new entrants. To systematically address the issues

a wireless network planning method that integrated multi-source data and machine learning was proposed. Firstly

based on multi-source data sources

a multidimensional factor system was constructed

and the weights of each factor were optimized through machine learning model training to form a regional comprehensive scoring system. Then a multi-quadrant matrix strategy was used to adjust regional priorities and target population coverage rate

and a regional deployment priority list was generated. Finally

the method was verified and applied through actual case. It shows that this method is more ROI-oriented than traditional planning methods

which can effectively improve both network coverage rate and ROI. This method can effectively increase the commercial area coverage rate by 14%

16% and 17% at three typical timeline in the 3rd

5th and 10th years respectively

and increase the investment return rate by 21%

19% and 16% respectively.

关键词

Keywords

references

陈宇 , 陈晓冬 , 刘悦 . 移动无线网大数据规划模型研究 [J ] . 电信科学 , 2019 , 35 ( 12 ): 112 - 121 .

Chen Y , Chen X D , Liu Y . Research on the big data planning model of mobile wireless network [J ] . Telecommunications Science , 2019 , 35 ( 12 ): 112 - 121 .

Yuliana H , Iskandar , Hendrawan . Comparative analysis of machine learning algorithms for 5G coverage prediction: identification of dominant feature parameters and prediction accuracy [J ] . IEEE Access , 2024 , 12 : 18939 - 18956 .

陆南昌 , 刘吉宁 , 黄海晖 . 5G无线网络智能规划技术的探索与实践 [J ] . 移动通信 , 2020 , 44 ( 5 ): 61 - 67 .

Lu N C , Liu J N , Huang H H . Exploration and practice of intelligent planning technology for 5G wireless networks [J ] . Mobile Communications , 2020 , 44 ( 5 ): 61 - 67 .

李梅 , 杜翠凤 , 沈文明 . 基于大数据分析的移动通信网络规划方法 [J ] . 移动通信 , 2015 , 39 ( 10 ): 22 - 27 .

Li M , Du C F , Shen W M . Mobile communication network planning based on big data analysis [J ] . Mobile Communications , 2015 , 39 ( 10 ): 22 - 27 .

Philippine Statistics Authority . City-level population and GDP open dataset [EB ] . 2020 .

OpenSignal . User experience dataset [EB ] . 2025 .

Open Street Map . Geographical dataset [EB ] . 2025 .

Chakravorti A , Chaugule S . Quality differentiation and entry deterrence in telecommunications [J ] . Telecom Policy Journal , 2005 .

Roland Berger Strategy Consultants . Succeeding as a telecom challenger: how to win facing strong competitors [J ] . Think Act , 2015 .

张斌 . TD-LTE无线网络规划关键技术研究 [D ] . 南京 : 南京邮电大学 , 2012 .

Zhang B . Research on key technologies of TD-LTE wireless network planning [D ] . Nanjing : Nanjing University of Posts and Telecommunications , 2012 .

钱权智 . 面向5G与LTE混合组网的无线网络规划研究 [D ] . 重庆 : 重庆邮电大学 , 2020 .

Qian Q Z . Research on wireless network planning for 5G and LTE hybrid network [D ] . Chongqing : Chongqing University of Posts and Telecommunications , 2020 .

Views

111

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of random forest in big data completion

A Big Data Based Analytical Model for Telecom Operator's Energy Usage Optimization

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

Research on telecom industry customer churn prediction based on explainable machine learning models

Related Author

Zheng WANG

Hua REN

Yanping FANG

Ai Fang

Duo Jin

Xiong Xu

Bing Liang

ZHANG Peng

Related Institution

China Mobile Group Design Institute Co., Ltd., Hubei Branch

College of Statistics and Data Science, Xinjiang University of Finance and Economics

School of Computer Science and Technology, Civil Aviation University of China

School of Safety Science and Engineering, Civil Aviation University of China

School of Information Engineering, Yangzhou University

⁰