A quantitative evaluation scheme of coverage performance in planning wireless network based on machine learning

被引：0
作者：
Xiao Z. [1 ,2 ]
Wu X. [2 ]
Xu Z. [1 ,2 ]
Liu H. [1 ,2 ]
Ma J. [3 ]
Wu R. [3 ]
机构：
[1] Research Institute of Economics and Technology, State Grid Hunan Electric Power Co. Ltd., Changsha
[2] State Grid Hunan Electric Power Co. Ltd., Changsha
[3] College of Computer Science and Electronic Engineering, Hunan University, Changsha
来源：
Wu, Renyong (wurenyong@hnu.edu.cn) | 2021年 / Central South University of Technology卷 / 52期
基金：
中国国家自然科学基金;
关键词：
Coverage performance evaluation; Machine learning; Network planning; Power wireless network;
D O I：
10.11817/j.issn.1672-7207.2021.10.014
中图分类号：
学科分类号：
摘要：
The coverage range and communication quality of a wireless network is determined by the coverage performance, which is also one of the key performance metrics of wireless networks, but the existing schemes can only achieve qualitative evaluation on the network planning and require high personnel professional knowledge and skills, and it is difficult to be popularized. In order to solve these problems, a new quantitative evaluating scheme based on machine learning was proposed. Performance evaluation of network coverage was a type of classification problems, and so the random forest algorithm was introduced to construct the evaluation model. To improve the accuracy, zero-phase component analysis(ZCA) was used to reduce the data correlation and the out-of-bag errors were calculated out. The results show that the proposed scheme can not only quantify the coverage performance, but also effectively and accurately analyze and compare the overall coverage performance of different network planning programs by calculating their network coverage rates, and the corresponding software platform can significantly reduce the complexity of evaluation work and the requirements to personnel professional knowledge and skills. © 2021, Central South University Press. All right reserved.
引用
收藏
页码：3505 / 3512
页数：7
相关论文
共 19 条
  • [1] ZHAO Honghao, BI Qinggang, LU Bin, Et al., The innovative application of power wireless private network in smart grid, Electric Power Information and Communication Technology, 17, 1, pp. 110-115, (2019)
  • [2] CAO Jinping, LIU Jianming, LI Xiangzhen, Et al., Performance analysis of a new power wireless private network in intelligent distribution networks, 2012 Power Engineering and Automation Conference, pp. 1-4, (2012)
  • [3] DONG Junhua, ZHANG Junmin, HUANG Xiaoguang, Et al., 4G wireless network planning and simulation method analysis, Mobile Communications, 41, 8, pp. 5-9, (2017)
  • [4] HE Qing, LI Ning, LUO Wenjuan, Et al., A survey of machine learning algorithms for big data, Pattern Recognition and Artificial Intelligence, 27, 4, pp. 327-336, (2014)
  • [5] ATHMAJA S, HANUMANTHAPPA M, KAVITHA V., A survey of machine learning algorithms for big data analytics, 2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), pp. 1-4, (2017)
  • [6] GUO G, WANG H, BELL D A, Et al., KNN model-based approach in classification, OTM Confederated International Conferences "On the More to Meaningful Internet Systems", (2003)
  • [7] BREIMAN L., Random forests, Machine Learning, 45, 1, pp. 5-32, (2001)
  • [8] SVETNIK V, LIAW A, TONG C, Et al., Random forest: a classification and regression tool for compound classification and QSAR modeling, Journal of Chemical Information and Computer Sciences, 43, 6, pp. 1947-1958, (2003)
  • [9] SAFAVIAN S R, LANDGREBE D., A survey of decision tree classifier methodology, IEEE Transactions on Systems, Man, and Cybernetics, 21, 3, pp. 660-674, (1991)
  • [10] ROKACH L, MAIMON O., Top-down induction of decision trees classifiers-a survey, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 35, 4, pp. 476-487, (2005)
12