An Adaptive Network Coverage Optimization Method based on Reinforcement Learning

LIU Xu-dong; ZHAO Su; ZHU Xiao-rong

doi:10.13756/j.gtxyj.2022.05.012

您当前的位置：

首页 >

文章列表页 >

An Adaptive Network Coverage Optimization Method based on Reinforcement Learning

更新时间：2023-01-29

- An Adaptive Network Coverage Optimization Method based on Reinforcement Learning
- Study on Optical Communications Issue 5, Pages: 66-73(2022)
- 作者机构：
  
  南京邮电大学　江苏省无线通信重点实验室，南京　210003
- 作者简介：
- 基金信息：
- DOI：10.13756/j.gtxyj.2022.05.012
  CLC： TP391
- Published：10 October 2022，
  
  Received：12 August 2021，
扫描看全文
LIU Xu-dong, ZHAO Su, ZHU Xiao-rong. An Adaptive Network Coverage Optimization Method based on Reinforcement Learning. [J]. Study on Optical Communications (5):66-73(2022)
DOI：

LIU Xu-dong, ZHAO Su, ZHU Xiao-rong. An Adaptive Network Coverage Optimization Method based on Reinforcement Learning. [J]. Study on Optical Communications (5):66-73(2022) DOI： 10.13756/j.gtxyj.2022.05.012.

摘要

随着第五代移动通信技术（5G）的发展以及网络架构的演进，网络覆盖的分析以及优化不仅需要考虑基站天馈系统的链路预算，而且需要结合基站覆盖区域的时空特性，从而设计出更精确的覆盖优化方案。文章提出了一种基于Q学习的自适应网络覆盖优化算法，首先采用一种基于数据挖掘的网络覆盖预测模型，通过小区天线参数的配置预测出接入终端的覆盖情况，并基于真实数据验证模型预测的准确性；其次，改进强化学习中智能体的动作选择策略，根据覆盖率设置各小区不同的优化优先级，结合贪心策略，选择出需要优化的小区及其优化参数值，有效地降低了迭代过程中陷入局部最优的概率。仿真结果表明，文章所提算法可提高优化过程收敛速度，同时对网络覆盖率的提升幅度可达到20%。

Abstract

With the development of 5th Generation Mobile Communication Technology (5G) and the evolution of network architecture

the analysis and optimization of network coverage need to consider comprehensive factors

including not only the link budget of the base station antenna system

but also the geographical conditions and time characteristics of the area covered by the base station. Therefore

a more accurate network coverage optimization plan should be designed. This paper proposes an adaptive network coverage optimization algorithm based on Q-learning. The method first adopts a cellular network coverage prediction model based on data mining

which can predict the coverage situation of the access terminal through the configuration of the antenna of the cell

and verify the accuracy of the prediction based on real data. Then

a network coverage optimization algorithm based on Q-learning is proposed which modifies the action selection strategy of the agent in reinforcement learning process. According to the coverage of each cell

different optimization priorities are set. Combined with the greedy strategy

a cell and its antenna parameters are decided by the agent in each iteration. This method effectively reduces the probability of falling into a local optimum during the iteration process

and the method also has a good performance in reducing the convergence time of the optimization process. The simulation result shows that the algorithm can increase the network coverage by up to 20%.

关键词

蜂窝网络覆盖优化Q学习贪心策略

Keywords

cellular networkcoverage optimizationQ-learninggreedy strategy

references

IMT-2020(5G)推进组. 5G概念白皮书[EB/OL]. (2015-02-11)[2021-08-12]. http://www.imt2020.org.cn/zhhttp://www.imt2020.org.cn/zh.

IMT-2020(5G) White Paper on Propulsion Group-5G concept[EB/OL]. (2015-02-11)[2021-08-12]. http://www.imt2020.org.cn/zhhttp://www.imt2020.org.cn/zh.

Bhushan N, Li J, Malladi D, et al. Network Densification: The Dominant Theme for Wireless Evolution into 5G[J]. Communications Magazine, IEEE, 2014, 55(2): 82-89.

夏永康, 梁晓霞. LTE网络天线下倾角自优化算法[J]. 无线电工程, 2014(3): 11-14.

Xia Y K, Liang X W. An Algorithm of Antenna Tilt Self-optimization in LTE Networks[J]. Radio Engineering of China, 2014(3): 11-14.

Eckhardt H, Klein S, Gruber M. Vertical Antenna Tilt Optimization for LTE Base stations[C]// Vehicular Technology Conference (VTC Spring). Budapest, Hungary: IEEE, 2011: 5956370.

Ma H, Sahoo P K, Chen Y W. Computational Geometry based Distributed Coverage Hole Detection Protocol for the Wireless Sensor Networks[J]. Journal of Network and Computer Applications, 2011, 34(5): 1743-1756.

Siomina I, Varbrand P, Yuan D. Automated Optimization of Service Coverage and Base Station Antenna Configuration in UMTS Networks[J]. IEEE Wireless Communications, 2006, 13(6): 16-25.

范绍帅. 自组织网络智能化控制与优化策略研究[D]. 北京: 北京邮电大学, 2015.

Fan Z S. Research on Intelligent Control and Optimization Strategy in Self-Organizing Networks[D]. Beijing: Beijing University of Posts and Telecommunications, 2015.

Breiman L. Random Forest[J]. MachineLearning, 2001, 45(1): 5-32.

周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.

Zhou Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016.

Lin Z, Ouyang Y, Su L, et al. A Machine Learning Assisted Method of Coverage and Capacity Optimization (CCO) in 4G LTE Self Organizing Networks (SON) [C]// 2019 Wireless Telecommunications Symposium (WTS). New York, NY, USA: IEEE, 2019: 8715538.

谷欣杏. LTE网络覆盖优化及无线定位优化算法的研究[D]. 北京: 北京邮电大学, 2019.

Gu X X. Research on Lte Network Coverage Optimization and Wireless Positioning Algorithm[D]. Beijing: Beijing University of Posts and Telecommunications, 2019.

肖智清. 强化学习：原理与Python实现[M]. 北京: 机械工业出版社, 2019.

Xiao Z Q. Reinforcement Learning Theory and Python Implementation[D]. Beijing: Machinery Industry Press, 2019.

衷宇清, 陈文文, 李昭桦. 不平衡数据分类中的数据重采样比较研究[J]. 通信技术, 2020, 53(6): 1376-1384.

Zhong Y Q, Chen W W, Li Z H. An Algorithm of Antenna Tilt Self-optimization in LTE Networks[J]. Communications Technology, 2020, 53(6): 1376-1384.

彭木根, 李勇. 宽带移动通信系统的网络自组织（SON）技术[M]. 北京: 北京邮电大学出版社, 2013.

Peng M G, Li Y. Self-Organization Networing Techniques in Broadband Mobile Communication Systems[M]. Beijing: Beijing University of Posts and Telecommunications Press, 2013.

更多指标>

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Improved Sphere Decoding Detection Algorithm based on Lattice-Reduction-Aided

Related Author

No data

Related Institution

School of Communication and Information Engineering CQUPT

Postal code：430205
Technical support is provided by Beijing Founder electronics co., LTD 鄂ICP备2022010197 鄂公网安备 42011202002092号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：75848 Visits Today：3

⁰