Indoor Genetic Algorithm-Based 5G Network Planning Using a Machine Learning Model for Path Loss Estimation

被引:21
作者
Hervis Santana, Yosvany [1 ,2 ]
Martinez Alonso, Rodney [1 ]
Guillen Nieto, Glauco [2 ]
Martens, Luc [1 ]
Joseph, Wout [1 ]
Plets, David [1 ]
机构
[1] Ghent Univ IMEC, Dept Informat Technol, Technol Pk Zwijnaarde 126, B-9052 Ghent, Belgium
[2] Res & Dev Telecommun Inst, LACETEL, Havana 19210, Cuba
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 08期
关键词
5G; genetic algorithm; indoor environment; machine learning; network planning; path loss; modeling; PROPAGATION; COVERAGE;
D O I
10.3390/app12083923
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Accurate wireless network planning is crucial for the deployment of new wireless services. This usually requires the consecutive evaluation of many candidate solutions, which is only feasible for simple path loss models, such as one-slope models or multi-wall models. However, such path loss models are quite straightforward and often do not deliver satisfactory estimations, eventually impacting the quality of the proposed network deployment. More advanced models, such as Indoor Dominant Path Loss models, are usually more accurate, but as their path loss calculation is much more time-consuming, it is no longer possible to evaluate a large set of candidate deployment solutions. Out of necessity, a heuristic network planning algorithm is then typically used, but the outcomes heavily depend on the quality of the heuristic. Therefore, this paper investigates the use of Machine Learning to approximate a complex 5G path loss model. The much lower calculation time allows using this model in a Genetic Algorithm-based network planning algorithm. The Machine Learning model is trained for two buildings and is validated on three other buildings, with a Mean Absolute Error below 3 dB. It is shown that the new approach is able to find a wireless network deployment solution with an equal, or smaller, amount of access points, while still providing the required coverage for at least 99.4% of the receiver locations and it does this 15 times faster. Unlike a heuristic approach, the proposed one also allows accounting for additional design criteria, such as maximal average received power throughout the building, or minimal exposure to radiofrequency signals in certain rooms.
引用
收藏
页数:18
相关论文
共 43 条
[1]   Genetic-Voronoi algorithm for coverage of IoT data collection networks [J].
Abdallah, Wajih ;
Mnasri, Sami ;
Val, Thierry .
30TH INTERNATIONAL CONFERENCE ON COMPUTER THEORY AND APPLICATIONS (ICCTA 2020), 2020, :16-22
[2]  
Adegoke E.I., 2019, IFIP WIREL DAY, P1
[3]  
Akhpashev RV, 2016, INT CONF SEMINAR, P64, DOI 10.1109/EDM.2016.7538693
[4]   Large-Scale Dataset for the Analysis of Outdoor-to-Indoor Propagation for 5G Mid-Band Operational Networks [J].
Ali, Usman ;
Caso, Giuseppe ;
De Nardis, Luca ;
Kousias, Konstantinos ;
Rajiullah, Mohammad ;
Alay, Ozgu ;
Neri, Marco ;
Brunstrom, Anna ;
Di Benedetto, Maria-Gabriella .
DATA, 2022, 7 (03)
[5]  
Apavatjrut A, 2021, ECTI T ELECT ENG ELE, V19, P322, DOI [10.37936/ecti-eec.2021193.244941, DOI 10.37936/ECTI-EEC.2021193.244941]
[6]   The impact of 5G on the evolution of intelligent automation and industry digitization [J].
Attaran, Mohsen .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 14 (5) :5977-5993
[7]  
Breiman L, 1996, MACH LEARN, V24, P123, DOI 10.1023/A:1018054314350
[8]  
Cheng H, 2018, I C INF COMM TECH CO, P605, DOI 10.1109/ICTC.2018.8539415
[9]   A Novel Link-to-System Mapping Technique Based on Machine Learning for 5G/IoT Wireless Networks [J].
Chu, Eunmi ;
Yoon, Janghyuk ;
Jung, Bang Chul .
SENSORS, 2019, 19 (05)
[10]   Study and Investigation on 5G Technology: A Systematic Review [J].
Dangi, Ramraj ;
Lalwani, Praveen ;
Choudhary, Gaurav ;
You, Ilsun ;
Pau, Giovanni .
SENSORS, 2022, 22 (01)