Path Loss Prediction Based on Machine Learning: Principle, Method, and Data Expansion
Source abstract
Abstract
Path loss prediction is of great significance for the performance optimization of wireless networks. With the development and deployment of the fifth-generation (5G) mobile communication systems, new path loss prediction methods with high accuracy and low complexity should be proposed. In this paper, the principle and procedure of machine-learning-based path loss prediction are presented. Measured data are used to evaluate the performance of different models such as artificial neural network, support vector regression, and random forest. It is shown that these machine-learning-based models outperform the log-distance model. In view of the fact that the volume of measured data sometimes cannot meet the requirements of machine learning algorithms, we propose two mechanisms to expand the training dataset. On one hand, old measured data can be reused in new scenarios or at different frequencies. On the other hand, the classical model can also be utilized to generate a number of training samples based on the prior information obtained from measured results. Measured data are employed to verify the feasibility of these data expansion mechanisms. Finally, some issues for future research are discussed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Millimeter-Wave Propagation and Modeling · Advanced MIMO Systems Optimization · Power Line Communications and Noise
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
Funding
National Natural Science Foundation of China · National High Technology Research and Development Program of China
References (35)
Show source-provided references
1. Rappaport, T.S. (2002). Wireless Communications: Principles and Practice, Prentice-Hall. [2nd ed.].
2. A survey of wireless path loss prediction and coverage mapping methods10.1109/SURV.2012.022412.00172 ↗
3. Macrocell path-loss prediction using artificial neural networks10.1109/TVT.2010.2050502 ↗
4. An empirically based path loss model for wireless channels in suburban environments10.1109/49.778178 ↗
5. A UHF path loss model using learning machine for heterogeneous networks10.1109/TAP.2017.2705112 ↗
6. Isabona, J., and Srivastava, V.M. (2016, January 21–23). Hybrid neural network approach for predicting signal propagation loss in urban microcells. Proceedings of the 2016 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Agra, India.10.1109/R10-HTC.2016.7906853 ↗
7. Wu, D., Zhu, G., and Ai, B. (2010, January 25–27). Application of artificial neural networks for path loss prediction in railway environments. Proceedings of the 2010 5th International ICST Conference on Communications and Networking, Beijing, China.10.4108/iwoncmm.2010.10 ↗
8. Popescu, I., Nikitopoulos, D., Constantinou, P., and Nafornita, I. (2006, January 11–14). ANN prediction models for outdoor environment. Proceedings of the 2006 IEEE 17th International Symposium on Personal, Indoor and Mobile Radio Communications, Helsinki, Finland.10.1109/PIMRC.2006.254270 ↗
9. Popescu, I., Nikitopoulos, D., Nafornita, I., and Constantinou, P. (2006, January 19–21). ANN prediction models for indoor environment. Proceedings of the 2006 IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, Montreal, QC, Canada.10.1109/PIMRC.2006.254270 ↗
10. A multi-wall and multi-frequency indoor path loss prediction model using artificial neural networks10.1007/s13369-015-1949-6 ↗
11. Body shadowing and furniture effects for accuracy improvement of indoor wave propagation models10.1109/TWC.2014.2339275 ↗
12. Popescu, I., Kanstas, A., Angelou, E., Nafornita, L., and Constantinou, P. (2002, January 18). Applications of generalized RBF-NN for path loss prediction. Proceedings of the 13th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, Pavilhao Altantico, Lisboa, Portugal.
13. Bhuvaneshwari, A., Hemalatha, R., and Satyasavithri, T. (2016, January 9–11). Performance evaluation of Dynamic Neural Networks for mobile radio path loss prediction. Proceedings of the 2016 IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics Engineering (UPCON), Varanasi, India.10.1109/UPCON.2016.7894698 ↗
14. A model to determine the propagation losses based on the integration of hata-okumura and wavelet neural models10.1155/2017/1034673 ↗
15. Cruz, H.A.O., Nascimento, R.N.A., Araujo, J.P.L., Pelaes, E.G., and Cavalcante, G.P.S. (2017, January 27–30). Methodologies for path loss prediction in LTE-1.8 GHz networks using neuro-fuzzy and ANN. Proceedings of the 2017 SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference (IMOC), Aguas de Lindoia, Brazil.10.1109/IMOC.2017.8121127 ↗
16. Salman, M.A., Popoola, S.I., Faruk, N., Surajudeen-Bakinde, N.T., Oloyede, A.A., and Olawoyin, L.A. (2017, January 29–31). Adaptive Neuro-Fuzzy model for path loss prediction in the VHF band. Proceedings of the 2017 International Conference on Computing Networking and Informatics (ICCNI), Lagos, Nigeria.10.1109/ICCNI.2017.8123768 ↗
17. Hung, K.C., Lin, K.P., Yang, G.K., and Tsai, Y.C. (2010). Hybrid support vector regression and GA/TS for radio-wave path-loss prediction. International Conference on Computational Collective Intelligence: Technologies and Applicat, Springer.10.1007/978-3-642-16693-8_26 ↗
18. Lin, K.P., Hung, K.C., Lin, J.C., and Wang, C.K. (2010). Applying least squares support vector regression with genetic algorithms for radio-wave path loss prediction in suburban environment. Advances in Neural Network Research and Applications, Springer.10.1007/978-3-642-12990-2_100 ↗
19. A new SVM-based modeling method of cabin path loss prediction
20. Uccellari, M., Facchini, F., Sola, M., Sirignano, E., Vitetta, G.M., Barbieri, A., and Tondelli, S. (2016, January 13–16). On the use of support vector machines for the prediction of propagation losses in smart metering systems. Proceedings of the 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), Vietri sul Mare, Italy.10.1109/MLSP.2016.7738887 ↗
21. Air-to-Air path loss prediction based on machine learning methods in urban environments
22. Hou, W., Shi, D., Gao, Y., and Yao, C. (2017, January 28–31). A new method for radio wave propagation prediction based on finite integral method and machine learning. Proceedings of the 2017 IEEE 5th International Symposium on Electromagnetic Compatibility (EMC-Beijing), Beijing, China.10.1109/EMC-B.2017.8260401 ↗
23. A machine-learning based connectivity model for complex terrain large-scale low-power wireless deployments10.1109/TCCN.2017.2741468 ↗
24. Chen, G.S., Wang, R.C., Lu, J.Y., and Xu, Y.R. (2018, January 2). Intelligent path loss prediction engine design using machine learning in the urban outdoor environment. Proceedings of the Sensors and Systems for Space Applications, Orlando, FL, USA.10.1117/12.2305204 ↗
25. Khalid, S., Khalil, T., and Nasreen, S. (2014, January 27–29). A survey of feature selection and feature extraction techniques in machine learning. Proceedings of the 2014 Science and Information Conference, London, UK.10.1109/SAI.2014.6918213 ↗
26. Han, H., Guo, X., and Yu, H. (2016, January 26–28). Variable selection using mean decrease accuracy and mean decrease Gini based on random forest. Proceedings of the 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS), Beijing, China.
27. Chang, C.C., and Lin, C.J. (2019, May 09). LIBSVM-A Library for Support Vector Machines. Available online: http://www.csie.ntu.edu.tw/cjlin/libsvm/.
28. A learning-based channel model for synergetic transmission technology10.1109/CC.2015.7275262 ↗
29. Kyösti, P. (2019, May 09). IST-4-027756 WINNER II D1.1.2 v1.2 WINNER II channel models. Available online: http://www.ist-winner.org/WINNER2-Deliverables/D1.1.2.zip.
30. Baum, D.S., El-Sallabi, H., Jämsä, T., and Meinilä, J. (2019, May 09). IST-2003-507581 WINNER D5.4 v1.4 Final Report on Link Level and System Level Channel Models. Available online: http://www.ist-winner.org/DeliverableDocuments/D5.4.pdf.
31. Meinila, J., Kyösti, P., Hentila, L., Jamsa, T., Suikkanen, E., Kunnari, E., and Narandzia, M.D. (2019, May 09). 5.3: WINNER+ Final Channel Models, CELTIC/CP5-026, June 2010. Available online: http://projects.celtic-initiative.org/winner+/index.html.
32. ITU-R M.2135-1 (2019, May 09). Guidelines for Evaluation of Radio Interface Technologies for IMT-Advanced. Available online: http://www.itu.int/pub/R-REP-M.2135/en.
33. Milijić, M., Stanković, Z., and Milovanović, I. (2011, January 5–8). Hybrid-empirical neural model for indoor/outdoor path loss calculation. Proceedings of the 2011 10th International Conference on Telecommunication in Modern Satellite Cable and Broadcasting Services (TELSIKS), Nis, Serbia.10.1109/TELSKS.2011.6143174 ↗
34. Popescu, I., Nikitopoulos, D., and Constantinou, P. (2006, January 25–28). Comparison of ANN based models for path loss prediction in indoor environment. Proceedings of the IEEE Vehicular Technology Conference, Montreal, QC, Canada.10.1109/VTCF.2006.43 ↗
35. Wen, J., Zhang, Y., Yang, G., He, Z., and Zhang, W. (2019). Path loss prediction based on machine learning methods for aircraft cabin environment. IEEE Access, submitted.10.1109/ACCESS.2019.2950634 ↗