ABSTRACT
Radio propagation models can predict the spatial distribution and strength of radio signals by simulating their propagation characteristics over coverage areas. Since the empirical propagation model with fixed structure is not suitable for complex environments due to its low prediction precision, and the ray tracing propagation model brings high cost for geographic scenario modeling, this paper proposes a data-driven radio propagation model based on machine learning. The model's input features are extracted following Non-Line-of-Sight propagation of radio signals, the scenario-spanning model structure is designed using XGBoost, and the model is trained with driving test data. We used practical measurement data collected in urban areas to evaluate the model, and it is demonstrated that the root mean square error of model prediction is no more than 10.33dB. The prediction accuracy of the proposed propagation model is better than that of empirical ones. Moreover, its prediction performance is close to that of ray tracing models, while its modeling cost is lower than that of ray tracing ones. Therefore, this model is a feasible and efficient approach for radio prediction in complex urban environment.
- T. S. Rappaport, “Radio communications : principles and practice. Second Edition,” Publishing House of Electronics Industry, Beijing, 2013, ISBN: 2013-02-01.Google Scholar
- T. S. Rappaport, Y. Xing, G. R. MacCartney, A. F. Molisch, E. Mellios and J. Zhang, “Overview of millimeter wave communications for fifth-generation (5G) radio networks—with a focus on propagation models,” IEEE Transactions on Antennas and Propagation, vol. 65, Aug. 2017, pp. 6213-6230, doi:10.1109/ TAP. 2017.2734243.Google ScholarCross Ref
- J. Yin, W. Miao, W. Ye, J. Teng, C. Jiang, and R. Liu, “Interference identification in smart grid communications,” World Wide Web, vol. 22, Sep. 2019,pp.2177-2207,doi:10.1007/s11280-018-0589-7.Google ScholarDigital Library
- C. Müller, H. Georg, M. Putzke and C. Wietfeld, "Performance analysis of radio propagation models for Smart Grid applications," 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm), Brussels, 2011,pp.96-101,doi:10.1109/SmartGridComm.2011.6102400.Google Scholar
- T. Jiang, W. Ye, J. Yin, S. Xiong and H. Jin, "Localization of Interference Sources in LTE Mobile Networks," 2019 4th International Conference on Communication and Information Systems (ICCIS), Wuhan, China, 2019, pp. 134-140, doi: 10.1109/ICCIS49662.2019.00031.Google Scholar
- HAGERLING C, IDE C, WIETFELD C. Coverage and capacity analysis of radio M2M technologies for smart distribution grid services[C]//IEEE Smart Grid Communications, Nov. 3-6, 2014, Venice, Italy: 368-373. DOI: 10.1109/SmartGridComm.2014.7007674Google Scholar
- Hussain S , Brennan C . An efficient ray tracing method for propagation prediction along a mobile route in urban environments[J]. Radio ence, 2017, 52(7-8):862-873.Google Scholar
- Ling Li and L. Carin, "Multilevel fast multipole calibration of ray models with application to wireless propagation," in IEEE Transactions on Antennas and Propagation, vol. 52, no. 10, pp. 2794-2800, Oct. 2004, doi: 10.1109/TAP.2004.834623.Google ScholarCross Ref
- LANCIA P, TENNINA S, GRAZIOSI F, Efficient urban coverage for relay aided smart energy radio networks[C]//IEEE Computer Aided Modeling and Design of Communication Links and Networks, June. 19-21, 2017, Lund, Sweden: 1-5. DOI: 10.1109/CAMAD.2017.8031647.Google Scholar
- LI L, CARIN L. Multilevel fast multipole calibration of ray models with application to radio propagation[J]. IEEE Transactions on Antennas and Propagation, 2004, 52(10): 2794–2800. DOI: 10.1109/TAP.2004.834623.Google ScholarCross Ref
- Siqueira G.L.,Dal Bello J.C.R.,Bertoni H.L..Theoretical analysis and measurement results of vegetation effectson path loss for mobile cellular communication systems[J].IEEE Transactions on Vehicular Technology,2000,49(4).Google Scholar
- MATHAR R, REYER M, SCHMEINK M. A cube oriented ray launching algorithm for 3D urban field strength prediction[C]// IEEE Communications, June 24-28, 2007, Glasgow, Scotland: 5034-5039. DOI: 10.1109/ICC.2007.831.Google Scholar
- Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016Google Scholar
- Sinha N K. Developing A Web based System for Breast Cancer Prediction using XGboost Classifier[J]. International Journal of Engineering and Technical Research, 2020, V9(6).Google Scholar
- Gumus M, Kiran M S. Crude oil price forecasting using XGBoost[C]// International Conference on Computer Science and Engineering. 0.Google Scholar
- Oughali M S, Bahloul M, Rahman S A E. Analysis of NBA Players and Shot Prediction Using Random Forest and XGBoost Models[C]// 2019 International Conference on Computer and Information Sciences (ICCIS). 201Google Scholar
Recommendations
A 3-D indoor radio propagation model for WiFi and RFID
MobiWac '11: Proceedings of the 9th ACM international symposium on Mobility management and wireless accessProliferation of indoor sensor infrastructure has created a new niche for communications technology to exploit, yet research in this field has not produced a pervasive dynamic indoor location system which utilizes this latent resource. Studies employing ...
An indoor radio propagation model considering angles for WLAN infrastructures
Wireless local area network fingerprint-based indoor location system is a hot topic these years because it needs no extra hardware and is very easy to deploy. However, it demands a database containing the distribution of received signal strength RSS of ...
Tuning of Empirical Radio Propagation Models Effect of Location Accuracy
The paper summarises tuning of empirical propagation model RX-level predictions to measurements. An algorithm using least-squares fit of predictions to measurements is discussed. The algorithm uses the Condition number of the resulting equations to ...
Comments