volume | PIER Journals

Abstract

Optimizing indoor transmitter placement via 3D ray-tracing is computationally intensive. To overcome this limitation, this study proposes an efficient method that integrates geometry-informed line-of-sight (LoS) pre-analysis with Bayesian optimization (BO). A boundary-line-based 2D occupancy grid is generated from CAD drawings to prevent the loss of vertical structures, and LoS scores for all 770 Tx candidate locations are obtained in approximately 3 s, including all preprocessing of the CAD geometry, without ray-tracing simulation. Spatially distributed candidates with high LoS scores are selected as initial points for BO to improve search efficiency and surrogate model accuracy. Simulation results in a smart factory environment show that the proposed method avoids local optima pitfalls of randomly initialized BO and reaches the global optimum in only 37 evaluations (5.9 h). This achieved a 33% reduction in search time compared to Particle swarm optimization (PSO) and up to 69% compared to the grey wolf optimizer (GWO) while finding the identical global optimum, demonstrating superior efficiency for computationally expensive propagation environments.

1. Wu, Yulei, Hong-Ning Dai, Haozhe Wang, Zehui Xiong, and Song Guo, "A survey of intelligent network slicing management for industrial IoT: Integrated approaches for smart transportation, smart energy, and smart factory," IEEE Communications Surveys & Tutorials, Vol. 24, No. 2, 1175-1211, 2022.
doi:10.1109/comst.2022.3158270 Google Scholar

2. Yun, Zhengqing, Sungkyun Lim, and M. F. Iskander, "An integrated method of ray tracing and genetic algorithm for optimizing coverage in indoor wireless networks," IEEE Antennas and Wireless Propagation Letters, Vol. 7, 145-148, 2008.
doi:10.1109/lawp.2008.919358 Google Scholar

3. Reza, Ahmed Wasif, Md. Sumon Sarker, and Kaharudin Dimyati, "A novel integrated mathematical approach of ray-tracing and genetic algorithm for optimizing indoor wireless coverage," Progress In Electromagnetics Research, Vol. 110, 147-162, 2010.
doi:10.2528/pier10091701 Google Scholar

4. El-Maghrabi, Hany M., "A standard ray tracing technique for predicting signal strength of wireless sensor network in smart building," Progress In Electromagnetics Research Letters, Vol. 105, 79-84, 2022.
doi:10.2528/pierl22052504 Google Scholar

5. Gopal, Govind R. and Bhaskar D. Rao, "Vector quantization methods for access point placement in cell-free massive MIMO systems," IEEE Transactions on Wireless Communications, Vol. 23, No. 6, 5425-5440, June 2024.
doi:10.1109/twc.2023.3326453 Google Scholar

6. Seretis, Aristeidis, Charley Xu, and Costas Sarris, "Fast selection of indoor wireless transmitter locations with generalizable neural network propagation models," IEEE Transactions on Antennas and Propagation, Vol. 72, No. 10, 7927-7940, October 2024.
doi:10.1109/tap.2024.3439826 Google Scholar

7. Kennedy, J. and R. Eberhart, "Particle swarm optimization," Proceedings of ICNN'95 --- International Conference on Neural Networks, Vol. 4, 1942-1948, Perth, WA, Australia.
doi:10.1109/icnn.1995.488968

8. Kim, J., Y. Lee, and S. Oh, "Optimal transmitter placement in indoor environments considering delay spread and received power," Proceedings of The International Workshop on Future Technology, 39-44, 2025.

9. Mirjalili, Seyedali, Seyed Mohammad Mirjalili, and Andrew Lewis, "Grey wolf optimizer," Advances in Engineering Software, Vol. 69, 46-61, March 2014.
doi:10.1016/j.advengsoft.2013.12.007 Google Scholar

10. Wang, Fasong, et al., "OIRS-assisted NLoS visible light positioning: An improved GWO dual-feature fusion approach for SISO systems," IEEE Internet of Things Journal, Vol. 13, No. 1, 906-917, January 2026.
doi:10.1109/jiot.2025.3626506 Google Scholar

11. Shahriari, Bobak, Kevin Swersky, Ziyu Wang, Ryan P. Adams, and Nando de Freitas, "Taking the human out of the loop: A review of Bayesian optimization," Proceedings of the IEEE, Vol. 104, No. 1, 148-175, January 2016.
doi:10.1109/jproc.2015.2494218 Google Scholar

12. Sato, Koya and Katsuya Suto, "Bayesian optimization framework for channel simulation-based base station placement and transmission power design," IEEE Networking Letters, Vol. 6, No. 4, 217-221, December 2024.
doi:10.1109/lnet.2024.3469175 Google Scholar

13. Sharma, Gourav Prateek, Durgesh Singh, and James Gross, "Robust base station placement in agricultural IoT via bayesian optimization," 2026 International Conference on Signal Processing and Communications (SPCOM), 1-5, Bangalore, India, July 2026.
doi:10.1109/spcom71105.2026.11623032

14. Shiroya, P. A., A. Ashtekar, S. Shashidhar, and M. E. Eltayeb, "Refined bayesian optimization for efficient beam alignment in intelligent indoor wireless environments," arXiv:2512.00036, 2025.
doi:10.48550/arXiv.2512.00036 Google Scholar

15. Jones, Donald R., Matthias Schonlau, and William J. Welch, "Efficient global optimization of expensive black-box functions," Journal of Global Optimization, Vol. 13, No. 4, 455-492, December 1998.
doi:10.1023/a:1008306431147 Google Scholar

16. McKay, M. D., R. J. Beckman, and W. J. Conover, "A comparison of three methods for selecting values of input variables in the analysis of output from a computer code," Technometrics, Vol. 21, No. 2, 239-245, May 1979.
doi:10.2307/1268522 Google Scholar

17. Rasmussen, C. E. and C. K. I. Williams, Gaussian Processes for Machine Learning, MIT Press, Cambridge, MA, 2006.

18. Snoek, J., H. Larochelle, and R. P. Adams, "Practical bayesian optimization of machine learning algorithms," Vol. 25, Advances in Neural Information Processing Systems, 2012.

Dr. Sejin Kim

Dr. Seungchan Lee

Prof. In-Sik Choi

Prof. Seongwon Oh