[Description]

Development and performance analysis of power and channel allocation strategies with beam sweeping for satellite communication networks. We design adaptive methods that select beam direction/schedule, allocate transmit power, and assign channels under time-varying links to improve throughput, coverage, and interference robustness.

[Achievement]

• [SCIE] Y. Cho, W. Yang, D. Oh, and H.-S. Jo, "Multi-Agent Deep Reinforcement Learning for Interference-Aware Channel Allocation in Non-Terrestrial Networks," IEEE Communications Letters, vol. 27, no. 3, pp. 936-940, March 2023. 

• [Patent] System and Method for Channel Allocation of Low Earth Orbit Satellites (App. No. 10-2025-0115429)

[Description]

Development and performance analysis of multi-agent AI that autonomously and jointly performs spectrum allocation, interference management, and congestion control to enable network recovery and reconfiguration.

[Achievement]

• [Project] Phase 2 Research Project of Specialized Research Laboratory for Space-Tier Intelligent Communication Networks (2026-2028) 

[Description]

We conduct interference analysis for satellite communication networks by modeling and quantifying aggregate interference from coexisting systems under realistic deployment and propagation conditions. Based on metrics such as I/N and SINR, we evaluate protection criteria compliance and derive insights to support spectrum sharing, interference mitigation, and reliable network operation.

[Achievement]

• [SCIE] Y. Cho, H.-K. Kim, M. Nekovee, and H.-S. Jo, "Coexistence of 5G With Satellite Services in the Millimeter-Wave Band," IEEE Access, vol. 8, pp. 163618-163636, 2020.

• [KCI] B.-H. Jang, D. Lee, Y. Kim, Y. Cho, and H.-S. Jo, "Interference Analysis between IMT-2030 and Low Earth Orbit Satellite Services Using Phased Array Antennas and Multi-User Beamforming," The Journal of Korean Institute of Electromagnetic Engineering and Science, vol. 36, no. 11, pp. 1043-1054, Nov 2025.

• [Copyright] Simulator for Radio Interference between Satellite and Other Wireless Services (Registration No. 111171-0007522)

[Description]

Accurate path loss modeling is a fundamental requirement for efficient wireless network design, interference analysis, and coverage optimization. Traditional statistical and empirical models—such as Modified Hata and ITU-R P.2108—often face limitations in capturing the complex propagation dynamics of high-density urban and residential environments due to their simplified physical assumptions. To address these challenges, this research develops data-driven path loss prediction models leveraging deep learning architectures. By training on empirical measurement data integrated with environmental context, such as building density and terrain features, the proposed models achieve significantly higher explanatory power and superior predictive precision (MSE) compared to conventional methods across diverse urban scenarios.


[Achievement]

• [Int'l Conf.] D. Lee, T. Nam, J. G. Yook, and H.-S. Jo, “Data-Driven Path Loss Modeling Using Multilayer Perceptron Networks,” International Conference on Artificial Intelligence in Information and Communication (ICAIIC).

• [Int'l Journal] H.-S. Jo, C. Park, E. Lee, H. K. Choi, J. Park, "Path Loss Prediction based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process," Sensors, 20(7), 1927, March 2020.