Skip to content
Log in

Author

Jinho Choi

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

2026

Active or Passive STAR-RIS-Assisted ISAC-NOMA: A Unified Approach

This paper investigates a downlink integrated sensing and communication (ISAC) system utilizing non-orthogonal multiple access (NOMA), empowered by an active simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) operating in energy splitting mode. We maximize the communication sum rate subject to per-user quality-of-service constraints, target sensing requirements, and practical active STAR-RIS hardware constraints. The proposed formulation is further generalized to a unified framework covering active/passive STAR-RIS architectures and NOMA/space-division multiple access schemes. To solve the resulting highly non-convex problem, we develop a computationally efficient optimization framework that alternately optimizes the base station transmit beamforming and STAR-RIS beamforming by introducing a common set of auxiliary variables, thereby accelerating convergence in solving the subproblems. We also develop a worst-case robust design under norm-bounded channel state information (CSI) uncertainty, where the uncertain rate expressions are replaced with tractable conservative bounds. Simulation results show that the proposed algorithm converges much faster than fractional programming-based benchmarks, and that the active STAR-RIS assisted NOMA achieves the best performance under various system constraints. The results also demonstrate the resilience of the proposed robust design against CSI errors, while revealing that excessive active amplification may degrade the achievable sum rate under practical nonlinear amplifier distortion.

Noureen Khan, Muhammad Rehman, Jinho Choi et al. · 0 citations
2026

Structured Reinforcement Learning for User Admission in Multi-Cell Massive MIMO via O-RAN

Artificial intelligence (AI) and machine learning (ML) are increasingly applied to wireless and cellular networks. With sixth-generation (6G) systems envisioned as AI-native, reinforcement learning (RL) offers a natural approach to complex network management and operation. This paper focuses on user admission control in multi-cell massive multiple-input multiple-output (MIMO) systems, where naive selfish strategies aiming to maximize local sum-rate can trigger a tragedy of the commons, degrading per-user performance and generating severe inter-cell interference (ICI). To address these challenges, we introduce a structured RL framework for massive MIMO systems. In particular, the policy is structured to introduce physical inductive bias terms, such as an interference-sensitive attenuation factor, which enables interference-aware learning through the open radio access network (O-RAN) architecture. Through stability analysis, we show that such physical inductive bias terms can guarantee network-wide stability. Experimental results demonstrate that the proposed approach balances aggregate spectral efficiency with per-user performance and maintains robustness during traffic surges, whereas selfish strategies suffer from degraded per-user performance.

Jinho Choi · 0 citations