곽정호 연구실

Hierarchical framework integrating Near-Real-Time (Near-RT) RIC for proactive policy orchestration and True-Real-Time (True-RT) RIC for sub-millisecond execution. Joint distribution and optimization of computing and networking resources through AI-driven xApps and dApps.

Collaborative on-device and cloud LLM inference utilizing speculative decoding for autonomous robots and vehicles. Integrates adaptive computing, networking, and LLM architecture scaling with lightweight auto-regressive generation on mobile edge devices and high-capacity verification on cloud servers.

Energy-aware LEO satellite onboard framework for integrated resource allocation. Joint control of multi-layer resources including routing, Inter-Satellite Link cooperation, inference scheduling, CPU/GPU DVFS, and battery State of Charge estimation.