UAV-gNB control system integrates aerial placement with per-user scheduling

Researchers have developed a hierarchical control system for tethered mmWave UAV-gNBs that integrates aerial placement with per-user scheduling. This system utilizes O-RAN disaggregation and a multi-timescale RIC architecture. A Non-Real-Time RIC rApp manages UAV placement and slice budgets, while a Near-Real-Time RIC xApp handles per-user resource allocation using a permutation-equivariant DeepSets Soft Actor-Critic scheduler. This approach significantly improves eMBB SLA satisfaction and URLLC on-time delivery compared to existing methods. AI

影响 This research could lead to more efficient and reliable mobile network coverage in challenging environments.

排序理由 Academic paper detailing a novel control system for UAV-gNBs. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Alireza Mohammadhosseini
• DeepSets Soft Actor-Critic
• mmWave
• O-RAN
• UAV-gNB

• 论文
• 基础设施

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →