研究人员开发了一种新颖的双智能体（DA）深度学习框架，旨在借助可重构智能表面（RIS）优化跟踪功率受限移动用户的能效。该方法集成了神经进化和监督学习，可实时联合管理RIS相位配置文件和用户发射功率，克服了离散相位响应和单比特反馈的挑战。数值模拟表明，在跟踪和静态定位场景中，DA框架在跟踪和静态定位方面均显著优于卡尔曼滤波器、粒子滤波器和传统指纹识别方案等现有方法。 AI
影响 该框架通过优化资源分配，有望实现更节能的无线通信系统。
排序理由 这是一篇详细介绍针对特定技术问题的深度学习新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.00056v1 Announce Type: cross Abstract: This paper studies energy efficient tracking of power-limited mobile users with the assistance of a Reconfigurable Intelligent Surface (RIS). Since localization pilot transmissions dominate the energy budget of power-constrained d…
This paper studies energy efficient tracking of power-limited mobile users with the assistance of a Reconfigurable Intelligent Surface (RIS). Since localization pilot transmissions dominate the energy budget of power-constrained devices, we introduce a low-overhead feedback link …
This paper studies energy efficient tracking of power-limited mobile users with the assistance of a Reconfigurable Intelligent Surface (RIS). Since localization pilot transmissions dominate the energy budget of power-constrained devices, we introduce a low-overhead feedback link …