测试时可扩展AI-RAN：无小区MIMO的推理时间分配
Test-Time Scalable AI-RAN: Inference Time Allocation for Cell-Free MIMO
浏览论文内容
中文总结 AI 辅助
本研究针对无小区MIMO系统，提出通用框架以分配测试时可扩展AI-RAN各模块的最优推理时间资源，实验验证其可充分挖掘该系统的性能潜力。
中文摘要 AI 辅助
人工智能赋能的无线接入网络（AI-RAN）预计将由多个基于AI的模块组成，这些模块可能由不同厂商独立开发。本研究聚焦AI-RAN赋能的无小区MIMO系统，重点关注现代AI模型对系统的影响，尤其关注大型语言模型（LLMs）推广的测试时可扩展性现象——即模型性能随测试时分配额外计算资源而提升。考虑到每个AI模块所需的最优额外计算资源通常取决于其与其他模块及底层无线信道的交互，我们提出一种通用框架，用于为无小区MIMO系统中每个测试时可扩展模块分配最优资源。实验结果表明，该框架能充分挖掘无小区MIMO系统中测试时可扩展AI-RAN的潜力。
英文摘要
Artificial intelligence-enabled radio access networks (AI-RANs) are envisioned to consist of multiple AI-based modules, potentially developed independently by different vendors. In this work, we study AI-RAN-enabled cell-free MIMO systems, with a particular focus on the system implications of modern AI models. Specifically, we focus on the phenomenon of test-time scalability popularized by large language models (LLMs), under which model performance improves as additional computational resources are allocated at testing time. By noting that the optimal amount of additional computational resources for each AI module should in general depend on its interaction with the other modules as well as with the underlying wireless channels, we propose a generic framework that enables optimal resource allocation for each test-time scalable module in cell-free MIMO systems. Experimental results demonstrate the effectiveness of the proposed framework in fully exploiting the potential of test-time scalable AI-RANs in cell-free MIMO systems.
