MINT：对生成式AI网络流量影响的建模
MINT: Modeling GenAI Impact on Network Traffic
- Rensselaer Polytechnic Institute（伦斯勒理工学院）
- Samsung Research America（三星美国研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MINT提出首个基于测量的GenAI流量建模框架，通过隔离捕获管道收集多模态轨迹，揭示突发特性并验证于ns-3，为网络模拟提供现实模型。
AI中文摘要：
生成式AI（GenAI）正成为主流网络工作负载，然而数据包级模拟器缺乏基于测量的GenAI流量模型。目前，研究人员必须使用传统来源（如文件传输和视频流）来近似GenAI服务，这限制了调度和容量规划的现实网络评估。我们提出MINT，一个用于GenAI网络流量的测量和建模框架。利用隔离的网络命名空间捕获管道，我们从三个LLM提供商、四种模态、云和边缘服务器以及有线和无线网络接入点收集客户端侧轨迹。我们发现GenAI模态表现出与传统应用不同的上传/下载不对称性和突发结构。MINT对这些突发状态进行聚类和建模，并在ns-3中验证了经验突发时序分布行为，归一化Wasserstein距离为2–25%。我们的结果还揭示，实际数据包突发比恒定令牌生成器模型具有显著更大的变异性。MINT开源了首个用于数据包级网络模拟的基于测量的GenAI流量模型。
英文摘要：
Generative AI (GenAI) is becoming a mainstream network workload, yet packet-level simulators lack measure\-ment-driven GenAI traffic models. Currently researchers must approximate GenAI services using traditional sources such as file transfer and video streaming, limiting realistic network evaluation of scheduling and capacity planning. We present MINT, a measurement and modeling framework for GenAI network traffic. Using an isolated net\-work-namespace capture pipeline, we collect client-side traces from three LLM providers across four modalities, cloud and edge servers, and wired and wireless network access points. We find that GenAI modalities exhibit distinct upload/download asymmetry and burst structures that differ from traditional applications. MINT clusters and models these burst regimes and validate empirical burst timing distribution behavior in ns-3 with normalized Wasserstein distances of 2--25\%. Our results also reveal that realistic packet bursts have significantly more variability than constant token generator models. MINT open-sources the first measurement-driven GenAI traffic model for packet-level network simulation.
