Problem
Research questions and friction points this paper is trying to address.
Generative AI
Network traffic modeling
Packet-level simulation
Burst characterization
MINT: Modeling GenAI Impact on Network Traffic
🤖 AI Summary
This study addresses the absence of measurement-driven models for generative AI (GenAI) network traffic, which hinders realistic evaluation of scheduling and capacity planning in conventional simulations. We propose the first open-source, packet-level GenAI traffic measurement and modeling framework. Multimodal large language model traffic is captured using isolated network namespaces, and burstiness characteristics are modeled via clustering techniques. Distributional fidelity is validated using the Wasserstein distance, and the resulting model is integrated into the ns-3 simulation platform. Experimental results demonstrate normalized errors of only 2%–25%, revealing pronounced asymmetry and high variability in GenAI traffic. These findings confirm that the proposed framework captures real-world burst dynamics significantly more accurately than constant-token-rate models.
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Generative AI traffic modeling
Packet-level simulation
Burst structure analysis
Measurement-driven framework
ns-3 validation
🔎 Similar Papers
No similar papers found.
