Research
Research Overview
I am a networking researcher committed to advancing digital equity through principled system design.
My north star is clear:
Access to a secure, performant, and affordable Internet must become a durable infrastructure guarantee–not a function of geography, income, or institutional capacity.
Realizing this goal requires more than faster protocols or incremental optimizations. It requires validated data systems that make digital infrastructure measurable, accountable, and intelligently operable.
My research develops the architectural foundations for this transformation — spanning public-interest broadband infrastructure and agentic, AI-powered network operations.
Path I — Public-Interest Broadband Data Infrastructure
Digital equity demands decision-grade visibility into broadband markets.
My work advances both the intellectual foundations and the operational infrastructure required to measure affordability, competition, and performance at scale.
Central to this effort is:
Broadband Query Tool (BQT / BQT+) — an address-level broadband pricing and availability intelligence platform enabling reproducible analysis of market structure and affordability.
BQT has informed regulatory and policy discussions across states and agencies, shaping how competition and pricing are evaluated in large-scale funding and oversight decisions. The broader vision is articulated in:
BQT+ advances this platform through agentic system design: decomposing complex ISP interaction processes into reusable, adaptive components that scale across providers while preserving methodological rigor.
BQT/BQT+ has enabled a series of research contributions grounded in rigorous measurement and statistical modeling:
- Contextualizing Speed Test Measurements (IMC 2022, Distinguished Paper Award) — establishing principled modeling of user-perceived performance.
- Decoding the Divide (SIGCOMM 2023) — introducing address-level broadband pricing measurement for rigorous market analysis.
- Assessing the Efficacy of the Connect America Fund (SIGCOMM 2024, ANRP Award) — scalable methodologies for extracting and synthesizing ISP plan data across heterogeneous interfaces.
We are extending this foundation through:
NetVibe — an evolving longitudinal latency intelligence platform that connects infrastructure-level performance measurements with user-level experience.
Together, this body of work establishes independent broadband data ecosystems grounded in statistical modeling, systems research, and reproducible infrastructure — capable of informing billion-dollar investment decisions and regulatory accountability.
Path II — Agentic and AI-Powered Network Operations (AIOps)
Digital equity also requires operational intelligence: networks that adapt, generalize, and remain trustworthy under dynamic conditions.
My group advances agentic and AI-powered network operations grounded in controllable data generation, structured representation learning, and principled validation.
Programmable Data Substrate
We are building a programmable experimentation infrastructure that enables scalable and verifiable network research:
- netUnicorn — distributed orchestration across heterogeneous environments.
- NetReplica — an evolving bottleneck-aware emulation framework for controlled experimentation.
- NetGent — an agentic workflow automation system that compiles high-level specifications into deterministic, reusable execution pipelines.
These systems share a central architectural insight: complex operational tasks become reliable and scalable when decomposed into smaller, verifiable components — a principle mirrored in BQT+.
Network Foundation Models and Validation
Building on this substrate, we introduced:
- netFound — a domain-specific network foundation model that learns spatial, temporal, and hierarchical structure directly from packet-level telemetry.
- NetBurst — ongoing modeling of bursty, event-driven network dynamics for improved temporal abstraction and forecasting.
- Intrinsic Evaluation Framework (NeurIPS 2025) — a representation-level validation methodology decoupling embedding quality from downstream task artifacts.
- Trustee (ANRP recognition) — advancing interpretability and structured introspection for learning-based network systems.
This program establishes validated foundations for agentic and AI-powered network operations that are robust, generalizable, and deployment-aware.
Deployment and Engagement
We actively engage with the Energy Sciences Network (ESnet) to explore how AIOps frameworks can support large-scale scientific infrastructure — advancing adaptive traffic management, scalable telemetry analysis, and AI-driven operational intelligence in production environments.
Representative Systems
- BQT / BQT+ — broadband plan querying tool
- NetVibe — evolving longitudinal latency intelligence platform
- netUnicorn — distributed orchestration platform
- netFound — network foundation model
- NetBurst — event-centric forecasting system
- NetReplica — evolving bottleneck-aware emulation framework
- NetGent — agentic workflow automation system
- Intrinsic Evaluation Framework — representation analysis for network foundation models
- Trustee — interpretability framework for ML-based network systems
Funding
The research in my group is supported by various government agencies, namely, the National Science Foundation (NSF), the Department of Energy (DoE), as well as different network/content service providers such as Google, Verizon Innovations, ViaSat, and vendors including Intel and Cisco.