Research

Research systems built for practical networking deployments.

Learning-based Deployment-focused

Maestro

QoE-aware dynamic resource allocation in Wi-Fi networks using telemetry-driven QoE estimation and RL-based flow control.

Wi-Fi resource management QoE-focused Multi-agent RL

LSTM-based QoE estimator that relies solely on controller telemetry—no client modifications.
DDQN multi-agent policy that jointly selects access category and traffic priority per flow.
Evaluated on an enterprise Wi-Fi 6 testbed with up to 25× QoE gains over WMM and up to 69% over QFlow.