Uhana is an exciting start up out of Stanford that is leveraging AI for mobile network optimization and slicing. The company has built a real-time deep learning engine that is being used to optimize network operations and application quality of experience by multiple tier one network operators around the world.
The Uhana AI engine is deployed in operator private clouds or public cloud infrastructure. The AI pipeline begins by ingesting real-time telemetry from many sources, including the mobile network infrastructure and applications. The real-time telemetry data is combined with operator policies and joined with other inputs, then processed through application specific neural networks. The neural networks deliver real-time, predictive guidance that is used to optimize application QoE and network operations.
A recent article highlighting Uhana’s AI-optimized control guidance here.
Uhana’s AI engine leverages deep reinforced learning, so the system learns how networks and applications can be controlled, then provides AI-optimized control guidance via an API. The guidance can be manually implemented or leveraged programmatically for closed loop automation. For the first time, application developers now have an API to access accurate, fine-grained network intelligence and predictive “what-if” modeling. Finally, a programmable network connectivity layer, which optimizes QoE for subscribers, increases CAPEX efficiency for operators and provides a foundation for new revenue generation.
A recent interview by Senza Fili Analyst, Monica Paolini with Sachin Katti the Founder of Uhana here.
If you are interested in learning more about how Uhana can help your team, contact us.
If you want to become part of our team in Palo Alto, CA, check out our open positions.