Machine Learning Based Thermal Management
Background:
CPUs and TPUs generate a lot of heat
Traditional temperature sensors can not easily acquire temperature data at any given point of the cooling system. They can either:
-
measure temperature at a single point or
-
for the overall system
Goals and Objectives:
-
Develop a model for a TPU chip cooling system that takes advantage of AI vision by measuring various properties of bubbles in the flow of a water cooling system
-
Train an AI model to recognize and interpret bubble/droplet dynamics
-
Gain a better understanding of how AI works
-
Learn how to use AI in real world applications
Sponsor
- Yoonjin Won (won@uci.edu)























