Multi-Objective Optimization Software for COOLERCHIPS

The team will develop an integrated decision support software tool for the design of next-generation data centers that seamlessly links the existing open-source software for modeling reliability, energy, carbon footprint, and cost with an innovative co-simulation framework. This tool will permit data center designers to develop transformational and disruptive design advances compared to existing state-of-the-art technologies. This project is funded by ARPAe, as part of the COOLERCHIPS program. In this project, we are collaborating with other professors at UMD, NREL, LBNL, University of Arkansas, and Trane. In this project, NEIT lab team is developing a Physics informed neural network-based PDE solver to allow high fidelity 2-phase simulations to assess the performance of novel cold plates for CPUs/GPUs.