Founded by two researchers from MIT, Ferveret reduces the amount of energy and water required to cool the chips that power AI.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at MIT News AI.
The paper reviews 194 papers on using artificial intelligence to optimize data center energy use, coding 63 of them. It finds that most control studies validate only in simulation, none consider water withdrawal or embodied carbon, and savings estimates overlap across methods, preventing ranking. The authors propose CLEAR‑DC, a framework that links control and workload demand through elasticity, reports net benefits, and records energy, carbon, water, embodied share, and validation venue.
The paper presents an LLM-based predictive scheduling system that forecasts execution time and energy consumption from source code, aiming to improve data center sustainability. By integrating these predictions into a real-time GPU allocation algorithm, the system reduces both energy use and queuing delays. In a collaboration with a data center, the approach achieved a 32% drop in energy consumption and a 30% reduction in waiting time.
arXiv:2608. 08761v1 Announce Type: cross Abstract: In an era defined by escalating climate change and the pervasive deployment of edge intelligence, the environmental cost of semiconductor manufacturing and operation has reached a critical threshold.
The MIT-developed tool "CrysVCD" uses AI to design new materials that are chemically stable in real-world conditions. By predicting stability early, it can significantly reduce the time and cost associated with testing and discarding unstable material designs.
arXiv:2607. 05408v1 Announce Type: cross Abstract: The environmental impact of training large language models (LLMs) is increasingly scrutinised, yet most published estimates focus on operational energy and disclose little about manufacturing (embodied) emissions, water consumption, or the underlying highperformance computing (HPC) infrastructure.
arXiv:2608. 14614v1 Announce Type: cross Abstract: As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets.