Vertiv, formerly Emerson Network Power, has unveiled machine learning software for improving cooling system reliability, efficiency and system lifespan in the data center.
The Liebert iCOM Autotuning software works with select Liebert cooling systems installed in North America.
The system regulates Liebert Direct Expansion (DX) compressors or chilled water valves to stabilize airflow and temperature.
With DX systems, the company said that it harmonizes compressors, fans and condensers to eliminate costly short cycling. With chilled water systems, it eliminates rapid fluctuations in valve positions, known as ‘valve hunting,’ to balance fan speeds, water temperature and flow rates.
Vertiv claims that this brings efficiency gains of up to 15 percent, and increases the lives of compressors and chilled water valves by up to 20 percent.
“The introduction of Liebert iCOM Autotuning marks a new level of controls available to operators of data centers and other mission critical operations” John Peter Valiulis, VP of North America thermal management marketing at Vertiv, said.
“It’s part of wave of technology we are introducing to enhance energy efficiency and provide the highest level of protection for mission critical operations.”
Other companies have also sought to bring machine learning to the data center - among them is Google, which claimed it cut its PUE by 15 percent using its DeepMind AI system, Cisco, which last year launched its data center “time machine,” and Romonet, which patented its machine learning analytics platform last summer.