Kawasaki, Japan based Fujitsu Laboratories Ltd. has announced the development of high-accuracy predictive technology for such metrics as temperature and humidity to
enable energy-saving operation of air conditioning equipment in data centers. To flexibly respond to the dynamic status changes that are unique to data centers, such as moving IT equipment in and out and changing rack arrangements, the technology sequentially builds a model that predicts air conditioning effects from collected data, enabling reductions in air conditioner energy use. Existing data center air conditioning equipment operates on the basis of information from a variety of installed sensors so as to maintain the target temperature and humidity even when the operating rate of the IT equipment it contains, such  as servers, increases. When sensor data exceeds a set value, the system carries out rapid cooling for safety reasons, which causes air conditioning to operate excessively. The new technology creates a database that incorporates the status of air conditioning equipment, including the utilization rate of machines and fan speed, and has a requirement to select useful information against prediction targets, and alsoto automatically select at least one variable from the air conditioning equipment status database. By creating a model using the selected variables, this technology improves predictive accuracy by responding to the frequent changes in the state of a data center by building sequential models. A simulation using actual 100-rack scale data confirmeda reduction of about 20 percent in power consumption. Fujitsu Laboratories will conduct field trials of this technology during fiscal 2016 at data centers operated by Fujitsu  Limited. For more information, visit www.fujitsu.com/jp/group/labs/en/