AI for industrial energy efficiency
At SMART ENERGY PLUS (SEP) 2026, held in Hall B at COEX in Samseong-dong, Seoul, on October 28, a monitor at the Electronics and Telecommunications Research Institute (ETRI) booth displayed real-time graphs showing factory equipment temperatures and operating conditions. The technology uses artificial intelligence to analyze equipment data and identify wasted energy.
ETRI introduced technologies that use AI to improve energy efficiency in factories and data centers. Rather than simply measuring electricity consumption, the focus was on analyzing equipment conditions to reduce energy consumption and improve operating efficiency.
One technology that attracted attention was the AI multisensor. It uses AI to analyze various data collected from factories and industrial facilities, including temperature, pressure and flow rate, to optimize energy use for individual pieces of equipment. Whereas conventional sensors were limited to measuring individual values, the AI multisensor combines multiple data sources to provide information needed for equipment operation.
In an application to an automotive parts hot press forming process presented by ETRI, furnace energy use fell by 23.2% and cooling system energy consumption by 32.5%. ETRI also confirmed reductions in energy consumption by drying and tentering equipment through AI use in textile dyeing processes.
Digital twin-based data center cooling
Technology to reduce electricity consumption at AI data centers was also introduced. ETRI exhibited technology that uses a digital twin to analyze data center temperatures and electricity consumption in real time and control cooling equipment.
A digital twin reproduces physical equipment in a virtual environment to analyze its operating condition. ETRI combined this with an AI-based thermal analysis model designed to predict heat generated by servers and adjust the cooling system. It also includes operational decision support using generative AI.
According to the exhibition materials, the technology aims to improve a data center's annual power usage effectiveness (PUE) by about 5% and shorten the investment payback period by two to three years. PUE is total data center electricity consumption divided by IT equipment electricity consumption, with a lower value indicating higher efficiency.
Microgrids for local power management
Technology for efficiently managing electricity supply and consumption at the local level was also unveiled. ETRI introduced microgrid operating technology that connects solar generation, an energy storage system (ESS) and the power grid in locations such as apartment complexes. It uses AI and data analysis to forecast electricity production and consumption and allocate energy resources optimally.
ETRI also presented technology that uses local generation facilities and ESS to supply electricity independently even when problems occur on the external grid. The effort aims to improve supply reliability as well as reduce electricity consumption.
Original Korean article: Money Today
English brief by Korea Wind Intelligence, koreawindintel.com
