Date Time
Deep Learning Trains Buildings to Optimize Efficiency
In the United States, residential and commercial buildings account for nearly 40 percent of all energy consumption. About 40 percent of that energy use is from heating, ventilation, and air-conditioning (HVAC) systems.
An emerging efficiency method for buildings called model predictive control (MPC) could reduce HVAC energy use by up to 50 percent without impacting occupant comfort. But the method has been hampered by high costs associated primarily with software and computing.
Now, a team of scientists at Pacific Northwest National Laboratory (PNNL) has developed a new deep learning approach that uses building data and physics knowledge to train the MPC. The learning approach allows nonexperts to optimize control of a building’s energy systems without the need for additional computing power and proprietary software.
Date Time
Artificial Intelligence Ecosystem: Ethics to Exascale
Artificial intelligence, or AI, has become a household word. Once reserved for research and national security circles, AI now permeates our everyday existence.
From smart appliances and social media to medical research and electricity delivery, the applications for AI seem limitless.
In recent forums, multidisciplinary experts from Pacific Northwest National Laboratory (PNNL) joined other international leaders to discuss opportunities, as well as challenges, for the future of neural information processing-the foundation for AI.
Svitlana Volkova (top left) joined a panel with scientists from Amazon AI, Facebook, Apple, and Carnegie Mellon University to discuss the state of NLP research, as well as challenges and opportunities presented by the COVID-19 outbreak. (Image capture by Svitlana Volkova | Pacific Northwest National Laboratory.)