Ann. N.Y. Acad. Sci. ISSN 0077-8923 ANNALS OF THE NEW YORK ACADEMY OF SCIENCES Issue: The Implications of a Data Driven–Built Environment Applying science and mathematics to big data for smarter buildings Young M. Lee, Lianjun An, Fei Liu, Raya Horesh, Young Tae Chae, and Rui Zhang Business Analytics and Mathematical Sciences, IBM Research, Yorktown Heights, New York Address for correspondence:Young M. Lee, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. ymlee@us.ibm.com Many buildings are now collecting a large amount of data on operations, energy consumption, and activities through systems such as a building management system (BMS), sensors, and meters (e.g., submeters and smart meters). However, the majority of data are not utilized and are thrown away. Science and mathematics can play an important role in utilizing these big data and accurately assessing how energy is consumed in buildings and what can be done to save energy, make buildings energy efficient, and reduce greenhouse gas (GHG) emissions. This paper discusses an analytical tool that has been developed to assist building owners, facility managers, operators, and tenants of buildings in assessing, benchmarking, diagnosing, tracking, forecasting, and simulating energy consumption in building portfolios. Keywords: buildings; energy; data; performance; analytics Introduction Energy consumption by humans causes a grad- ual increase in concentrations of greenhouse gas (GHG) in the Earth’s atmosphere and is consid- ered to be the main source of global warming. 1 In the United States, 40% of the nation’s total energy consumption is due to commercial and residential buildings, 2 and this figure is constantly increasing. Such buildings also contribute 45% of the coun- try’s GHG emissions. 3 The majority of the world’s population either lives or works in buildings; there- fore, everybody has a responsibility and a role to play in reducing energy consumption, controlling GHG emissions, and confronting climate change and its potential impacts. End-use energy efficiency can contribute to more than 50% of total global energy conservation. 4 Saving energy, improving energy efficiency, and reducing GHG emissions are key initiatives for many cities, municipalities, building owners, and opera- tors. For example, the New York City (NYC) govern- ment spends over $1 billion/year on energy for their approximately 4000 buildings (e.g., public schools, prisons, court houses, administrative buildings, and waste water treatment plants) and is committed to reducing the City government’s energy consump- tion and carbon dioxide (CO 2 ) emissions by 30% by 2017 from their 2005 levels through an initia- tive called PlaNYC. 5 NYC plans to invest, each year, an amount equal to 10% of its energy expenses in energy-saving measures over the next 10 years. The largest segment of NYC government buildings is the 1,200 K–12 public schools serving 1.1 million stu- dents and covering about 150 million square feet. The NYC Department of Education was interested in understanding how energy efficient their build- ings were and what could be done to make the build- ings more energy efficient. In order to reduce energy consumption in buildings, however, one needs to understand pat- terns of energy usage and heat transfer as well as characteristics of building structures, opera- tions, and occupants’ behavior that influence energy consumption. This understanding can be aided through development of scientific models that are based on physics, mathematics, and statistics. These models can then be used to simulate the impact of possible changes that can be made to build- ings regarding energy consumption, energy costs, and GHG emissions, and provide decision support for making buildings more energy efficient. The doi: 10.1111/nyas.12193 18 Ann. N.Y. Acad. Sci. 1295 (2013) 18–25 C  2013 New York Academy of Sciences.