Automated decision support system for optimizing the selection of green building measures

Buildings in the United States account for 72% of electricity consumption, 40% of energy consumption, 13% of water consumption, 39% of carbon footprint, and 30% of waste output. In order to minimize these negative environmental impacts, many public and private owners are requesting that their buildings be more sustainable and certified under the widely known programs such as leadership in energy and environmental design for existing buildings (LEED-EB). To accomplish this, buildings are increasingly integrating green building measures including energy efficient lighting, motion sensors, thermal pane glass, geothermal heat pumps, EnergyStar rated HVAC systems, photovoltaic systems, and wind turbines. This research paper presents the development of an automated decision support system (DSS) that is designed to optimize the selection of green building measures which can be used to upgrade existing buildings. The developed DSS incorporates two optimization models that are capable of (i) minimizing the total upgrade costs required to accomplish a specified LEED-EB certification level such as silver or gold; and (ii) maximizing the number of accredited LEED-EB points within a specified budget of upgrade costs. The DSS is designed to identify a set of optimal upgrade decisions that accomplishes these two optimization objectives. An application example is used to illustrate the capabilities of the DSS and to validate its result.