Researchers at Drexel University in Philadelphia have developed a way to use machine learning to aid energy reduction strategies in an urban setting.
In a study, Performance evaluation of deep learning architectures for load and temperature forecasting under dataset size constraints and seasonality, the researchers at the university’s College of Engineering detailed the machine learning model they developed to help predict how energy consumption will change as urban neighborhoods evolve.
“For Philadelphia in particular, neighborhoods vary so much from place to place in prevalence of certain housing features and zoning types that it’s important to customize energy programs for each neighborhood, rather than trying to enact blanket policies for carbon reduction across the entire city or county,” Simi Hoque, a professor in the College of Engineering who led machine learning research for granular energy-use modeling, said in a statement.
In 2017, Philadelphia set a goal of becoming carbon dioxide neutral by 2050, led in large part by a reduction in greenhouse gas emissions from building energy use, which accounted for nearly three-quarters of Philadelphia’s carbon dioxide footprint at the time.
Existing machine learning programs, properly deployed, can provide some clarity on how zoning decisions could affect future greenhouse gas emissions from buildings, Hoque said. “Right now there is a huge volume of energy use data, but it’s often just too inconsistent and messy to be reasonably put to use,” he said. For example, he said, a dataset corresponding to certain housing characteristics may have usable energy estimates, but another dataset corresponding to socioeconomic features could be missing too many values to be usable. “Machine learning is well equipped to handle this challenge,” he said.
Hoque and his team developed a process using two machine learning programs, one that can tease out patterns from massive data sets and use them to make projections about future energy and a second that can pinpoint the details in the model that likely had the greatest effect on changing the projections.
In addition to establishing sustainable energy use practices for current buildings, the researchers said the model can also be used to incorporate energy use projections into zoning decisions that can inform future development.
The researchers tested the model by providing input data from a hypothetical scenario proposed by the Delaware Valley Regional Planning Commission that estimated continuing economic development in Philadelphia through the year 2045.
Looking at residential energy use for the 2045 scenario, the program suggested that six of the 11 areas would decrease their energy use – mostly lower-income regions. While mixed-income regions would likely see an increase in energy use.
“Overall, the residential energy prediction model finds that features related to lower building intensity relate to lower energy consumption estimates in the model, for example lower lot acreage, lower number of rooms per unit,” they wrote. “These results give reason to reinvestigate the effects of upzoning policies, commonly present as an affordable housing solution in Philadelphia and other cities across the U.S., and subsequent changes in energy use for these areas.”
“With respect to the commercial sector, the study suggests that commercial buildings in the top quantiles of square footage and employee count should be the primary targets for energy reduction programs,” the authors said. “The research posits an approximate threshold of 10,000 square feet of total building area, with buildings over that marker being prioritized due to their disproportionate influence on the energy prediction of the model.”
The researchers said more testing is necessary and the program will improve as more data becomes available. The next step for the research would be to analyze areas of Philadelphia with known high energy use to better understand the factors contributing to that high use.
