A data-driven predictive model of city-scale energy use in buildings

Abstract

Many cities across the United States have turned to building energy disclosure (or benchmarking) laws to encourage transparency in energy efficiency markets and to support sustainability and carbon reduction plans. In addition to direct peer-to-peer comparisons, the benchmarking data published under these laws have been used as a tool by researchers and policy-makers to study the distribution and determinants of energy use in large buildings. However, these policies only cover a small subset of the building stock in a given city, and thus capture only a fraction of energy use at the urban scale. To overcome this limitation,. we develop a predictive model of energy use at the building, district, and city scales using training data from energy disclosure policies and predictors from widely-available property and zoning information. We use statistical models to predict the energy use of 1.1 million buildings in New York City using the physical, spatial, and energy use attributes of a subset derived from 23,000 buildings required to report energy use data each year. Linear regression, random forest, and support vector regression algorithms are fit to the city's energy benchmarking data and then used to predict electricity and natural gas use for every property in the city and model accuracy is assessed and validated at the building level and zip code level using actual consumption data from calendar year 2014. We find the OLS model performs best when generalizing to the City as a whole, and SVM results in the lowest MAE for predicting energy use within the LL84 sample. Our median predicted electric energy use intensity for office buildings is 71.2 kbtu/sf and for residential buildings is 31.2 kbtu/sf with mean absolute log accuracy ratio of 0.17. Building age is found to be a significant predictor of energy use, with newer buildings (particularly those built since 1991) found to have higher consumption levels than those constructed before 1930. We also find higher electric consumption in office and retail buildings, although the sign is reversed for natural gas. In general, larger buildings use less energy per square foot, while taller buildings with more stories, controlling for floor area, use more energy per square foot. Attached buildings-those with adjacent buildings and a shared party wallare found to have lower natural gas use intensity. The results demonstrate that electric consumption can be reliably predicted from a relatively small subset of buildings with actual data, while natural gas use presents a more complicated problem given the bimodal distribution of consumption and infrastructure availability.

Window opening model using deep learning methods

“…The potential of deep learning methods for energy consumption related OB modeling has already been researched by a number of studies [15], [34], [35], [36] [37], [38]. Coelho et al [34] designed a graphics processing unit (GPU)-based parallel strategy for timeseries learning of energy consumption.…”

“…In addition, they pointed out that two hidden layers were sufficient to achieve an optimal performance. Kontokosta and Tull [36] used deep learning methods to predict the energy intensity of 1.1 mio. buildings in New York.…”

Incorporating machine learning with building network analysis to predict multi-building energy use

“…A considerable number of studies have been conducted to develop efficient energy models for single buildings [8][9][10]. In recent years, some researchers have recognized the importance of energy use studies in large-scale areas with distributed building groups to analyze distributed building energy use patterns and optimize net-zero building or distribution energy systems [11,12], also, for city-scale buildings through benchmarking building energy use and reducing city building emissions [13,14]. Focus on analyzing and modeling urban building energy use at the large scale can potentially provide insights into large-scale building energy use patterns and opportunities to save energy [15,16].…”

Structure dependent weather normalization

“…In ref. 13 machine learning techniques are used to model electricity and natural gas consumption for every property in New York City using the physical, spatial, and energy use attributes of a subset derived from 23 000 buildings. The proposed method learns and models the behavior of a building in energy usage habits and energy loss.…”