URBAN ENERGY FOOTPRINT
Tell Me More

Project Overview

This project seeks to develope innovative models to estimate urban residential, commerical, and transportation energy consumption footprints. The models are constructed using advance machine-learning, data fusion and syntehsizing techniques. The developed models only require public accessible data sources, including Residential Energy Consumption Survey (RECS), Commerical Building Energy Consumption Survey (CBECS), and Regional Origina-Destination Matrix, as models inputs. Given the national availability of the requried data sources, the developed models hold the potential to be applied to any Major metropolitan area throughout the United States and therefore overcoming one of the drawbacks of existing energy consumption estimation models.


Residential Energy Model

Understand spatial distribution of residential energy consumption using statistical matching, machine learning and population synthesizing techniques and RECS data.

Transportation Energy Model

Model household transportation energy footprint with Origin-Destination matrix from regional transportation demand model.

Commercial Energy Model

Estimate commercial building energy consumption by applying machine learning approaches to the CBECS data.

PUBLICATION



  • This paper presents a methodology for the calculation of household travel energy consumption at the level of the traffic analysis zone (TAZ) in conjunction with information that is readily available from a standard four-step travel demand model system. The methodology presented in this paper embeds two algorithms that facilitate the integrated modeling of travel demand and household travel energy consumption. The first algorithm provides a means of allocating non-home-based to residential zones that are the source of such trips, while the second algorithm provides a mechanism for incorporating the effects of household vehicle fleet mix distribution on fuel consumption. The methodology is then applied to the Greater Atlanta metropolitan region in the United States.


    Cite this work: Garikapati, V. M., You, D., Zhang, W., Pendyala, R. M., Guhathakurta, S., Brown, M. A., & Dilkina, B. (2017). Estimating household travel energy consumption in conjunction with a travel demand forecasting model. Transportation Research Record: Journal of the Transportation Research Board, (2668), 1-10.

  • In this study we develop a novel method for estimating household energy demand that can be applied to any urban region in the US with the help of publicly available data. To improve estimates of residential energy this paper describes a methodology that utilizes a matching algorithm to stitch together data from RECS with the Public Use Microdata Sample (PUMS) provided by the Bureau of Census. Our workflow statistically matches households in RECS and PUMS datasets based on the shared variables in both, so that total energy consumption in the RECS dataset can be mapped to the PUMS dataset. Following this mapping procedure, we generate synthetic households using processed PUMS data together with marginal totals from the American Community Survey (ACS) records. By aggregating energy consumptions of synthesized households, small area or neighborhood-based estimates of residential energy use can be obtained.


    Cite this work: Zhang, W., S. Guhathakurta, R.M. Pendyala, V.M. Garikapati, C. Ross (2017) A Generalizable Method for Estimating Household Energy by Neighborhoods in US Urban Regions. Energy Procedia (forthcoming).

  • Building energy consumption makes up 40% of the total energy consumption in the United States. Given that energy consumption in buildings is influenced by aspects of urban form such as density and floor-area-ratios (FAR), understanding the distribution of energy intensities is critical for city planners. This paper presents a novel technique for estimating commercial building energy consumption from a small number of building features by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Our results show that gradient boosting regression models perform the best at predicting commercial building energy consumption, and can make predictions that are on average within a factor of 2 from the true energy consumption values (with an r2 score of 0.82). We validate our models using the New York City Local Law 84 energy consumption dataset, then apply them to the city of Atlanta to create aggregate energy consumption estimates. In general, the models developed only depend on five commonly accessible building and climate features, and can therefore be applied to diverse metropolitan areas in the United States and to other countries through replication of our methodology.


    Cite this work: Robinson, C., Dilkina, B., Hubbs, J., Zhang, W., Guhathakurta, S., Brown, M. A., & Pendyala, R. M. (2017). Machine learning approaches for estimating commercial building energy consumption. Applied Energy, 208, 889-904.

  • Prior research has shown that land use patterns and the spatial configurations of cities have a significant impact on residential energy demands. Given the pressing issues surrounding energy security and climate change, there is renewed interest in developing and retrofitting cities to make them more energy efficient. Yet, there are significant methodological constraints for deriving metropolitan scale residential energy footprints. Without access to high resolution data from energy providers, it is difficult to estimate energy use at the neighborhood level for metropolitan regions. In this study, a bottom-up model is proposed to estimate residential energy demand using datasets that are commonly available in the United States. The model applies novel machine learning methods to match records in the Residential Energy Consumption Survey (RECS) with Public Use Microdata samples (PUMS) to estimate neighborhood level synthetic household energy distribution in a metro region. The model was tested and validated with data from the Atlanta metropolitan region to demonstrate its application and promise.


    Cite this work: Zhang, W., Robinson, C., Guhathakurta, S., Garikapati, V. M., Dilkina, B., Brown, M. A., & Pendyala, R. M. (2018). Estimating residential energy consumption in metropolitan areas: A microsimulation approach. Energy, 155, 162-173.

  • To be
    Continued

Our Amazing Team


Subhrajit Guhathakurta

Professor @ Urban and Regional Planning, Georgia Tech

Ram Pendyala

Professor @ Sustainable Engineering and the Built Environment, Arizona State University

Marilyn Brown

Professor @ Public Policy,
Georgia Tech

Bistra Dilkina

Assistant Professor @ Computational Science & Engineering, Georgia Tech

Venu Garikapati

Project Leader @ National Renewable Energy Laboratory

Caleb Robinson

PhD Student @ Computational Science & Engineering, Georgia Tech

Jefferey Hubbs

Research Scientist @ Public Policy, Georgia Tech

Wenwen Zhang

Assistant Professor @ Urban & Affairs Planning, Virginia Tech