Search

Efficient and effective city planning in improving the energy performance of residential buildings requires a clear understanding of the influential features. Previous studies on modeling the relationships between influential features and the energy consumption have several gaps and limitations, such as the linear modeling methodology and insufficient consideration of particular features. This study therefore aims at investigating the influence of 171 possibly related features on the regional energy use intensity (EUI) of residential buildings using a non-linear regression algorithm, namely Random Forests (RF). The New York City (NYC) was focused on due to data availability. The 171 features covered seven different aspects, which are building, economy, education, environment, households, surrounding, and transportation. The average site EUI of the residential buildings in each Block Group (BG) was set as the dependent variable. The regression model was compared to the models using typical linear methods, such as Multiple Linear Regression and Lasso. The results show that the RF model achieved a lower mean square error. In addition, the top 20 influential features were identified based on the out-of-bag estimation in RF. Results show that less percentage of well-educated people, higher percentage of households heated by fuel oil, lower household income and more residential complaints per capita are correlated with higher average site EUI in NYC. Related suggestions on improving the energy performance in different regions are presented to the local government.

Buildings are the major source of energy consumption in urban areas. Accurate modeling and forecasting of the building energy use intensity (EUI) in the urban scale have many important applications, such as energy benchmarking and urban energy infrastructure planning. The use of Big Data technology is expected to have the capability of integrating a large number of predictors and giving an accurate prediction of the energy use intensity of buildings in the urban scale. However, past research has often used Big Data technology in estimating energy consumption of a single building rather than the urban scale, due to several challenges such as data collection and feature engineering. This paper therefore proposes a geographic information system integrated data mining methodology framework for estimating the building EUI in the urban scale, including preprocessing, feature selection, and algorithm optimization. Based on 216 prepared features, a case study on estimating the site EUI of 3640 multi-family residential buildings in New York City, was tested and validated using the proposed methodology framework. A comparative study on the feature selection strategies and the commonly used regression algorithms was also included in the case study. The results show that the framework was able to help produce lower estimation errors than previous research, and the model built by the Support Vector Regression algorithm on the features selected by Elastic Net has the least cross-validation mean squared error.