Application of Machine Learning for Predicting Building Energy Use at Different Temporal and Spatial Resolution under Climate Change in USA

Rezvan Mohammadiziazi,Melissa Bilec

doi:10.3390/buildings10080139

Abstract

Given the urgency of climate change, development of fast and reliable methods is essential to understand urban building energy use in the sector that accounts for 40% of total energy use in USA. Although machine learning (ML) methods may offer promise and are less difficult to develop, discrepancy in methods, results, and recommendations have emerged that requires attention. Existing research also shows inconsistencies related to integrating climate change models into energy modeling. To address these challenges, four models: random forest (RF), extreme gradient boosting (XGBoost), single regression tree, and multiple linear regression (MLR), were developed using the Commercial Building Energy Consumption Survey dataset to predict energy use intensity (EUI) under projected heating and cooling degree days by the Intergovernmental Panel on Climate Change (IPCC) across the USA during the 21st century. The RF model provided better performance and reduced the mean absolute error by 4%, 11%, and 12% compared to XGBoost, single regression tree, and MLR, respectively. Moreover, using the RF model for climate change analysis showed that office buildings’ EUI will increase between 8.9% to 63.1% compared to 2012 baseline for different geographic regions between 2030 and 2080. One region is projected to experience an EUI reduction of almost 1.5%. Finally, good data enhance the predicting ability of ML therefore, comprehensive regional building datasets are crucial to assess counteraction of building energy use in the face of climate change at finer spatial scale.

Highlights

Urban areas account for nearly 67% of total energy consumption worldwide [1]
Since previous studies have drawn a different conclusion from applying ML to various subsets of the Commercial Building Energy Consumption Survey (CBECS) dataset [25,26], we first investigated the performance of simple statistical and complex machine learning algorithms on a subset of CBECS, that contains all commercial building use types and more than a hundred predictors, to single out the one that provides better goodness-of-fit to proceed with climate change analysis
We assessed the ability of the prediction model that was developed using random forest algorithm in capturing the change in energy use intensity of commercial building as result of climate change

Summary

Introduction

Urban areas account for nearly 67% of total energy consumption worldwide [1]. As the population shifts from rural areas to cities, the energy consumption in cities will continue to rise [2,3]. Understanding energy use in cities and associated greenhouse gas emissions, is critical to solving energy and policy goals. Data related to urban energy use is disparate and diverse, especially in the area of building energy use. In London buildings consumes 61% of the city’s energy which is two times higher than the share of transportation [4]. The rising dependency of city residents and workers on appliances, office equipment, and space conditioning has led to the increase in building energy use [1,5]

Objectives

Methods

Results

Conclusion