Physics-informed ensemble learning with residual modeling for enhanced building energy prediction

Developing a landscape of urban building energy use with improved spatiotemporal representations in a cool-humid climate

Spatial distribution of building energy use in the United States through satellite imagery of the earth at night

Rapid urbanization, climate change, and aging infrastructure pose significant challenges to achieving sustainability and resilience goals in urban building energy use. Although retrofitting offers a viable solution to mitigate building energy use, there has been limited analysis of its effects under various weather conditions associated with climate change in urban building energy use simulations. Moreover, certain parameters in energy simulations necessitate extensive auditing or survey work, which is often impractical. This research proposes a framework that integrates various datasets, including building footprints, Lidar data, property appraisals, and street view images, to conduct neighborhood-scale building energy use analysis using the Urban Modeling Interface (UMI), an Urban Building Energy Model (UBEM), in a coastal neighborhood in Galveston, Texas. Seven retrofit plans and three weather conditions are considered in the scenarios of building energy use. The results show that decreasing the U-value of building envelopes helps reduce energy use, while increasing the U-value leads to higher energy consumption in the Galveston neighborhood. This finding provides direction for coastal Texas cities, like Galveston, to update building standards and implement retrofit measures.

Energy-use patterns in many of California's fastest-growing industries are not typical of the existing mix of industries in the US. Many California firms operate small- and medium-sized facilities housed in buildings used simultaneously or interchangeably over time for commercial (office, retail, warehouse) and industrial activities. In these industrial subsectors, the energy required for building services (providing occupant comfort and necessities like lighting, HVAC, office equipment, computers, etc.) may be at least as important as the more familiar process energy requirements -- especially for electricity and on-peak demand. Electricity for building services is sometimes priced as if it were base loaded like process uses; in reality this load varies significantly according to occupancy schedules and cooling and heating loads, much as in any commercial building. Using informal field surveys, simulation studies, and detailed analyses of existing data (including utility commercial/industrial audit files), we studied the energy use of this industrial subsector through a multi-step procedure: (1) characterizing non-process building energy and power use in California industries, (2) identifying conservation and load-shaping opportunities in industrial building services, and (3) investigating industrial buildings and system design methodologies. In an earlier report, we addressed these issues by performing an extensive survey of the existing publicly available data, characterizing and comparing the building energy use in this sector. In this report, we address the above objectives by examining and analyzing energy use in two industrial case-study facilities in California. Based on the information for the case studies, we discuss the design consideration for these industrial buildings, characterize their energy use, and review their conservation and load-shaping potentials. In addition, we identify and discuss some research ideas for further investigation.

Building energy use in China: Ceiling and scenario

Urban form and building energy use: A systematic review of measures, mechanisms, and methodologies

Data analysis and stochastic modeling of lighting energy use in large office buildings in China

Propagating downscaled future weather file uncertainties into building energy use

The warming urban climates increase the building energy consumption by changing the heating/cooling loads of the buildings. On the other hand, building induced anthropogenic heat emissions can also contribute to the urban heating, creating a warming feedback loop. Such impact is more profound in the (sub)tropical and hot/arid context, where Air Conditioning (AC) systems are widely used. A better understanding of the building energy consumption and its contribution to urban heating can therefore help mitigate urban heating. To this end, we aim to estimate building energy use and induced heat emissions in Kuala Lumpur, Malaysia, using both a bottom-up strategy based on building energy modelling and a top-down strategy based on national scale energy inventory. We further integrate the building energy model with measured diurnal temperature profiles at different land use areas, to discuss the impact of urban heat island (UHI) on energy use, and potential mitigation strategies through different urban morphologies. The estimated energy use obtained via both bottom-up and the top-down approaches were within the range of actual energy use from case studies available for Kuala Lumpur. It also highlights the need to adapt multi-scale strategies to mitigate the building energy use, and the associated impacts on the UHI.

The effect of neighbourhood-level urban form on residential building energy use: A GIS-based model using building energy benchmarking data in Seattle

Urban Heat Islands (UHI) affect building energy use in many cities worldwide. The correlations between UHI and building energy use have mostly been studied via city-scale modeling simulations, making validation of the obtained results challenging. In this study, we use clustering and statistical methods to examine the relationship between various indicators of UHI and building energy use, utilizing archived empirical data on energy consumption in office buildings across the entire country of South Korea. Our findings reveal considerable differences in UHI behavior across provinces and cities in the country. These variations are driven by a complex interplay of factors related to geographic locations, urbanization levels, and the topography of the provinces. These results suggest that mitigative efforts for UHI in South Korea should consider targeted measures tailored to specific locales. We also identify strong positive correlations between various UHI indicators, particularly monthly average Urban Heat Island Intensity (UHII) and cooling energy consumption in office buildings. However, the relationship between UHII and heating energy consumption was largely non-existent. These findings offer an empirical foundation for the development of efficient and inclusive policies that promote livability in urbanized areas.

DUE-A: Data-driven Urban Energy Analytics for understanding relationships between building energy use and urban systems

abstractThe purpose of this study was to propose a building energy management process, verify the proposed model by applying energy management techniques in a real office building, and develop an empirical approach for predicting building energy use with regression analysis. This study proposed the four major energy management steps: energy audit, energy analysis, identifying and evaluating the energy saving opportunities, and retrofit implementation and follow-through. For the prediction of energy use, simple regression models were developed based on historical energy consumption data as a function of daily outside temperatures, while the predicting equations were derived for different operational modes and day types. By selecting a real building as a case study, the feasibilities of the building energy management process and the empirical approach for predicting building energy use have been examined.

Forecasting district-scale energy dynamics through integrating building network and long short-term memory learning algorithm

Structural, geographic, and social factors in urban building energy use: Analysis of aggregated account-level consumption data in a megacity