Big-data for building energy performance: Lessons from assembling a very large national database of building energy use

Abstract

15Building energy data has been used for decades to understand energy flows in 16 buildings and plan for future energy demand. Recent market, technology and policy 17 drivers have resulted in widespread data collection by stakeholders across the 18 buildings industry. Consolidation of independently collected and maintained 19 datasets presents a cost-effective opportunity to build a database of unprecedented 20 size. Applications of the data include peer group analysis to evaluate building 21 performance, and data-driven algorithms that use empirical data to estimate energy 22 savings associated with building retrofits. This paper discusses technical 23considerations in compiling such a database using the DOE Buildings Performance 24 Database (BPD) as a case study. We gathered data on over 700,000 residential and 25 commercial buildings. We describe the process and challenges of mapping and 26 cleansing data from disparate sources. We analyze the distributions of buildings in 27 the BPD relative to the Commercial Building Energy Consumption Survey (CBECS) 28 and Residential Energy Consumption Survey (RECS), evaluating peer groups of 29 buildings that are well or poorly represented, and discussing how differences in the 30 distributions of the three datasets impact use-cases of the data. Finally, we discuss 31 the usefulness and limitations of the current dataset and the outlook for increasing 32 its size and applications. 33

Quantifying flexibility of commercial and residential loads for demand response using setpoint changes

“…Users can use the tool to estimate the energy performance without creating physical models. Similarly, a very large database of building energy use at the national level is presented to support empirical comparison of energy use and data-driven savings analysis and help users identify the energy saving potentials [33]. Those studies provide insight into the use of physical models and large datasets in the most efficient manner.…”

Ferramenta para extração de dados semi-estruturados para carga de um big data

“…Ou seja, não são gerados de maneira organizada ou padronizada. Podemos citar alguns exemplos de dados não estruturados, como fotos, vídeos, mídias sociais, sensores, dentre outros [8].…”

In-Depth Analysis of Energy Efficiency Related Factors in Commercial Buildings Using Data Cube and Association Rule Mining

“…To date, much research has been conducted to reduce energy consumption and to improve energy efficiency in buildings [6][7][8][9][10]. For example, Chae et al proposed a prediction model for electrical energy consumption in buildings based on an artificial neural network and Bayesian regularization algorithm [8].…”

“…Lei et al investigated the energy performance of building envelopes integrating the phase change materials (PCMs) for cooling load reduction in Singapore by using numerical simulations [9]. Mathew et al analyzed the performance of energy efficiency according to the composition of various building envelopes [10].…”