Applications of machine learning methods to identifying and predicting building retrofit opportunities

Marasco, Daniel E.; Kontokosta, Constantine E.

doi:10.1016/j.enbuild.2016.06.092

Cited by 75 publications

(24 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The benefits of using statistical or machine learning approaches to energy use prediction include the potential to achieve greater degrees of certainty in the output over simulation-based or rule-of-thumb approaches, and a more robust understanding of the effects of individual covariates, such as building characteristics, spatial variables, and use types. Coupled with audit data, machine learning techniques can be used to drive an evidenced-based approach to energy use and carbon emission reduction strategies (Marasco and Kontokosta 2016).…”

Section: Literature Reviewmentioning

confidence: 99%

A data-driven predictive model of city-scale energy use in buildings

2017

Self Cite

View full text Add to dashboard Cite

Many cities across the United States have turned to building energy disclosure (or benchmarking) laws to encourage transparency in energy efficiency markets and to support sustainability and carbon reduction plans. In addition to direct peer-to-peer comparisons, the benchmarking data published under these laws have been used as a tool by researchers and policy-makers to study the distribution and determinants of energy use in large buildings. However, these policies only cover a small subset of the building stock in a given city, and thus capture only a fraction of energy use at the urban scale. To overcome this limitation,. we develop a predictive model of energy use at the building, district, and city scales using training data from energy disclosure policies and predictors from widely-available property and zoning information. We use statistical models to predict the energy use of 1.1 million buildings in New York City using the physical, spatial, and energy use attributes of a subset derived from 23,000 buildings required to report energy use data each year. Linear regression, random forest, and support vector regression algorithms are fit to the city's energy benchmarking data and then used to predict electricity and natural gas use for every property in the city and model accuracy is assessed and validated at the building level and zip code level using actual consumption data from calendar year 2014. We find the OLS model performs best when generalizing to the City as a whole, and SVM results in the lowest MAE for predicting energy use within the LL84 sample. Our median predicted electric energy use intensity for office buildings is 71.2 kbtu/sf and for residential buildings is 31.2 kbtu/sf with mean absolute log accuracy ratio of 0.17. Building age is found to be a significant predictor of energy use, with newer buildings (particularly those built since 1991) found to have higher consumption levels than those constructed before 1930. We also find higher electric consumption in office and retail buildings, although the sign is reversed for natural gas. In general, larger buildings use less energy per square foot, while taller buildings with more stories, controlling for floor area, use more energy per square foot. Attached buildings-those with adjacent buildings and a shared party wallare found to have lower natural gas use intensity. The results demonstrate that electric consumption can be reliably predicted from a relatively small subset of buildings with actual data, while natural gas use presents a more complicated problem given the bimodal distribution of consumption and infrastructure availability.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A data-driven predictive model of city-scale energy use in buildings

2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Table 9 summarizes the machine learning algorithms used in papers that are reviewed in this section. [132], [140] Clustering and ANN [19] Clustering [133] Random Forest [134] Linear Regression [135] Linear Regression and PCA [136] Gradient Boosting [137] Linear Regression and Clustering [138] Gradient Boosting and Clustering [139] ANN [141] Evaluate energy conservation measures ANN, SVM, K-Nearest Neighbors, and Linear Regression [143] ANN [144] Gradient Boosting and Linear Regression [145] Characterize buildings Random Forest [150] SVM [151] CNN [152] Boosted Decision Trees [153] SVM [154] 6.1 Identify retrofit potential Usually, building retrofit planning requires detailed energy audits, which are time-consuming. As the audit data accumulates, machine learning methods will be feasible to explore the underlying patterns of the data to support the generalization of the retrofit planning to large building stocks.…”

Section: Machine Learning For Building Retrofitmentioning

confidence: 99%

“…Benefitting from the New York City's energy audit mandates, in one case study [132] the public audit data of more than 1100 buildings were used to train a falling rule list classifier (a form of decision tree) to predict the eligible energy conservation measures (ECMs) for a certain building based on its characteristics, such as type, build year, envelope, and system type, among others. This helps stakeholders prioritize the most-likely retrofit candidates.…”

Section: Machine Learning For Building Retrofitmentioning

confidence: 99%

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

250

View full text Add to dashboard Cite

Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.

show abstract

“…As part of this, developing automated or virtual audit tools to reduce the cost and uncertainty around energy savings opportunities would make it easier for both regulators and owners to determine the energy conservations measures most suitable to the particular property and with the highest return on investment. Machine learning algorithms and rich energy use and energy audit datasets, like those available through disclosure laws, are a promising way to achieve these objectives (Marasco and Kontokosta 2016).…”

Section: Conclusion and Policy Implicationsmentioning

confidence: 99%

Low hanging fruit? Regulations and energy efficiency in subsidized multifamily housing

Reina

Kontokosta

2017

Energy Policy

View full text Add to dashboard Cite

The U.S. government has invested in multifamily housing through an array of subsidized housing programs. These programs provide a venue for understanding how regulations governing multifamily housing can affect an owner's incentive to make energy efficient investments, and a tenant's desire to reduce their energy consumption levels. This paper empirically tests the impact of subsidized housing regulations on the energy efficiency of multi-family housing for low-income households. We begin by constructing a unique database that integrates actual energy use with physical, socioeconomic, and regulatory characteristics of all large multifamily properties in New York City, focusing on whether a property receives a federal rental subsidy. We employ multivariate regression models to examine the factors that influence energy consumption in multi-family buildings and compare subsidized housing to market-rate housing. We find that subsidized properties are associated with higher energy consumption than similar market-rate properties and, of the subsidized housing programs, Public Housing tends to consume the most energy. Our results suggest that despite the potential for retrofitting multifamily

show abstract

Applications of machine learning methods to identifying and predicting building retrofit opportunities

Cited by 75 publications

References 24 publications

A data-driven predictive model of city-scale energy use in buildings

A data-driven predictive model of city-scale energy use in buildings

State-of-the-art on research and applications of machine learning in the building life cycle

Low hanging fruit? Regulations and energy efficiency in subsidized multifamily housing

Contact Info

Product

Resources

About