Data-driven framework towards realistic bottom-up energy benchmarking using an Artificial Neural Network

Geraldi, Matheus Soares; Ghisi, Enedir

doi:10.1016/j.apenergy.2021.117960

Cited by 24 publications

(3 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Methodsmentioning

confidence: 99%

“…In addition, this study used benchmarking values to identify whether the performance found was close to the typical energy consumption values of public schools in Brazil (up to 120 kWh/m 2 ). 63,64 Envelope's thermal properties. According to the project's specifications from the manual provided by FNDE, 8 the building presented the following conventional construction system: reinforced concrete structure combined with ceramic perforated bricks envelope.…”

Section: Energy Model Definitionsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-objective optimization of school building envelope for two distinct geometric designs in southern Brazil

Maciel

Cruz

Torres

et al. 2023

Indoor and Built Environment

View full text Add to dashboard Cite

The standard Brazilian school projects (EMEIs) were created for the Proinfância [Pro-Childhood] program to respond to the growing national demand for public schools. Unfortunately, the project disregards the Brazilian local climate, leading to an inadequate architectural design, especially in terms of energy performance. Within this context, this research aimed to assess the impact of a new geometric design and envelope proposal on the energy performance of a Brazilian school building. The study object is a standard project (EMEI) of the Proinfância program located in Pelotas, Brazil. Two distinct multi-objective optimizations were performed based on EnergyPlus coupled with the Strength Pareto Evolutionary Algorithm 2 (SPEA2), in which the objective functions were defined to minimize heating and cooling Energy Use Intensity (EUI) for different geometric designs (Base and Linear models). The design variables considered were window-to-wall ratio (WWR); thermal insulation thickness for walls and floor; solar absorptance values for walls and roof; and solar orientation. A total of 74.520 simulations were carried out, and the results indicated that the new geometric design combined with bioclimatic envelope strategies was capable of reducing 52% of the Energy Use Intensity when compared to the standard school project.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Energy Model Definitionsmentioning

confidence: 99%

Multi-objective optimization of school building envelope for two distinct geometric designs in southern Brazil

Maciel

Cruz

Torres

et al. 2023

Indoor and Built Environment

View full text Add to dashboard Cite

show abstract

“…In this context, a number of clustering algorithms have been invented, tested and compared. The prevailing algorithm, by date, is k-Means, adopted in [16], [18]- [21], [23], [25]. Hierarchical clustering has been adopted in [17], while Zarabie et al [26] claim that Affinity Propagation Algorithm outperforms k-Means, k-Medoids and Spectral clustering for residential load profiles grouping.…”

Section: Literature Reviewmentioning

confidence: 99%

A Machine Learning Based Methodology for Load Profiles Clustering and Non-Residential Buildings Benchmarking

Eiraudo

Barbierato

Giannantonio

et al. 2023

IEEE Trans. on Ind. Applicat.

View full text Add to dashboard Cite

Buildings benchmarking based on their electric profiles is a fundamental step to identify, evaluate and then possibly implement energy efficiency oriented actions. Indeed, benchmarking enables comparison among peer buildings or industrial sites and the identification of reference cases, either efficient and inefficient ones. In this regard, temporal data clustering is an effective and widely applicable benchmarking tool. In this work, we propose a novel Machine Learning based methodology, taking advantage of two fundamental tools, namely a decomposition algorithm and a clustering one. Several clustering algorithms have been tested to identify k-Means as the most suitable one. The proposed methodology includes the evaluation of energy Key Performance Indicators for effective analysis and comparison of buildings. The proposed framework has been tested on a real-world case study including around 2000 non-residential buildings. The classification of buildings based on K-Means achieved an accuracy of 99.7% with respect to their usage category. Furthermore, reference Key Performance Indicator values for each cluster are obtained and discussed to understand buildings' energy behaviour and possible reasons for inefficiencies.

show abstract

Review of Uncertainties in Building Characterization for Urban-Scale Energy Modeling

Bolluk

Seyis

2022

Advances in Building Information Modeling

View full text Add to dashboard Cite

Data-driven framework towards realistic bottom-up energy benchmarking using an Artificial Neural Network

Cited by 24 publications

References 67 publications

Multi-objective optimization of school building envelope for two distinct geometric designs in southern Brazil

Multi-objective optimization of school building envelope for two distinct geometric designs in southern Brazil

A Machine Learning Based Methodology for Load Profiles Clustering and Non-Residential Buildings Benchmarking

Review of Uncertainties in Building Characterization for Urban-Scale Energy Modeling

Contact Info

Product

Resources

About