Attention-based interpretable neural network for building cooling load prediction

Applied Energy, Journal Year: 2021, Volume and Issue: 299, P. 117238 - 117238

Published: June 25, 2021

Language: Английский

---

Hourly energy consumption prediction of an office building based on ensemble learning and energy consumption pattern classification

Energy and Buildings, Journal Year: 2021, Volume and Issue: 241, P. 110929 - 110929

Published: March 20, 2021

Language: Английский

---

Machine learning for occupant-behavior-sensitive cooling energy consumption prediction in office buildings

Renewable and Sustainable Energy Reviews, Journal Year: 2021, Volume and Issue: 142, P. 110714 - 110714

Published: March 7, 2021

Language: Английский

---

Accuracy of different machine learning algorithms and added-value of predicting aggregated-level energy performance of commercial buildings

Energy and Buildings, Journal Year: 2019, Volume and Issue: 209, P. 109705 - 109705

Published: Dec. 15, 2019

As with many other sectors, to improve the energy performance and neutrality requirements of individual buildings groups buildings, built environment is also making use machine learning for improved demand predictions. The goal achieving through maximized on-site produced renewable attaining optimal level at building-cluster requires reliable short term (resolution shorter than one day) However, prediction analysis still focused on building not small neighborhood scale or clusters. In a smart grid context, better understand electricity consumption different spatial levels, should be both as well especially neighborhoods definite boundaries (such universities, hospitals). Therefore, in this paper, using data from 47 commercial number algorithms were evaluated predict aggregated hourly intervals. Predicting granularity important short-term dynamics, yet most studies are limited yearly, monthly, weekly, daily resolutions. Two years used training model was performed another year untrained data. Learning such as; boosted-tree, random forest, SVM-linear, quadratic, cubic, fine-Gaussian ANN all analysed tested predicting buildings. results showed that provided best outcomes when metrics computational time error accuracy compared.

Language: Английский

---

Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption — A systematic review

Engineering Applications of Artificial Intelligence, Journal Year: 2022, Volume and Issue: 115, P. 105287 - 105287

Published: Aug. 12, 2022

Language: Английский

---