A novel energy demand prediction strategy for residential buildings based on ensemble learning
TLDR
The prediction models are developed based on ensemble learning methods which combined extreme gradient boosting, extreme learning machine, multiple linear regression with support vector regression, and a historical energy comprehensive variable named EWMA to improve the prediction accuracy.About:
This article is published in Energy Procedia.The article was published on 2019-02-01 and is currently open access. It has received 35 citations till now. The article focuses on the topics: Ensemble learning & Extreme learning machine.read more
Citations
More filters
Journal ArticleDOI
A review of the-state-of-the-art in data-driven approaches for building energy prediction
TL;DR: This paper provides a comprehensive review on building energy prediction, covering the entire data-driven process that includes feature engineering, potential data- driven models and expected outputs, and concludes with some potential future research directions based on discussion of existing research gaps.
Journal ArticleDOI
A review on machine learning forecasting growth trends and their real-time applications in different energy systems
TL;DR: A comprehensive review is conducted on supervised based machine learning algorithms by using three well-known forecasting engines to suggest suitable methods for forecasting analysis and several other prediciton tasks to choose a better forecasting model for performing the desired task in multiple applications.
Journal ArticleDOI
Accuracy of different machine learning algorithms and added-value of predicting aggregated-level energy performance of commercial buildings
TL;DR: Using data from 47 commercial buildings, a number of machine learning algorithms were evaluated to predict the electricity demand at individual building level and aggregated level in hourly intervals and showed that boosted-tree, random forest, and ANN provided the best outcomes for prediction at hourly granularity.
Journal ArticleDOI
Data Analytics in the Supply Chain Management: Review of Machine Learning Applications in Demand Forecasting
TL;DR: Neural networks, artificial neural networks, support vector regression, and support vector machine were among the most widely used algorithms in demand forecasting with 27%, 22%, 18%, and 10%, respectively.
Journal ArticleDOI
Systematic Review of Deep Learning and Machine Learning for Building Energy
TL;DR: A comprehensive review of ML- and DL-based techniques applied for handling BE systems and the performance of these techniques is evaluated, with results obtained for energy demand forecasting and energy consumption forecasting.
References
More filters
Journal ArticleDOI
Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy
TL;DR: In this paper, a sensor-based forecasting model using Support Vector Regression (SVR), a commonly used machine learning technique, was applied to an empirical data-set from a multi-family residential building in Manhattan.
Journal ArticleDOI
Spatial distribution of urban building energy consumption by end use
TL;DR: In this article, the authors estimate the building sector energy end-use intensity (kwh/m2 floor area) for space heating, domestic hot water, electricity for space cooling and electricity for non-space cooling applications in New York City.
Journal ArticleDOI
Ensemble of various neural networks for prediction of heating energy consumption
TL;DR: It is shown that all proposed neural networks can predict heating consumption with great accuracy, and that using ensemble achieves even better results.
Journal ArticleDOI
Data mining in building automation system for improving building operational performance
TL;DR: This study shows that DM techniques are valuable for knowledge discovery in BAS database; however, solid domain knowledge is still needed to apply the knowledge discovered to achieve better building operational performance.
Journal ArticleDOI
Predicting failure in the U.S. banking sector: An extreme gradient boosting approach
TL;DR: In this paper, extreme gradient boosting was used to predict bank failure in the U.S. banking sector, finding that lower values for retained earnings to average equity, pretax return on assets, and total risk-based capital ratio are associated with a higher risk of bank failure.