Tuning machine learning models for prediction of building energy loads

Seyedzadeh, Saleh; Rahimian, Farzad Pour; Rastogi, Parag; Glesk, Ivan

doi:10.1016/j.scs.2019.101484

Cited by 159 publications

(79 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These models can be run based on the historical operational data for a building without taking into consideration the physical characteristics of the site. [12]. The commonly used black-box models include regression analysis, artificial neural networks, and support vector machines [13].…”

Section: A Load Prediction Methodsmentioning

confidence: 99%

Ultra-Short-Term Building Cooling Load Prediction Model Based on Feature Set Construction and Ensemble Machine Learning

Ding

Kong

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As the requirements for the optimal control of building systems increase, the accuracy and speed of load predictions should also increase. However, the accuracy of load predictions is related to not only the prediction algorithm, but also the feature set construction. Therefore, this study develops a shortterm building cooling load prediction model based on feature set construction. The impacts of four different feature set construction methods-feature extraction, correlation analysis, K-means clustering, and discrete wavelet transform (DWT)-on the prediction accuracy are compared. To ensure that the effect of the feature set construction method is universal, three different prediction algorithms are used. The influences of the sample dimension and prediction time horizon on the prediction accuracy are also analysed. The prediction model is developed based on an ensemble learning algorithm utilising the cubist algorithm, and the performance of the prediction model is improved when DWT is used for constructing the feature set. Compared with other commonly used prediction models, the proposed model exhibits the best performance, with R-squared and CV-RMSE values of 99.8% and 1.5%, respectively. INDEX TERMS Cooling load prediction, Feature extraction, Ensemble learning algorithms, Discrete wavelet transform Nomenclature RF Random forest R-squared Square correlation coefficient GBM Gradient boosting machine FOG First order 5-h gradient DWT Discrete wavelet transform MSG Mean value of the square of the 1-h gradients in the past 5 h CA Correlation analysis FS Feature sets PCA Principal component analysis Large sample FS1 t-SNE t-distributed stochastic neighbour embedding Small sample FS10 g Principal component contribution ratio ARE Absolute value of relative error between predicted and actual values rspearman Spearman rank correlation coefficient IR Degree of improvement in the prediction accuracy Dk Sum of intra-cluster distances At Actual value SSE Sum of the squared error Ft Predicted value MSE Mean square error n Sample size CV-RMSE Root-mean-square error coefficient of variation Reduction ratio Reduction values between two time points

show abstract

Section: A Load Prediction Methodsmentioning

confidence: 99%

Ultra-Short-Term Building Cooling Load Prediction Model Based on Feature Set Construction and Ensemble Machine Learning

Ding

Kong

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Donkor et al (2014) reviewed the performance of econometric models, Artificial Neural Networks (ANN), and simulation or scenario-based modeling on water consumption. Recently, machine learning (ML) approaches have gained significant interest (Bourdeau et al, 2019;Seyedzadeh et al, 2019;Yu et al, 2016;Froemelt et al, 2019) and tend to perform better than traditional statistical regression modeling techniques thanks to their machine-based algorithmic computation. In particular, Decision Tree (DT) (Badhrudeen et al, 2020), ANN, ensemble methods (e.g., bagging and boosting methods), Support Vector Machine (SVM) (Parsa et al, 2019b), and regularized linear regression (e.g., ridge and lasso regression) tend to be the most popular ML approaches applied in the previous studies (Wei et al, 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

Interrelated Patterns of Electricity, Gas, and Water Consumption in Large-Scale Buildings

Movahedi¹,

Derrible²

2020

Preprint

View full text Add to dashboard Cite

As cities keep growing worldwide, so does the demand for key resources such as energy (electricity and gas) and water that residents consume. Meeting the demand for these resources can be challenging and requires an understanding of their consumptions patterns. In this work, we apply XGBoost (Extreme Gradient Boosting) to predict and analyze water and energy consumption in large-scale buildings in New York City. For this, the New York City’s local law 84 extensive dataset was merged with the Primary Land Use Tax Lot Output (PLUTO) dataset as well as with other socio-economic databases. Specifically, we developed three models: electricity, gas, and water consumption. Seven major lessons were learnt in terms of interrelationships between electricity, gas, and water consumption. In particular, water and gas consumption are highly interrelated with one another (often because gas is used for water heating). Furthermore, electricity consumption is affected by building type, and electricity and water consumption are particularly interrelated in nonresidential buildings. Overall, the knowledge gained from the models and from the SHAP analysis can help planners, engineers, and policymakers develop more effective strategies and help them manage the demand for energy and water in large-scale buildings.

show abstract

“…Artificial Neural Networks (ANN) [2,[9][10][11][12][13][14][15][16][17][18][19]] Decision Trees (DT) [20] Support Vector Regression (SVR) [11,13,14,19,[21][22][23]] Random Forest (RF) and Trees Ensemble [8,13,14,[20][21][22][23][24][25][26][27][28][29] Multi-Layer Perceptron (MLP) [14,20,23,27] Gaussian Mixture Model (GMM) [30] Gradient Boosted Regression Trees (GBRT) [24,31] Extreme Learning Machine (ELM) [10,32,33] Linear Regression (LR) [10,13,21,23,27,34,35] Radial Basis ...…”

Section: Machine Learning Techniques Papersmentioning

confidence: 99%

An Octahedric Regression Model of Energy Efficiency on Residential Buildings

Navarro-González

Villacampa

2019

Applied Sciences

View full text Add to dashboard Cite

System modeling is a main task in several research fields. The development of numerical models is of crucial importance at the present because of its wide use in the applications of the generically named machine learning technology, including different kinds of neural networks, random field models, and kernel-based methodologies. However, some problems involving the reliability of their predictions are common to their use in the real world. Octahedric regression is a kernel averaged methodology developed by the authors that tries to simplify the entire process from raw data acquisition to model generation. A discussion about the treatment and prevention of overfitting is presented and, as a result, models are obtained that allow for the measurement of this effect. In this paper, this methodology is applied to the problem of estimating the energetic needs of different buildings according to their principal characteristics, a problem that has importance in architecture and civil and environmental engineering due to increasing concerns about energetic efficiency and ecological footprint.

show abstract

Tuning machine learning models for prediction of building energy loads

Cited by 159 publications

References 51 publications

Ultra-Short-Term Building Cooling Load Prediction Model Based on Feature Set Construction and Ensemble Machine Learning

Ultra-Short-Term Building Cooling Load Prediction Model Based on Feature Set Construction and Ensemble Machine Learning

Interrelated Patterns of Electricity, Gas, and Water Consumption in Large-Scale Buildings

An Octahedric Regression Model of Energy Efficiency on Residential Buildings

Contact Info

Product

Resources

About