A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models

Wang, Zeyu; Srinivasan, Ravi S.

doi:10.1016/j.rser.2016.10.079

Cited by 518 publications

(247 citation statements)

References 71 publications

Supporting

Mentioning

244

Contrasting

Unclassified

Order By: Relevance

“…Moreover, they concluded that ensemble modelling (which consists in the association of several single models), in this case (SVR + ANN), had even better performance than single modelling. Wang and Srinivasan came to a similar conclusion in their review since they found that ensemble models have better prediction accuracy than single models (multiple linear regression [MLR], ANN, and SVR). Massana et al found similar results comparing ANN and linear regression for electric load forecasting of a nonresidential building, but in their application, SVR was slightly better than ANN.…”

Section: Neural Network Applications Over a Building's Lifementioning

confidence: 78%

“…They produced a very complete review of the studies involving machine learning with a particular focus on the buildings type, temporal granularities, sort of energy consumption predicted, origin of data, kind of features, data sizes, and performance of the model. Wang and Srinivasan conducted a review on energy use prediction, not only on artificial intelligence based models but also on ensemble models, which consist in the association of several single prediction models for a better accuracy. Deb et al also wrote a review dealing with forecasting techniques, but they give to the reader a more precise state of the art regarding ensemble modelling (also called “hybrid modelling”), which appears to be the most effective forecasting technique modelling for time‐series analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Overview of the use of artificial neural networks for energy‐related applications in the building sector

et al. 2019

View full text Add to dashboard Cite

Summary The incessant growing of the world's energy consumption and associated greenhouse gases emissions have created tremendous problems to be solved by today's and future generations. As the building sector is one of the biggest energy consumers, reducing its energy consumption is now mandatory. Being able to conceive and built efficient buildings, to effectively manage and operate them, and to rapidly renovate the existing building stock is a challenging task. Neural networks models open new possibilities to address this problem. This paper offers a comprehensive review of the studies that use neural networks for energy‐related applications in the building sector focusing on their application and on the technical characteristics of the network (ie, learning algorithm, number of layers, number of neurons, inputs and output variables, and performance criteria). On the basis of this review, limitations concerning the use of neural networks in the building sector along with existing research gaps and future research directions are identified.

show abstract

Section: Neural Network Applications Over a Building's Lifementioning

confidence: 78%

Section: Introductionmentioning

confidence: 99%

Overview of the use of artificial neural networks for energy‐related applications in the building sector

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The aforementioned algorithms can be called the single AI-based method. To eliminate several essential limitations in these algorithms, researchers also propose hybrid methods that integrate at least two AI algorithms, such as the GA-ANN [33] and PSO-GA models [12][13][14][15][16], to improve the prediction accuracy. The hybrid combination of a single AI algorithm shows greater performance compared with other methods.…”

Section: Methodmentioning

confidence: 99%

“…However, the current AI-based energy demand forecasting model does not determine this historical relationship through econometric and statistical analysis. This condition can be recognized as a "black-box" without knowing the internal relationship between energy demand and its affecting factors [33]. Accordingly, this model cannot be adopted for energy demand prediction when the historical relationship estimated through the AI-based model will change over time.…”

Section: Introduction To Ai-based Energy Demand Modelmentioning

confidence: 99%

Energy Demand Forecasting: Combining Cointegration Analysis and Artificial Intelligence Algorithm

Huang

Tang

Chen

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Energy is vital for the sustainable development of China. Accurate forecasts of annual energy demand are essential to schedule energy supply and provide valuable suggestions for developing related industries. In the existing literature on energy use prediction, the artificial intelligence-based (AI-based) model has received considerable attention. However, few econometric and statistical evidences exist that can prove the reliability of the current AI-based model, an area that still needs to be addressed. In this study, a new energy demand forecasting framework is presented at first. On the basis of historical annual data of electricity usage over the period of 1985-2015, the coefficients of linear and quadratic forms of the AI-based model are optimized by combining an adaptive genetic algorithm and a cointegration analysis shown as an example. Prediction results of the proposed model indicate that the annual growth rate of electricity demand in China will slow down. However, China will continue to demand about 13 trillion kilowatt hours in 2030 because of population growth, economic growth, and urbanization. In addition, the model has greater accuracy and reliability compared with other single optimization methods.

show abstract

“…The cooling load calculation is the first step for the design of building air conditioning systems because the transmission and distribution system, the size of the ultimate system and cooling resources, and the control strategies of the whole air conditioning system are all dependent on the cooling load [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

A Simplified Calculation Method for Building Envelope Cooling Loads in Central South China

et al. 2018

View full text Add to dashboard Cite

Abstract:The cooling load calculation of building envelopes is important for building design to realize building energy efficiency. A simplified way to predict the building envelope cooling loads is desperately needed to predict the cooling load of building envelopes with various construction layouts and to predict the energy-saving effect of various reconstruction measures for buildings. In light of this need a simplified calculation model for building envelope cooling loads is proposed in this paper. The model is based on dynamic hourly calculations using EnergyPlus. It considers almost all the thermal factors about the building envelope which may affect the building cooling load and it is studied by dimensional analysis. The equivalent window to wall ratio (EWWR) and building orientation factor are defined to study the building envelope cooling load. The cooling loads of twenty hypothetical buildings with various envelopes are predicated by EnergyPlus. With the results from EnergyPlus the simplified calculation model is developed by MATLAB. Then the newly developed model is validated by two typical actual buildings located in Central-South China. The results show the model is accurate enough to predict the building envelope cooling loads.

show abstract

A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models

Cited by 518 publications

References 71 publications

Overview of the use of artificial neural networks for energy‐related applications in the building sector

Overview of the use of artificial neural networks for energy‐related applications in the building sector

Energy Demand Forecasting: Combining Cointegration Analysis and Artificial Intelligence Algorithm

A Simplified Calculation Method for Building Envelope Cooling Loads in Central South China

Contact Info

Product

Resources

About