Prediction of building energy consumption by using artificial neural networks

Ekici, Betül Bektaş; Aksoy, U. Teoman

doi:10.1016/j.advengsoft.2008.05.003

Cited by 320 publications

(114 citation statements)

References 10 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…In the same spirit, [20] used the temperature data in a feedback NN with a remarkable MAPE of the 1.945 % (for instance, [26] included inputs about orientation, insulation thickness and transparency ratio without improving that result). As aforementioned, NNs require much historical data (which, in our case may not be available) and, further, a complicated configuration process that yield them unable to be easily adaptable to single small scenarios(say the buildings of a school).…”

Section: Introductionmentioning

confidence: 99%

Short-term load forecasting in air-conditioned non-residential Buildings

Penya

Borges

Agote

et al. 2011

2011 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

Abstract-Short-term load forecasting (STLF) has become an essential tool in the electricity sector. It has been classically object of vast research since energy load prediction is known to be nonlinear. In a previous work, we focused on non-residential building STLF, an special case of STLF where weather has negligible influence on the load. Now we tackle more modern buildings in which the temperature does alter its energy consumption. This is, we address here fully-HVAC (Heating, Ventilating, and Air Conditioning) ones. Still, in this problem domain, the forecasting method selected must be simple, without tedious trial-and-error configuring or parametrising procedures, work with scarce (or any) training data and be able to predict an evolving demand curve. Following our preceding research, we have avoided the inherent non-linearity by using the work day schedule as day-type classifier. We have evaluated the most popular STLF systems in the literature, namely ARIMA (autoregressive integrated moving average) time series and Neural networks (NN), together with an Autoregressive Model (AR) time series and a Bayesian network (BN), concluding that the autoregressive time series outperforms its counterparts and suffices to fulfil the addressed requirements, even in a 6 day-ahead horizon.

show abstract

Section: Introductionmentioning

confidence: 99%

Short-term load forecasting in air-conditioned non-residential Buildings

Penya

Borges

Agote

et al. 2011

2011 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

show abstract

“…The graphics clearly show that the training of the model was successfully accomplished since the model fits with software data. This case is also supported by the fact that R 2 values were very close to 1 [14,31,32,34,51].…”

Section: Ann Modelmentioning

confidence: 53%

“…This function can range between 0 and 1, but it is also sometimes useful to use the −1 to 1 range [31]. An ANN is usually composed of an input layer, some hidden layers, and an output layer.…”

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

“…They are not programmed in the traditional way but they are trained using past history data representing the behaviour of a system [14]. ANNs can be defined as the learning, understanding and thinking ability of computers [10] that have been widely used for a range of applications in the area of energy modelling [11,[30][31][32][33][34][35][36][37]. Several studies published on predicting energy consumption, cooling load and heat load of buildings using ANN methods [23,[30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

“…Several studies published on predicting energy consumption, cooling load and heat load of buildings using ANN methods [23,[30][31][32][33]. Ekici and Aksoy [31] implemented ANNs for prediction of building energy consumption in Turkey. The main objective of the study was to predict buildings energy needs based on orientation, insulation thickness and transparency.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comparative study of a building energy performance software (KEP-IYTE-ESS) and ANN-based building heat load estimation

Turhan

Kazanasmaz

Uygun

et al. 2014

Energy and Buildings

View full text Add to dashboard Cite

a b s t r a c tThe several parameters affect the heat load of a building; geometry, construction, layout, climate and the users. These parameters are complex and interrelated. Comprehensive models are needed to understand relationships among the parameters that can handle non-linearities. The aim of this study is to predict heat load of existing buildings benefiting from width/length ratio, wall overall heat transfer coefficient, area/volume ratio, total external surface area, total window area/total external surface area ratio by using artificial neural networks and compare the results with a building energy simulation tool called KEP-IYTE-ESS developed by Izmir Institute of Technology. A back propagation neural network algorithm has been preferred and both simulation tools were applied to 148 residential buildings selected from 3 municipalities of Izmir-Turkey. Under the given conditions, a good coherence was observed between artificial neural network and building energy simulation tool results with a mean absolute percentage error of 5.06% and successful prediction rate of 0.977. The advantages of ANN model over the energy simulation software are observed as the simplicity, the speed of calculation and learning from the limited data sets.

show abstract

Transfer learning for forecasting hourly indoor air temperatures of buildings with electrochromic glass

Srisamranrungruang,

Hiyama

2024

Japan Architectural Review

View full text Add to dashboard Cite

This study aimed to employ transfer learning with a fully connected feed‐forward neural network for forecasting the indoor air temperatures of adaptive buildings with electrochromic (EC) glass. This study predicted indoor air temperatures for an intermediate season requiring heating and cooling. Forecasting indoor air temperature can help control the EC glass to avoid overheating the interiors. The forecasting times for the predictions varied from 1 to 5 h between early morning and noon, which is when the interior is often overheated. The pretrained model was created using multilayer perceptron learning with the simulation data of a source building in Tokyo and transfer learning with feature‐based extraction models that used datasets from the simulation of target buildings in Tokyo and Fukuoka. Further, the effects of facade orientation were investigated. The root mean squared error (RMSE) of the pretrained model varied from 0.027 to 0.935 when predicting the indoor air temperatures from 1 to 5 h. The RMSE of the transfer learning models using the pretrained model with the same and different orientations varied from 0.022 to 1.205 and from 0.9301 to 2.566. This study demonstrated that utilizing predicted indoor air temperatures to control EC glass can help protect against overheating.

show abstract

Prediction of building energy consumption by using artificial neural networks

Cited by 320 publications

References 10 publications

Short-term load forecasting in air-conditioned non-residential Buildings

Short-term load forecasting in air-conditioned non-residential Buildings

Comparative study of a building energy performance software (KEP-IYTE-ESS) and ANN-based building heat load estimation

Transfer learning for forecasting hourly indoor air temperatures of buildings with electrochromic glass

Contact Info

Product

Resources

About