The prediction of heating energy consumption in a model house by using artificial neural networks in Denizli–Turkey

Dombaycı, Ö. Altan

doi:10.1016/j.advengsoft.2009.09.012

Cited by 75 publications

(50 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They also require significant efforts and time to compute the best fitting of the actual data. Static neural network models [19][20][21] are used for daily prediction and [22][23][24][25] are used for hourly prediction of the buildings energy consumptions. Though dynamic neural network model [27][28] gives better precision in compared to static neural network, they do not consider occupancy profile and operational power level characteristics of the plant system and therefore not adapted for the ESCOs to manage energy production for control applications.…”

Section: Introductionmentioning

confidence: 99%

“…Dong et al [17] used support vector machine (SVM) to predict the monthly building energy consumption using dry bulb temperature, relative humidity and global solar radiation. Performance of SVM and neural network model wee compared and results show that SVM was better than neural network in prediction.Various authors [22][23][24][25][26] performed hourly building energy prediction using ANN. Mihalakakou et al [22] performed hourly prediction of residential buildings with solar radiation and multiple delays of air temperature predictions as input variables.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Paudel

Elmtiri

Kling

et al. 2014

Energy and Buildings

104

View full text Add to dashboard Cite

This paper presents the building heating demand prediction model with occupancy profile and operational heating power level characteristics in short time horizon (a couple of days) using artificial neural network. In addition, novel pseudo dynamic transitional model is introduced, which consider time dependent attributes of operational power level characteristics and its effect in the overall model performance is outlined. Pseudo dynamic model is applied to a case study of French Institution building and compared its results with static and other pseudo dynamic neural network models. The results show the coefficients of correlation in static and pseudo dynamic neural network model of 0.82 and 0.89 (with energy consumption error of 0.02%) during the learning phase, and 0.61 and 0.85 during the prediction phase respectively. Further, orthogonal array design is applied to the pseudo dynamic model to check the schedule of occupancy profile and operational heating power level characteristics. The results show the new schedule and provide the robust design for pseudo dynamic model. Due to prediction in short time horizon, it finds application for Energy Services Company (ESCOs) to manage the heating load for dynamic control of heat production system.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Paudel

Elmtiri

Kling

et al. 2014

Energy and Buildings

104

View full text Add to dashboard Cite

show abstract

“…For daily basis, Zhou et al [10] proposed a new OIHF-Elman network involving factors such as weather, temperature and daily data type, Farahat and Talaat [11] used curve fitting approach based on genetic algorithm and Jain et al [12] built a sensor-based forecasting model using support vector regression (SVR) for forecasting daily residential NG consumption. For hourly basis, Dombayci [13] applied neural networks to estimate heating energy consumption.…”

Section: Introductionmentioning

confidence: 99%

Daily natural gas consumption forecasting based on a structure-calibrated support vector regression approach

Bai

2016

Energy and Buildings

View full text Add to dashboard Cite

“…Energy consumption data, which were calculated using the finite difference method of transient state one-dimensional heat conduction, were employed to train the model inside MATLAB ANN toolbox. Following the same process, Dombaycı (2010) predicted the hourly energy usage of a house during the design stage but the employed ANN model was trained with energy consumption data calculated by degree hour method covering the period from 2004-2007. Apart from load prediction, ANN models have been also utilised in optimising the performance of energy management systems. For example, to save the electricity used for water heating, Wezenberg and Dewe (1995) adopted some ANN models in generating an operation schedule for a residential water heating system based the cheapest tariffs and without compromising the thermal comfort.…”

Section: 223applicability In the Building Life-cyclementioning

confidence: 99%

Energy planning and forecasting approaches for supporting physical improvement strategies in the building sector: A review

Chalal

Medjdoub

White

et al. 2016

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

The strict CO2 emission targets set to tackle the global climate change associated with greenhouse gas emission exerts so much pressure on our cities which contribute up to 75 % of the global carbon dioxide emission level, with buildings being the largest contributor (UNEP, 2015). Premised on this fact, urban planners are required to implement proactive energy planning strategies not only to meet these targets but also ensure that future cities development is performed in a way that promotes energy-efficiency. This article gives an overview of the stateof-art of energy planning and forecasting approaches for aiding physical improvement strategies in the building sector. Unlike previous reviews, which have only addressed the strengths as well as weaknesses of some of the approaches while referring to some relevant examples from the literature, this article focuses on critically analysing more approaches namely; 2D GIS and 3DGIS (CityGML) based energy prediction approaches, based on their frequent intervention scale, applicability in the building life cycle, and conventional prediction process. This will be followed by unravelling the gaps and issues pertaining to the reviewed approaches. Finally, based on the identified problems, future research prospects are recommended.

show abstract

The prediction of heating energy consumption in a model house by using artificial neural networks in Denizli–Turkey

Cited by 75 publications

References 19 publications

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Daily natural gas consumption forecasting based on a structure-calibrated support vector regression approach

Energy planning and forecasting approaches for supporting physical improvement strategies in the building sector: A review

Contact Info

Product

Resources

About