Application of Artificial Neural Networks in the Urban Building Energy Modelling of Polish Residential Building Stock
Open Access
Abstract
The development of energy-efficient buildings and sustainable energy supply systems is an obligatory undertaking towards a more sustainable future. To protect the natural environment, the modernization of urban infrastructure is indisputably important, possible to achieve considering numerous buildings as a group, i.e., Building Energy Cluster (BEC). The urban planning process evaluates multiple complex criteria to select the most profitable scenario in terms of energy consumption, environmental protection, or financial profitability. Thus, Urban Building Energy Modelling (UBEM) is presently a popular approach applied for studies towards the development of sustainable cities. Today’s UBEM tools use various calculation methods and approaches, as well as include different assumptions and limitations. While there are several popular and valuable software for UBEM, there is still no such tool for analyses of the Polish residential stock. In this work an overview on the home-developed tool called TEAC, focusing on its’ mathematical model and use of Artificial Neural Networks (ANN). An exemplary application of the TEAC software is also presented.Keywords
This publication has 48 references indexed in Scilit:
- Short-Term Load Forecasting for Microgrids Based on Artificial Neural NetworksEnergies, 2013
- Energy-related emissions and mitigation opportunities from the household sector in DelhiEnergy Policy, 2007
- Long-term energy savings and greenhouse gas emission reductions in the Swiss residential sectorEnergy Policy, 2007
- Artificial neural networks in energy applications in buildingsInternational Journal of Low-Carbon Technologies, 2006
- Bayesian Regularization in a Neural Network Model to Estimate Lines of Code Using Function PointsJournal of Computer Science, 2005
- A revival of the autoregressive distributed lag model in estimating energy demand relationshipsEnergy, 2001
- Cascaded artificial neural networks for short-term load forecastingIEEE Transactions on Power Systems, 1997
- CO2, Emission Reduction Costs in the Residential Sector: Behavioral Parameters in a Bottom-Up Simulation ModelThe Energy Journal, 1996
- A Bayesian Approach to Combining Conditional Demand and Engineering Models of Electricity UsageReview of Economics and Statistics, 1987
- A model of residential energy use in New ZealandEnergy, 1980