Abstract
Energy efficiency benchmarking can be used to monitor changes in the overall efficiency of buildings. Benchmarking models, based on energy efficiency indicators, are valuable tools for both public and private stakeholders because they allow an improvement in the building energy management. For the last decade, some governments have used these tools to define their building regulations (Santamouris, M., et al., 2005. Energy performance of residential buildings book. UK: James and James/Earthscan. ISBN: 1-902916-49-2, Chung, W., Hui, Y.V., and Miu Lam, Y., 2006. Benchmarking the energy efficiency of commercial buildings. Applied Energy, 83, 1–14). This paper tries to go further, integrating a benchmarking and a modelling process, into the same energy efficiency analysis. The connections between the energy use intensities (EUIs) and the characteristic building factors are modelled using neural network techniques. The process is divided into two stages: the data acquisition stage and the benchmarking and modelling stage. The benchmarking and modelling stage is focused on the adjustment of these EUIs within the climatic conditions (with a severity climate index method) and the development of a prediction model for calculating the relationship between these climate-adjusted EUIs and the significant factors of a building. In order to validate this methodology, an application to schools in Catalonia is presented. Additionally, the use of the artificial neural network (ANN) benchmark model for predicting potential energy savings from retrofit projects was evaluated. Some of the input variables were modified to reflect potential energy savings from a retrofit project, and the new input set was simulated with the ANN model. The preliminary results show that the developed ANN model can be used to predict energy savings from retrofit projects.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have