The building sector along with its sub-sectors is the world’s leading consumer of all forms of energy and consumes about 30% of the world’s final energy consumption. With the increase in population, industrialization and urbanization trend, the energy sector has grown rapidly in the past decades to cater to the increase in energy demand. To cater this, many regulatory efforts in the form of energy efficiency and conservation codes offering guidelines and measures during and post design have been proposed in different countries of the world. In order to optimize the consumption of energy and achieving energy efficiency in buildings, an important role is played by the energy consumption prediction. In the due course of time, various energy prediction models have been developed by researchers, which are either based on Physical, Hybrid, or Data-driven methods. In this paper, the energy prediction results using two mostly used data-driven methods i.e. multi linear regression and artificial neural network methods, are compared. For this energy consumption data was collected and monitored from six dwelling units when the outside temperature range is 4°C to 15 °C. It has been observed that the monthly energy consumption predicted using ANN method is more accurate than the prediction using MLR. The variation in energy prediction values ranges between -0.302% to +1.752% in ANN, whereas in MLR it ranges between -2.112% to +2.448%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.