Modeling of the space and domestic hot-water heating energy-consumption in the residential sector using neural networks

Two methods have been used to model residential end-use energy consumption at the national or regional level: the engineering method and the conditional demand-analysis method. It was recently shown that the neural network (NN) method is capable of accurately modeling the behaviours of the appliances, lighting, and space-cooling energy consumption in the residential sector. As a continuation of the work on the use of the NN method for modeling residential end-use energy-consumption, two NN based energy-consumption models were developed to estimate the space and domestic hot-water heating energy consumptions in the Canadian residential sector. This paper presents the NN methodology used in developing the models, the accuracy of the predictions, and some sample results.