Using Recurrent Artificial Neural Networks to Forecast Household Electricity Consumption

The electricity consumption related to the civil sector (residential and tertiary) in the most developed countries has considerably increased during the last years, especially in the summer season. One of the reasons for this rise can be found in the drastic growth of the sales of mono and multi-split systems for air-conditioning. In this context is very important to assess the correlation between electricity demand and utilization of electric appliances (especially air-conditioners). This paper describes a model based on an Elman Artificial Neural Network (ANN) for the short-time forecasting (1 hour ahead) of the household electric consumption related to a suburban area in the neighbours of the town of Palermo (Italy). One of the aims of the study is the assessment of the influence of the use of air-conditioning equipments on the electricity demand. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the organizing committee of 2nd International Conference on Advances in Energy Engineering (ICAEE).