XIV Conferencia de la Asociación Española para la Inteligencia Artificial - CAEPIA 2011, Tenerife (España). 07-11 noviembre 2011
Resumen:
This paper describes a new family of derived variables to measure the efect of outdoor air temperature in electricity and natural gas consumption. The proposed Dynamic Degree-Days (DDD) are temperature-derived functions allowing the definition and use of new quantitative indexes which can help to explain easily the daily variations of electricity and natural gas consumption due to temperature. The DDD are based on a piecewise-linear model for daily temperature, previously adjusted using historical data. These new degree-days allow improving energy forecasting models as well as better monitoring energy performance. Illustrative results are presented.
Palabras clave: degree-days; demand; forecasting
Publicado en Advances in Artificial Intelligence, ISBN: 978-3-642-25273-0
Fecha de publicación: 2011-11-11.
Cita:
E.F. Sánchez-Úbeda, A. Berzosa, New variables to improve electricity and natural gas consumption forecasting: dynamic degree-days, XIV Conferencia de la Asociación Española para la Inteligencia Artificial - CAEPIA 2011, Tenerife (España). 07-11 noviembre 2011. En: Advances in Artificial Intelligence: 14th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2011, La Laguna, Spain, November 7-11, 2011. Proceedings, ISBN: 978-3-642-25273-0
