DYNAMIC STRUCTURAL-ANALYSIS AND FORECASTING OF RESIDENTIAL ELECTRICITY CONSUMPTION

This paper studies the dynamic relationships between electricity consu mption and several potentially relevant variables, such as weather, pr ice, and consumer income. Monthly data from January 1969 to December 1 990 for all-electric residences in the southeast United States are use d for this study. Because of the nature of the annual weather cycle, s everal of these time series are highly seasonal. Multiple-input transf er function models are employed to analyze the data for their dynamic structure and to evaluate future levels of electricity consumption. Th e linear transfer function (LTF) method is employed in the identificat ion of transfer function models for structural analysis and forecastin g. A major finding is that price plays a major role in explaining cons ervation behavior by electricity consumers. This result has important implications for forecasting the consumption of electric energy. This paper also demonstrates the appropriate construction of models for eco nomic time series with strong seasonality.