The teachers/practitioners corner comparative analysis of load forecasting techniques at a southern utility

✍ Scribed by William R. Huss

• Book ID: 102843205
• Publisher: John Wiley and Sons
• Year: 1985
• Tongue: English
• Weight: 536 KB
• Volume: 4
• Category: Article
• ISSN: 0277-6693
• DOI: 10.1002/for.3980040113

✦ Synopsis

The prime directive of any regulated electric utility is to provide adequate and reliable electricity supplies to the consuming public at reasonable cost. This requires the continual addition of new generating plants which is based on a long term forecast of energy and peak demand. This study documents the forecasting process used at a southern utility and compares the accuracy of their models to that produced using Holt's exponential smoothing and generalized adoptive filtering. KEY WORDS Application-sector, utilities, electricity Comparative methods-urved exponential smoothing Comparative methods-adaptive fitting, other

The prime directive of any regulated electric utility is to provide adequate and reliable electricity supplies to the consuming public at a reasonable cost. Over time, the demand for electricity is constantly changing, as are construction and fuel costs. To meet these fluctuations in demand, a utility must be constantly adding new capacity, retiring inefficient plants and expanding existing ones. New plant construction normally requires 5-10 years. Proposed sites must be selected and evaluated, financing must be obtained and approval from the regulatory body received. Because of a lead time which may extend to several years, capacity expansion must be based on aforecast of future demand. The ability of a utility to minimize the cost of electricity depends directly on the ability of the load forecast to predict the level of energy sales and peak demand over time.

Prior to 1973, most industries, including utilities, forecast growth using a rather unsophisticated time trend approach. In other words, by fitting a curve (often a straight line) to historical data, an estimate of future energy sales could be made. Unfortunately, these curves did not capture the underlying causes of load growth and therefore were unable to predict sudden changes in growth such as those which occurred as a result of the 1973-1974 oil embargo. Soon after the oil embargo, new, more sophisticated forecasting techniques were introduced to the utility industry, particularly econometric and end-use models.

Econometric models employ regression analysis to fit to historical energy consumption data a curve defined by economic variables such as income, population and employment. Whereas the trending models use only one independent variable, namely time, the econometric models can look at many dimensions, each having some intuitive as well as statistical relation to electricity demand.