Hourly Load Forecasting Research Articles

A regression-based approach to short-term system load forecasting

The authors describe a novel linear regression-based model for the calculation of short-term system load forecasts. The model's most significant new aspects fall into the following areas: innovative model building, including accurate holiday modeling by using binary variables; temperature modeling by using heating and cooling degree functions; robust parameter estimation and parameter estimation under heteroskedasticity by using weighted least-squares linear regression techniques; the use of 'reverse errors-in-variables' techniques to mitigate the effects on load forecasts of potential errors in the explanatory variables; and distinction between time-independent daily peak load forecasts and the maximum of the hourly load forecasts in order to prevent peak forecasts from being negatively biased. The significant impact of these issues on the accuracy of a model's results was established through testing of an existing load forecasting algorithm. The model has been tested under a variety of conditions and it was shown to produce excellent results. It is also sufficiently general to be used by other electric power utilities. >

Un outil pour la prévision a court-terme

A brief expose of the studies performed at IREQ on the problem of short-term forecasting of stochastic variables is presented. The method developed has been applied for hourly load forecasting of the Hydro-Quebec system. Some of the results of this application are also included.

Adaptive Forecasting of Hourly Loads Based on Load Measurements and Weather Information

Emphasis is placed on devising a physically meaningful procedure for hourly load forecasting. It is proposed that accurate forecasting depends on the use of both weather information and historical patterns. In order to efficiently use this information the total load is decomposed into a nominal load, a residual load and a part which reflects the known changes in the load. The forecast is made by forecasting each component load separately. Alternative procedures based on this decomposition are developed and results from a test case study are presented.