Very short-term load forecasting using artificial neural networks

In a deregulated, competitive power market, utilities tend to maintain thei r generation reserve close to the minimum required by an independent system operator This creates a need for an accurate instantaneous-load forecast f or the next several dozen minutes. This paper; presents a novel approach to very short-time load forecasting by the application of artificial neural n etworks to model load dynamics. The proposed algorithm is more robust as co mpared to the traditional approach when actual loads are forecasted and use d as input variables. It provides more reliable forecasts, especially when the weather conditions are different from those represented in the training data. The proposed method has been successfully implemented and used for o n-line load forecasting in a power utility in the United States. To assure robust performance and training times acceptable for on-line use, the forec asting system was implemented as a set of parsimoniously designed mural net works. Each network was assigned a task of forecasting load for a particula r time lead and for a certain period of day with a unique pattern in load d ynamics. Some details of this implementation are presented in the paper.