An artificial neural network technique is used to provide real time hourly load update, next day load profile, and daily peak load forecast. Weather and time factors are included in the proposed method by using them as the network's inputs. Results from the neural network are compared with those from autoregressive moving average model with exogenous input (ARMAX). Experiments are conducted on two Utilities historical data, each contains a time period longer than one year. Forecasting accuracy is evaluated throughout a whole year in order to determine the effect of seasonal load variation on the accuracy of the proposed forecasting models.
展开▼
