One day ahead load forecasting for electricity market of Iran by ANN

One of the basic requirements for power systems is accurate short-term load forecasting (STLF). In this study, the application of artificial neural networks is explored for designing of short-term load forecasting systems for electricity market of Iran. In this paper, two seasonal artificial neural networks (ANNs) are designed and compared; so that model 2 (hourly load forecasting model) is partitioning of model 1 (daily load forecasting model). Our study based on feed-forward back propagation is trained and tested using three years (2003-2005) data. At the end, extensive data sets test the results; and good agreement is founded between actual data and NN results. Results show that daily forecasting model is better than the hourly one.