Application of Extreme Learning Machine-Autoencoder to Medium Term Electricity Price Forecasting

This paper proposes a new forecasting approach for medium-term electricity market prices based on an extreme learning machine-autoencoder (ELM-AE). The main idea behind is to use trained weights for hidden layer instead of randomly generated weights. The input hidden layer weights are obtained by solving a network with the same input outputs by the autoencoder method. To do so, a data-set is created using input data, where the ahead 24 hours are forecasted based on previous 168 data. The simulations have been performed on New York Independent System Operator prices and compared with the classic ELM demonstrating the high accuracy of the proposed method in both training and testing.