MODELLING TECHNIQUES FOR ELECTRICITY LOAD FORECASTING

Abstract

SinglelayerFeedforwardNeuralNetwork(FNN)isusedmanyatime asalastlayerinmodelssuchasseq2seqorasimpleRNNnetwork. The importance of such layer is to transform the output to our required dimensions. When it comes to weights and biases initialization, there is no such specific technique that could speed up the learning process. We could depend on deep network initialization techniques such as Xavier or He initialization. But such initialization fails to show much improvement in learning speed or accuracy. Zero Initialization (ZI) for weights of a single layer network is proposed here. We first test this technique with on a simple RNN network and compare the results against Xavier, He and Identity initialization. As a final test we implement it on a seq2seq network. It was found that ZI considerably reduces the number of epochs used and improve the accuracy. Multi-objective swarm intelligence is also utilized for weights and biases initialization for quicker learning. The developed model has been applied for short-term load forecastingusingtheloaddataofAustralianEnergyMarket. Themodel is able to forecast the day ahead price accurately with error of 0.94%.