Short-term load forecasting using neural networks and global climate models: An application to a large-scale electrical power system.

• We develop shallow and deep neural networks for the Short-Term Load Forecasting problem. • Different neural networks architectures are tested, including uni- and bi-directional structures. • Global climate models' information is used as input of the neural networks. • We present a real study case of time series forecasting for the Brazilian power system. • Relevant results are presented and systematically compared using Diebold-Mariano test. This paper focuses on the development of shallow and deep neural networks in the form of multi-layer perceptron, long-short term memory, and gated recurrent unit to model the short-term load forecasting problem. Different model architectures are tested, and global climate model information is used as input to generate more accurate forecasts. A real study case is presented for the Brazilian interconnected power system and the results generated are compared with the forecasts from the Brazilian Independent System Operator model. In general terms, results show that the bidirectional versions of long-short term memory and gated recurrent unit produce better and more reliable predictions than the other models. From the obtained results, the recurrent neural networks reach Nash-Sutcliffe values up to 0.98, and mean absolute percentile error values of 1.18%, superior than the results obtained by the Independent System Operator models (0.94 and 2.01% respectively). The better performance of the neural network models is confirmed under the Diebold-Mariano pairwise comparison test. [ABSTRACT FROM AUTHOR]