Additive Ensemble Neural Network with Constrained Weighted Quantile Loss for Probabilistic Electric-Load Forecasting.

Forecasts in this area have been historically treated with time-series statistical analysis methods, e.g., autoregressive integrated moving average (ARIMA) [ 4 ], with a clear trend towards the use of machine learning techniques [ 5 ], and with emphasis on the application of generic neural network (NN) models [ 6 ] and especially deep learning (DL) models [ 7 , 8 ].

also in 19,460 other papers