Hybrid Artificial Neural Networks for Electricity Consumption Prediction

Ricardo Augusto Manfredini

Artificial Neural Network, Artifial Inteligence, eletricity consumption predictions, time series.

We present a comparative study of electricity consumption predictions using the SARIMAX method (Seasonal Auto Regressive Moving Average eXogenous variables), the HyFis2 model (Hybrid Neural Fuzzy Inference System) and the LSTNetA model (Long and Short Time series Network Adapted), a hybrid neural network containing GRU (Gated Recurrent Unit), CNN (Convolutional Neural Network) and dense layers, specially adapted for this case study. The comparative experimental study developed showed a superior result for the LSTNetA model with consumption predictions much closer to the real consumption. The LSTNetA model in the case study had a rmse (root mean squared error) of 198.44, the HyFis2 model 602.71 and the SARIMAX method 604.58.

Received: 26 Jun 2022, Received in revised form: 14 Jul 2022, Accepted: 22 July 2022, Available online: 19 Aug 2022

10.22161/ijaers.98.32