Hybrid Artificial Neural Networks for Electricity Consumption Prediction
Journal: International Journal of Advanced Engineering Research and Science (Vol.9, No. 08)Publication Date: 2022-08-12
Authors : Ricardo Augusto Manfredini;
Page : 292-299
Keywords : Artificial Neural Network; Artifial Inteligence; eletricity consumption predictions; time series.;
Abstract
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.
Other Latest Articles
- Waste of Electrical and Electronic Equipment (WEEE): Analysis of the Knowledge of Direct Users
- Strategic Planning and Territorial Development: A New Methodological Construction from those affected by the Sobradinho-BA Dam
- Miguel Ferrante´s Seringal: human exploitation and violence in Amazonian rubber plantations
- A Timeline of the Risk Field: Bridging Fundamental Achievements and Modern Research
- Quality of Life of Military Policemen in a Western Amazon State in Times of the Covid-19 Pandemic
Last modified: 2022-08-23 15:00:03