Abstract
Abstract
Many of the deep learning solutions for electricity consumption forecasting reported
in the literature include complex neural networks that may not be directly employed
by the practitioner in the field. Throughout this study, we first demonstrate how the
standard deep neural networks (DNN), i.e. convolutional neural network (CNN),
long short-term memory (LSTM), and primitive methods, i.e. arima, random forest
perform on univariate electricity consumption dataset. Then, we build hybrid models
in order to test them on the newly formed multivariate dataset by combining weather
and electricity datasets and show that they perform better on this dataset than the
single models do on the univariate dataset. After doing this, we propose a hybrid
model that utilizes data fusion approach, called shortly Fusion model. Fusion model
consists of a single model that runs on a univariate dataset and a hybrid model that
runs on a multivariate dataset. The predicted values by these 2 submodels are fed
to a linear regression. As a result, we show that the overall result of the Fusion model
is better than any submodels’ results. The proposed Fusion model outperforms RF,
Arima, CNN, CNN+LSTM, LSTM+LSTM and kCNN-LSTM models on Pittsburgh,
Chicago electricity consumption and IHEC datasets. The RMSE scores are improved
by average value of 0.0732. Moreover, we show the usability of transfer learning
in case of lack of data, size of which is not necessary to fully train a model. Lastly,
we attach our findings related to the effect of preprocessing techniques and hybridization
of the transformer model for the electric consumption forecasting task.