Price Forecasting in the Ontario Electricity Market via TriConvGRU Hybrid Model : Univariate vs. Multivariate Frameworks

Electricity price forecasting is a challenging task for decision-makers in deregulated power markets due to the inherent characteristics of electricity prices, e.g., high frequency and volatility. Accordingly, we propose a novel hybrid Deep Learning model to forecast one-step, two-step, and three-step ahead electricity prices based on a Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU). Our model consists of three consecutive CNN-GRU models combined in parallel with different input data. We downsampled input data via pooling layers at the beginning of two streams of the model to capture different frequencies of price patterns concurrently. Also, a set of external variables, including previous prices, electricity load, generation, import and export, and weather data, were considered in our forecasting models to test whether these features improve the efficiency of the models. Finally, three experiments in various weeks of 2022 were carried out in the Ontario electricity market to assess the model. The results indicate that the proposed model reduced the forecasting error significantly by 63.3% in the first experiment, 41.8% in the second, and 28.2% in the third, on average. Also, the proposed model was compared with several baseline models, including statistical time-series, Machine Learning, and Deep Learning models and outperformed them. Furthermore, the comparison of results in univariate and multivariate settings indicated that adding variables to forecasting models did not help reduce forecasting errors