Electrical Load Consumption and Photovoltaic Power Forecasting using Deep CNN

The modern world is highly dependent on electricity and needs a continuous supply of load demand. During the past decades, renewable energies (REs), as clean and economical sources, have been developed to answer the increasing load demand. However, both renewable energy production and electricity consumption have random characteristics caused by different uncertain factors such as weather conditions and customer behavior. Therefore, it is crucial to simultaneously perform load forecasting and RE generation prediction in areas where most of the demand is supplied by REs. This study proposes a forecasting framework based on a deep three-dimensional convolutional neural network for load forecasting and photovoltaic (PV) power prediction. In this way, power system operators can balance demand and supply based on the predicted values. Also, using the same framework, which is capable of forecasting both load and PV power, would significantly reduce computational costs. The comparative analysis for 15-min, 90-min, 3-h, and 6-h ahead horizon shows that the accuracy of the proposed method increased in all time horizons compared to long short-term memory (LSTM), gated recurrent unit (GRU), and two-dimensional convolutional neural network (Conv2D).