Deep Learning based Models for Solar Energy Prediction (original) (raw)

Solar energy becomes widely used in the global power grid. Therefore, enhancing the accuracy of solar energy predictions is essential for the efficient planning, managing and operating of power systems. To minimize the negatives impacts of photovoltaics on electricity and energy systems, an approach to highly accurate and advanced forecasting is urgently needed. In this paper, we studied the use of Deep Learning techniques for the solar energy prediction, in particular Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU). The proposed prediction methods are based on real meteorological data series of Errachidia province, from 2016 to 2018. A set of error metrics were adopted to evaluate the efficiency of these models for real-time photovoltaic forecasting, to achieve more reliable grid management and safe operation, in addition to improve the cost-effectiveness of the photovoltaic system. The results reveal that RNN and LSTM outperform slightly GRU thanks to their capacity to maintain long-term dependencies in time series data.