Time Series Forecasting of Solar Energy Production Data Using LSTM

Balbal K. F., Çelik Ö., İkikardeş S.

Journal of Artificial Intelligence and Data Science (JAIDA), vol.3, no.2, pp.116-123, 2023 (Peer-Reviewed Journal)


The fact that countries have increased the use of renewable energy resources in order to meet increasing energy demands has brought to light the fact that the components and energy production amounts of the solar energy systems to be installed must be estimated accurately. With the benefits provided by developing technology, forecasting calculations of these variable natural energy resources have become much more economical by using machine learning methods. In this context, this study proposes a deep learning-based methodology that includes LSTM-based tuned models for PV power forecasting, with univariate time series estimation of the amount of power obtained from a solar energy system integrated on a factory roof. When the created models are compared, the results show that the model approach named LSTM13 provides the most accurate prediction performance with the lowest RMSE metric value of 0.1470 among the other proposed models.