Multivariate Deep Learning Bidirectional LSTM Model for Forecasting Solar Radiation

The rising demand for green energy is resulting in the global proliferation of solar power plants. The power output of solar plants relies on solar radiation, which is influenced by weather conditions. Effectively forecasting solar radiation is a key factor in the successful integration of solar power plants into the grid. This work aims to develop a Bidirectional Long Short-Term Memory (Bi-LSTM) based multivariate deep learning (DL) model to forecast solar radiation. To build the DL model, the wind speed and ambient temperature along with solar radiation have been taken as input. The effectiveness of the proposed forecasting model is measured using statistical indices like Mean Absolute Error (MAE), Mean Square Error (MSE), and R2 Error. The presented DL model demonstrates superior performance metrics, with MAE of 0.0356, MSE of 0.0051, and R2 values of 0.92. The high-quality meteorological data for Delhi is used to develop the model. A comparative analysis is carried out with other DL models to validate the obtained results. The proposed model is found to be accurate, and it can be useful for smart grid applications to maintain grid stability, reliability, and power quality.