Short-term power prediction of the photovoltaic power generation on the basis of the AOA-DELM

To enhance the accuracy of short-term power prediction for photovoltaic (PV) power generation and ensure stable power system operations following the grid connection of PV power plants, a combined model is proposed. This model utilises an Algorithmic Optimisation Algorithm (AOA) to optimise a Deep Extreme Learning Machine (DELM) for short-term power prediction of PV power generation. The DELM model's hyperparameters are optimised with AOA to predict the PV data's output power. The simulation results show that for measured data of a PV power plant in the Australian region, the AOA-DELM model has greater power prediction accuracy compared to other prediction models. This verifies the efficacy and adaptability of the model.