The transformer-based short-term photovoltaic power forecasting

To improve the accuracy of photovoltaic power forecasting and ensure optimal scheduling and stable operation of power systems, a Transformer-based short-term photovoltaic power forecasting model is proposed. First, historical data is analysed to identify key meteorological features. Then, a multi-head attention mechanism is introduced to construct a Transformer-based model for short-term photovoltaic power forecasting. Finally, case studies are conducted, and the results show that the proposed model effectively improves the accuracy of photovoltaic power prediction, with the root mean square error reduced by 20.88% compared to the recurrent neural network model and by 20.32% compared to the long short-term memory model.