Development of MVMD-EO-LSTM Model for a Short-Term Photovoltaic Power Prediction

The accuracy and stability of short-term photovoltaic (PV) power prediction is crucial for planning dispatching in a grid system. For this reason, the multi-resolution variational modal decomposition (MVMD) method proposed to achieve multi-scale input features mining PV prediction. Here, MVMD combined with Spearman extracts correlation weather data. An equilibrium optimizer (EO) integrated optimal values long memory (LSTM) parameters. Firstly, determined selected by Spearman. model used mine high solar radiation conduct cross-correlation analysis extract feature components. Secondly, similar days sample set are classified ensure good adaptability different situations. Finally, introduced into EO optimized LSTM. Performance using actual output data from plant shows that extraction can effectively an dataset under seasons. Compared gray wolf particle swarm optimization algorithms, has better performance low discrimination components power.