Domestic Solar Photovoltaic Generation Prediction Based on Hybrid Machine Learning Models in the Presence of Uncertain Weather

To provide effective data support for the operation and scheduling strategies of the power grid, and reduce the harm caused by large-scale grid connection of new energy generation, accurate prediction of power generation is crucial. This paper proposes a domestic solar photovoltaic generation prediction based on hybrid machine-learning models in the presence of uncertain weather. The proposed solution is assessed through experiments and the numerical results confirmed the effectiveness of the proposed solution. The hybrid model designed in this work has stronger robustness and information extraction ability compared to other single network models, which can produce better prediction results.