A New Hybrid Forecasting Model for Solar Energy Output

In recent years, photovoltaic solar power plants have been widely adopted worldwide due to their favorable energy potential and accessibility. However, despite its accessibility, the output power characteristics of solar energy are inherently unstable. When integrating this energy generation into the power grid, the presence of unbalanced electric currents can adversely affect various control components of the system. Consequently, there is a growing demand for accurate short-term power forecasting. This paper introduces a novel hybrid model to address the aforementioned challenge. The proposed method encompasses three interconnected networks: Boost by Refinement (BF), Mixture of Experts (MoE), and Enhanced MoE (EMoE). Within these networks, the problem space is initially divided into distinct classes, which are then combined using a specific approach. The obtained results provide compelling evidence supporting the effectiveness and superiority of the proposed method.