Intelligent prediction of short-term photovoltaic power output based on PSO-RF and LASSO-penalized multi-kernel learning-based robust regression algorithm

The utilization of solar energy plays a significant role in alleviating the energy crisis and promoting sustainable development. However, photovoltaic (PV) power generation is impacted by several complex factors that cause discontinuity and randomness problems. This paper presents a novel approach to improving the precision of PV power forecasting, based on a LASSO-penalized multi-core learning-based robust regression algorithm with random forest (RF) optimization. This was further enhanced using particle swarm optimization (PSO). Initially, the PSO-RF was employed to identify the key variables influencing the PV output power. Second, the issue of a shallow Gaussian multi-core structure was addressed by employing the multi-kernel learning (MKL) method, which was used to construct a highly robust depth mapping kernel based on the multi-layer information of deep neural networks. A multiscale Gaussian kernel was combined with a kernel matrix to create an improved kernel. This paper presents a novel computational approach based on local quadratic approximation for solving models. The findings indicate that the robust multi-core sparse prediction model developed in this paper achieves enhanced prediction accuracy and robustness. Regarding the coefficient of determination, the PSORF-LPMKLRRA model achieves the highest value of 0.998, demonstrating a closer approximation to 1 than the alternative predictive models.