An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation

With the expansion of grid-connected solar power generation, the variability of photovoltaic power generation has become increasingly pronounced. Accurate photovoltaic output prediction is necessary to ensure power system stability. In this work, an inertia weighting strategy and the Cauchy mutation operator are introduced to improve the moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation. The former balances the search and mining capabilities at the population location search equation, and the latter helps to increase the diversity of the masses and to void avoid entrapment into local optima. Various meteorological conditions affecting the photovoltaic power generation are discussed and the experimental input data is optimized by grey relational analysis. The results using multiple test functions and the real data of photovoltaic power station in Australia have verified that the proposed model has better optimization performance compared with other models. The proposed method contributes to improve photovoltaic energy prediction, reduces the impact of photovoltaic power penetration into the grid, and maintains the system reliability.