Ultra-Short-Term Prediction of Photovoltaic Power Based on Periodic Extraction of PV Energy and LSH Algorithm

Ultra-short-term photovoltaic power prediction is one of the important measures to reduce the adverse effects of the safe and stable operation of traditional power systems. First, the periodicity of the PV power is taken into account to extract periodic components. For the remaining components, under different weather types, the local sensitive hashing algorithm algorithm is used to achieve rapid classification of photovoltaic power segments, and the European distance is introduced as a measure of the prediction to predict. Using the data of the photovoltaic power station for verification, the results show that the method has a higher prediction accuracy.