Abstract: To further improve the accuracy and stability of short-term forecasting of photovoltaic output power, an adaptive hybrid prediction model based on similar weather clustering, wavelet neural network (WNN) and AdaBoost is proposed. Firstly, the fuzzy C-means (FCM) algorithm is used to divide the initial data set according to different seasons and weather types. Secondly, WNN is selected as the base learner of the improved AdaBoost to build the WNN-AdaBoost model, and the improved hybridizing grey wolf optimization (IHGWO) algorithm is used to optimize the wavelet factor and weight of WNN. Finally, the actual measured output power data of a photovoltaic power station in the central region of China is selected to analyze the calculation example, and the prediction effect is verified by comparison with other models. The results show that the proposed model can obtain better prediction results under different weather types, and it has strong adaptability and robustness while effectively improving the accuracy of photovoltaic short-term output power prediction.