Short-term offshore wind power combined prediction method

The invention discloses a short-term offshore wind power combined prediction method, and the method comprises the steps: obtaining offshore wind power data, inputting the offshore wind power data into an LSTM-LSSVM combined prediction model, and obtaining a prediction result of the short-term offshore wind power; wherein the LSTM-LSSVM combined prediction model is obtained through training of a training data set, and the LSTM-LSSVM combined prediction model comprises an LSTM prediction model based on an improved seagull algorithm and an LSSVM prediction model based on an improved whale algorithm. According to the invention, accurate prediction of the short-term wind power of the offshore wind plant is finally realized. 本发明公开了一种短期海上风电功率组合预测方法，包括：获取海上风电功率数据，将所述海上风电功率数据输入LSTM-LSSVM组合预测模型中，获得短期海上风电功率的预测结果；其中，LSTM-LSSVM组合预测模型通过训练数据集训练获得，LSTM-LSSVM组合预测模型包括基于改进型海鸥算法的LSTM预测模型和基于改进型鲸鱼算法的LSSVM预测模型。本发明最终实现海上风电场短期风电功率的精确预测。