基于深度学习的水力发电预测

Hydropower Prediction Based on Deep Learning

精准的水力发电预测有助于安排检修计划等。为此,文章提出一种基于门控循环单元的水力发电预测模型。首先,采用自适应噪声的完全集合经验模态分解将原始水力发电序列分解为多个序列分量;接着,运用样本熵对所有分量进行复杂度分析后对序列分量进行重构;最后,对重构后的序列分量分别构建门控循环单元进行预测,将所有预测结果进行重构获得最终的预测结果。结合实际算例分析,验证了本文所提模型的有效性。

Accurate hydroelectric prediction helps to arrange maintenance plans and so on.Therefore,a hydraulic power generation prediction model based on gated recurrent unit is proposed.Firstly,the original hydropower generation sequence is decomposed into multiple sequence components by using the complete ensemble empirical mode decomposition of adaptive noise.Secondly,the sample entropy is used to analyze the complexity of all components and then the sequence components are reconstructed.Finally,the gated recurrent unit is constructed to predict the sequence components after reconstruction,and all the prediction results are reconstructed to obtain the final prediction results.The effectiveness of the proposed model is verified by a practical example.