HydroFlow: Towards probabilistic electricity demand prediction using variational autoregressive models and normalizing flows
HydroFlow: Towards probabilistic electricity demand prediction using variational autoregressive models and normalizing flows
复制标题
DOI：
10.1002/int.22864
复制
发表时间：
2022-03
影响因子：
7
通讯作者：
Fan Zhou;Zhiyuan Wang;Ting Zhong;Goce Trajcevski;A. Khokhar
中科院分区：
文献类型：
--
作者：
Fan Zhou;Zhiyuan Wang;Ting Zhong;Goce Trajcevski;A. Khokhar
我们提出了HydroFlow，这是一种用于预测大型水电站发电需求的新型深度生成模型。HydroFlow使用潜在随机递归神经网络来捕获多变量时间序列中的依赖关系。它不仅利用了神经网络的隐状态，而且考虑了与自然和社会因素有关的变量的不确定性。我们还引入了一种基于生成流的端到端方法，以精确的似然来近似时间序列的后验分布。我们的模型是强大的，因为它增加了不同因素的随机性（例如，水库容量和水流量测量），从而克服了确定性预测方法的表达局限性。它还支持可训练的潜在转换，可以提高模型的可解释性。我们根据从一家大型水电开发公司的水电站收集的数据对HydroFlow进行了评估。实验结果表明，我们的模型显着优于最先进的基线方法，同时提供可解释的结果。
We present HydroFlow, a novel deep generative model for predicting the electricity generation demand of large‐scale hydropower stations. HydroFlow uses a latent stochastic recurrent neural network to capture the dependencies in the multivariate time series. It not only utilizes the hidden state of the neural network, but also considers the uncertainty of variables related to natural and social factors. We also introduce an end‐to‐end approach based on generative flows to approximate the posterior distribution of time series with exact likelihoods. Our model is powerful as adding stochasticity to different factors (e.g., reservoir capacity and water‐flow measurements) and thus overcomes the expressiveness limitations of deterministic prediction methods. It also enables trainable latent transformations that can improve the model interpretability. We evaluate HydroFlow on the data collected from the hydropower stations of a large‐scale hydropower development company. Experimental results show that our model significantly outperforms the state‐of‐the‐art baseline methods while providing explainable results.