本文已被：浏览 1746次 下载 759次
投稿时间：2020-04-08
投稿时间：2020-04-08
中文摘要: 基于循环神经网络的模型具有出色的捕获非线性关系的能力，在电量预测中具有良好的性能。但它无法完全捕获历史信息，影响了预测结果的准确性。为了解决这些问题，提出了一种门控循环单元（GRU）模型结合STL分解的方法。评估结果表明，该方法能较好地捕获局部和全局信息，并具有比传统模型更高的预测精度。
Abstract:Recurrent Neural Network based models have good performance in electricity forecasting because of their excellent ability to capture non-linear relationships.However,they cannot fully capture historical information,which has an impact on prediction accuracy.In order to address these problems,we propose a method by combining STL decomposition and gated recurrent unit(GRU) model.The proposed scheme is validated,and the simulation results show that our proposed method can perfectly capture local and global information and achieve higher prediction accuracy than traditional models.
keywords: gated recurrent unit short-term electricity forecasting recurrent neural network deep learning time series decomposition
文章编号：20205001 中图分类号：TM715;TP18 文献标志码：
基金项目:国家自然科学基金（61702321）。
引用文本：
李晋国,周绍景,李红娇.GRU结合STL分解的短期电量预测方法[J].上海电力大学学报,2020,36(5):415-420.
LI Jinguo,ZHOU Shaojing,LI Hongjiao.A Short-term Electricity Forecasting Method Based on GRU and STL Decomposition[J].Journal of Shanghai University of Electric Power,2020,36(5):415-420.
李晋国,周绍景,李红娇.GRU结合STL分解的短期电量预测方法[J].上海电力大学学报,2020,36(5):415-420.
LI Jinguo,ZHOU Shaojing,LI Hongjiao.A Short-term Electricity Forecasting Method Based on GRU and STL Decomposition[J].Journal of Shanghai University of Electric Power,2020,36(5):415-420.