| 基于周期性建模的时间序列预测方法及电价预测研究 |
| |
| 引用本文： | 徐任超, 阎威武, 王国良, 杨健程, 张曦. 基于周期性建模的时间序列预测方法及电价预测研究. 自动化学报, 2020, 46(6): 1136−1144 doi: 10.16383/j.aas.c180712 |
| |
| 作者姓名： | 徐任超 阎威武 王国良 杨健程 张曦 |
| |
| 作者单位： | 1.上海交通大学电子信息与电气工程学院 上海 200240;;2.系统控制与信息处理教育部重点实验室 上海 200240;;3.上海工程技术大学 电子电气工程学院 上海 201620;;4.南方电网国际有限责任公司 广州 510630 |
| |
| 基金项目： | 国家重点研究发展计划基金(2019YFB1705702), 国家自然科学基金(60974119, 61533013)资助 |
| |
| 摘 要： | 时间序列数据广泛存在于人类的生产生活中, 通常具有复杂的非线性动态和一定的周期性. 与传统的时间序列分析方法相比, 基于深度学习的方法更能捕捉数据的深层特性, 对具有复杂非线性的时间序列有较好的建模效果. 为了在神经网络中显式地建模时间序列数据的周期性和趋势性, 本文在循环神经网络的基础上引入了周期损失和趋势损失, 建立了基于周期性建模和多任务学习的时间序列预测模型. 将模型应用到欧洲能源交易所法国市场的能源市场价格预测中, 结果表明周期损失和趋势损失能够提高神经网络的泛化能力, 并提高预测时间序列趋势的精度.
|
| 关 键 词： | 时间序列预测 深度学习 循环神经网络 周期趋势建模 |
| 收稿时间： | 2018-10-31 |
Time Series Forecasting Based on Seasonality Modeling and Its Application to Electricity Price Forecasting |
| |
| Xu Ren-Chao, Yan Wei-Wu, Wang Guo-Liang, Yang Jian-Cheng, Zhang Xi. Time series forecasting based on seasonality modeling and its application to electricity price forecasting. Acta Automatica Sinica, 2020, 46(6): 1136−1144 doi: 10.16383/j.aas.c180712 |
| |
| Authors: | XU Ren-Chao YAN Wei-Wu WANG Guo-Liang YANG Jian-Cheng ZHANG Xi |
| |
| Affiliation: | 1. School of Electronic Information and Electrical Engineering, Shanhai Jiao Tong University, Shanghai 200240;;2. Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240;;3. Shanghai University of Engineering Science, Shanghai 201620;;4. China Southern Power Grid International Co., Ltd., Guangzhou 510630 |
| |
| Abstract: | Time series data exist widely in human production and life. The real time series data often contain complex nonlinear dynamics and seasonality. Compared with traditional time series analysis methods, deep learning based methods have good modeling effect for the time series with complex nonlinearities but fail to model the seasonality and trend of time series. In order to model the seasonality and trending explicitly in neural networks, this paper introduces seasonal loss and trend loss into recurrent neural networks (RNNs), establishing the time series prediction model based on seasonality modeling and multi-task learning. The suggested method is then applied to the electricity price forecasting on EPEX (European Power Exchange) France market. The experiment results show that seasonal loss and trend loss can improve the generation ability of neural networks and the performance of sequence trend forecasting. |
| |
| Keywords: | Time series forecasting deep learning recurrent neural networks (RNNs) seasonality and trend modeling |
|
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
