摘要
中国经济的快速增长推动了电网的扩张。电力变压器是电网工程中的关键设备，其价格变化对造价控制有着重大影响。然而，电力变压器材料价格表现为非平稳和非线性的序列。因此，电网工程的设备购置费估算困难，阻碍了电力工程的正常建设。为了更准确地预测电力变压器材料价格，本研究提出了一种基于互补集合经验模态分解（CEEMD）和门控循环单元（GRU）网络的方法。首先，CEEMD 将价格序列分解为多个固有模态函数（IMF）。根据每个 IMF 的样本熵，对多个 IMF 进行聚类，以获得多个聚合序列。然后，对样本熵较大的聚合序列进行经验小波变换（EWT），再利用 GRU 模型对分解得到的多个子序列进行预测；对样本熵较小的聚合序列利用 GRU 模型直接进行预测。最后，我们使用了电力变压器材料价格的真实历史数据来验证所提出的方法。结果表明所提方法在两个数据集上都很有效，平均绝对百分比误差（MAPE）分别小于1%和3%，对未来电力变压器材料价格预测领域的研究具有重要的参考价值。
Price prediction of power transformer materials based on CEEMD and GRU
基于CEEMD和GRU的电力变压器材料价格预测
Yan Huang,Yufeng Hu,Liangzheng Wu,Shangyong Wen,Zhengdong Wan
1.Energy Development Research Institute,China Southern Power Grid,Guangzhou 510623,P.R.China
2.China Southern Power Grid,Guangzhou 510623, P.R.China
收听作者1分钟语音介绍
Abstract
Keywords
Power transformer material; Price prediction; Complementary ensemble empirical mode decomposition; Gated recurrent unit; Empirical wavelet transform
Fig. 1 Price prediction framework for power transformer materials based on complete ensemble empirical mode decomposition (CEEMD) and gated recurrent unit (GRU)
Fig. 2 Flowchart of CEEMD
Fig. 3 GRU model structure
Fig. 4 Electrolytic copper price change trend chart
Fig. 5 CEEMD decomposition results of price sequence of Dataset 1
Fig. 6 Prediction results of the three aggregation sequences of Datasets 1 and 2
Fig. 7 Comparison of the prediction results of each model on Dataset 1
Fig. 8 Comparison of the prediction results of each model on Dataset 2
本文引文信息
Huang Y, Hu Y F,Wu L Z, et al. (2023) Price prediction of power transformer materials based on CEEMD and GRU, Global Energy Interconnection, 7(2): 217-227
黄琰，胡玉峰，吴良峥等 (2023) 基于CEEMD和GRU的电力变压器材料价格预测. 全球能源互联网（英文）, 7(2): 217-227
Biographies
Yan Huang
Yan Huang received a master’s degree from North China Electric Power University, Beijing, in 2005. She is working at the Energy Development Research Institute, China Southern Power Grid. Her research interests include economic engineering and project management.
Yufeng Hu
Yufeng Hu received a Ph.D. degree in power system automation from Huazhong University of Science and Technology, Wuhan, in 2004. He is working at the China Southern Power Grid. His research interests include power system automation and related scientific innovation.
Liangzheng Wu
Liangzheng Wu received a master’s degree from Jilin University, Changchun, in 2007. He is working at the Energy Development Research Institute, China Southern Power Grid. His research interests include preroject evaluation, post-project evaluation, and project management.
Shangyong Wen
Shangyong Wen received a master’s degree from Wuhan University, Wuhan, in 2001. He is working at the Power Construction Quota Station, China Southern Power Grid. His research interests include technological economics and project management.
Zhengdong Wan
Zhengdong Wan received his master’s degree from Harbin Institute of Technology. Harbin, in 2009, He is working at the Energy Development Research Institute, China Southern Power Grid. His research interests include economic engineering and cost study of power grid projects.
编辑：王彦博
审核：王 伟
郑重声明
根据国家版权局相关规定，纸媒、网站、微博、微信公众号转载、摘编本微信作品，需包含本微信名称、二维码等关键信息，并在文首注明《全球能源互联网》原创。
个人请按本微信原文转发、分享。
分享优秀论文，帮小编点个 “在看” 哦
