首页 | 本学科首页   官方微博 | 高级检索  
     

基于特征迁移学习的综合能源系统小样本日前电力负荷预测
引用本文:孙晓燕,李家钊,曾博,巩敦卫,廉智勇.基于特征迁移学习的综合能源系统小样本日前电力负荷预测[J].控制理论与应用,2021,38(1):63-72.
作者姓名:孙晓燕  李家钊  曾博  巩敦卫  廉智勇
作者单位:中国矿业大学信息与控制工程学院,江苏徐州221116;新能源电力系统国家重点实验室(华北电力大学),北京102206;太原煤气化龙泉能源发展有限公司,山西太原030303
基金项目:中央高校基本科研业务费专项资金项目(2020ZDPY0216).
摘    要:基于历史数据和深度学习的负荷预测已广泛应用于以电能为中心的综合能源系统中以提高预测精度,然而,当区域中出现新用户时,其历史负荷数据往往极少,此时,深度学习难以适用.针对此,本文提出基于负荷特征提取和迁移学习的预测机制.首先,依据源域用户历史负荷数据,融合聚类算法和门控循环单元网络构建源域数据的特征提取和分类模型;然后,...

关 键 词:综合能源系统  日前电力负荷预测  特征提取  迁移学习  门控循环单元
收稿时间:2020/5/18 0:00:00
修稿时间:2020/8/19 0:00:00

Small-sample day-ahead power load forecasting of integrated energy system based on feature transfer learning
SUN Xiao-yan,LI Jia-zhao,ZENG Bo,GONG Dun-wei and LIAN Zhi-yong.Small-sample day-ahead power load forecasting of integrated energy system based on feature transfer learning[J].Control Theory & Applications,2021,38(1):63-72.
Authors:SUN Xiao-yan  LI Jia-zhao  ZENG Bo  GONG Dun-wei and LIAN Zhi-yong
Affiliation:School of Information and Control Engineering, China University of Mining and Technology,School of Information and Control Engineering, China University of Mining and Technology,State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources (North China Electric Power University),School of Information and Control Engineering, China University of Mining and Technology,Taiyuan Coal Gasification Longquan Energy Development Co. , Ltd
Abstract:Deep learning-based load forecasting with large size of historical data has been successfully used in integrated energy systems to effectively improve the prediction accuracy. However, when new users join in the system, the historical load data is often very rare, and deep learning is no longer applicable. Motivated by this, we propose a forecasting mechanism based on load feature extraction and transfer learning. Firstly, the feature extraction and classification models of source domain data are constructed through optimal clustering and gated recurrent unit (GRU) training. Then, the trained GRU classification model is used to extract the features and category information of small samples in the target domain to be predicted. A feature fusion strategy based on feature similarity and time forgetting factor is proposed. Finally, according to the fusion characteristics, the load prediction based on transfer learning and feature input is given. The proposed algorithm is applied to the electricity load forecasting of high schools and buildings in Cardiff. The experimental results show the effectiveness of the algorithm in power load forecasting with small size of samples.
Keywords:integrated energy system  day-ahead power load forecasting  feature extraction  transfer learning  gated recurrent unit (GRU)
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《控制理论与应用》浏览原始摘要信息
点击此处可从《控制理论与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号