MTTLA‐DLW: Multi‐task TCN‐Bi‐LSTM transfer learning approach with dynamic loss weights based on feature correlations of the training samples for short‐term wind power prediction
Jifeng Song, Xiaosheng Peng, Jiajiong Song, Zimin Yang, Bo Wang, Jianfeng Che
{"title":"MTTLA‐DLW: Multi‐task TCN‐Bi‐LSTM transfer learning approach with dynamic loss weights based on feature correlations of the training samples for short‐term wind power prediction","authors":"Jifeng Song, Xiaosheng Peng, Jiajiong Song, Zimin Yang, Bo Wang, Jianfeng Che","doi":"10.1002/we.2909","DOIUrl":null,"url":null,"abstract":"Wind power prediction for newly built wind farms is usually faced with the problem of no sufficient historical data. To efficiently extract the useful features from related wind farms, a novel transfer learning method based on temporal convolutional network (TCN)‐Bi‐long short‐term memory (LSTM) with dynamic loss weights is proposed. Firstly, a novel multi‐task TCN‐Bi‐LSTM model is designed to extract common features. The separate TCNs, and common Bi‐LSTM layers of the proposed model are designed to extract the temporal features from related wind farms. Secondly, in the pre‐training stage, to optimize the training process of the neural networks, a dynamic loss‐weighting strategy is proposed for multi‐task learning (MTL) to select the most related features, which increase the prediction accuracy by providing a suitable optimization object. Thirdly, the multi‐task TCN‐Bi‐LSTM model is re‐trained based on the samples from the target wind farm. Finally, a dataset of seven wind farms was employed to evaluate the efficiency of the proposed MTL structure and the dynamic loss‐weighting strategy. The result shows that the root mean squared error of the 12‐h short‐term prediction can be decreased by 4.19% compared with the traditional single‐task learning model, which verifies the validity of the proposed multi‐task transfer learning method.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.0000,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Wind Energy","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1002/we.2909","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
Abstract
Wind power prediction for newly built wind farms is usually faced with the problem of no sufficient historical data. To efficiently extract the useful features from related wind farms, a novel transfer learning method based on temporal convolutional network (TCN)‐Bi‐long short‐term memory (LSTM) with dynamic loss weights is proposed. Firstly, a novel multi‐task TCN‐Bi‐LSTM model is designed to extract common features. The separate TCNs, and common Bi‐LSTM layers of the proposed model are designed to extract the temporal features from related wind farms. Secondly, in the pre‐training stage, to optimize the training process of the neural networks, a dynamic loss‐weighting strategy is proposed for multi‐task learning (MTL) to select the most related features, which increase the prediction accuracy by providing a suitable optimization object. Thirdly, the multi‐task TCN‐Bi‐LSTM model is re‐trained based on the samples from the target wind farm. Finally, a dataset of seven wind farms was employed to evaluate the efficiency of the proposed MTL structure and the dynamic loss‐weighting strategy. The result shows that the root mean squared error of the 12‐h short‐term prediction can be decreased by 4.19% compared with the traditional single‐task learning model, which verifies the validity of the proposed multi‐task transfer learning method.
期刊介绍:
Wind Energy offers a major forum for the reporting of advances in this rapidly developing technology with the goal of realising the world-wide potential to harness clean energy from land-based and offshore wind. The journal aims to reach all those with an interest in this field from academic research, industrial development through to applications, including individual wind turbines and components, wind farms and integration of wind power plants. Contributions across the spectrum of scientific and engineering disciplines concerned with the advancement of wind power capture, conversion, integration and utilisation technologies are essential features of the journal.