MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual Network
Time series is a huge quantity of data related to time sequence in real life and its forecast remains challenging. In this paper, a deep learning model, which is called MSRN-Informer (Multi-scale Residual Network Improved Informer) model, is proposed to enhance the precision of time series forecast....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10164113/ |
| _version_ | 1797787420583788544 |
|---|---|
| author | Xiaohui Wang Mengchen Xia Weiwei Deng |
| author_facet | Xiaohui Wang Mengchen Xia Weiwei Deng |
| author_sort | Xiaohui Wang |
| collection | DOAJ |
| description | Time series is a huge quantity of data related to time sequence in real life and its forecast remains challenging. In this paper, a deep learning model, which is called MSRN-Informer (Multi-scale Residual Network Improved Informer) model, is proposed to enhance the precision of time series forecast. A multi-scale structure is added in Informer model to extract data features of different scales, and a residual network is applied to reduce data loss, which can reduce the waste of significant resources and overfitting caused by increasing the depth of the network in traditional improvement methods. To prove the effectiveness of the presented MSRN-Informer model, it is compared with Informer, Informer + and ARIMA methods on four datasets. The results show that MSRN-Informer has a better prediction ability and show a reduced error. The research findings of this paper can be potentially used as reliable reference and basis for effective time series prediction. |
| first_indexed | 2024-03-13T01:21:41Z |
| format | Article |
| id | doaj.art-ba893bfb459343de9d00da90fc730b51 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T01:21:41Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ba893bfb459343de9d00da90fc730b512023-07-04T23:00:17ZengIEEEIEEE Access2169-35362023-01-0111650596506510.1109/ACCESS.2023.328982410164113MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual NetworkXiaohui Wang0Mengchen Xia1https://orcid.org/0000-0001-8221-9660Weiwei Deng2School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, ChinaTime series is a huge quantity of data related to time sequence in real life and its forecast remains challenging. In this paper, a deep learning model, which is called MSRN-Informer (Multi-scale Residual Network Improved Informer) model, is proposed to enhance the precision of time series forecast. A multi-scale structure is added in Informer model to extract data features of different scales, and a residual network is applied to reduce data loss, which can reduce the waste of significant resources and overfitting caused by increasing the depth of the network in traditional improvement methods. To prove the effectiveness of the presented MSRN-Informer model, it is compared with Informer, Informer + and ARIMA methods on four datasets. The results show that MSRN-Informer has a better prediction ability and show a reduced error. The research findings of this paper can be potentially used as reliable reference and basis for effective time series prediction.https://ieeexplore.ieee.org/document/10164113/Time seriesinformer1D-CNNmulti-scaleresidual network |
| spellingShingle | Xiaohui Wang Mengchen Xia Weiwei Deng MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual Network IEEE Access Time series informer 1D-CNN multi-scale residual network |
| title | MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual Network |
| title_full | MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual Network |
| title_fullStr | MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual Network |
| title_full_unstemmed | MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual Network |
| title_short | MSRN-Informer: Time Series Prediction Model Based on Multi-Scale Residual Network |
| title_sort | msrn informer time series prediction model based on multi scale residual network |
| topic | Time series informer 1D-CNN multi-scale residual network |
| url | https://ieeexplore.ieee.org/document/10164113/ |
| work_keys_str_mv | AT xiaohuiwang msrninformertimeseriespredictionmodelbasedonmultiscaleresidualnetwork AT mengchenxia msrninformertimeseriespredictionmodelbasedonmultiscaleresidualnetwork AT weiweideng msrninformertimeseriespredictionmodelbasedonmultiscaleresidualnetwork |