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. 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.

Automated summary

In this paper, a deep learning model called MSRN-Informer is proposed to enhance the precision of time series forecast. The model utilizes a multi-scale structure to extract data features of different scales and applies a residual network to reduce data loss. Compared with other methods, MSRN-Informer shows better prediction ability and reduced error. The research findings of this paper can serve as a reliable reference and basis for effective time series prediction.