Time series online forecasting based on sequence decomposition learning networks

Research on time series online modeling has received much attention in recent years. The existing advanced methods are often accompanied by the problem of low model established efficiency, so it is difficult to realize online modeling in practical applications. This paper proposed a sequence decomposition learning networks (SDLN) to solve time series online forecasting problems. In contrast to most time series forecasting methods, SDLN is a novel time series online forecasting method without capturing sliding time window features. The SDLN consists of five layers of neurons, namely, the input layer, decomposition layer, sparse layer, hidden layer, and output layer, where the additions of the decomposition layer and sparse layer enable a fast model calculation speed and do not require the capture of sliding time window features. In addition, it can establish time series forecasting models with better model accuracy and model stability in a very short model calculation time. To verify the effectiveness of SDLN, eight publicly available time series datasets are applied. Experimental results show that SDLN can obtain better model performance than other state-of-the-art methods, especially in terms of model computation speed. It can achieve a model accuracy of 10-4 to 10-2 and a model computation time of 10-2 seconds for short-and medium-term forecasting on all eight datasets. Therefore, SDLN is an effective time series online modeling method.

Automated summary

This study proposes a novel method, SDLN, for time series online forecasting without capturing sliding time window features. By adding decomposition and sparse layers, SDLN achieves fast model calculation speed and better model accuracy and stability in a short time. Experimental results show that SDLN outperforms other state-of-the-art methods in terms of model computation speed and achieves high accuracy and fast computation time for short- and medium-term forecasting across different datasets.