Time series of dynamic system resources typically exhibit complex long- and short-term dependencies, posing significant challenges for accurate multi-step forecasting. To address the limitations of conventional single-architecture models in capturing both global patterns and local dynamics, this paper proposes an enhanced multivariate forecasting model, PatchTST_SLG(Serial LSTM-GRU). This model utilizes the Patch Time Series Transformer (PatchTST) as the backbone to extract global dependencies from long sequences and serially integrates Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) modules at the output to smooth prediction trajectories and correct local errors. Experiments on the Abilene dataset demonstrate that the proposed model significantly outperforms baseline models, including LSTM, GRU, and the original PatchTST, achieving substantial reductions in MAE and RMSE. The results confirm the effectiveness of this serial structure and its significant contribution to improving predictive stability.
Jianwei Guo, Shuaiyuan Feng, Yuanxin Gao et al.· 2026 IEEE International Conf...· 0 citations
The rapid growth of Internet applications has led to increasingly complex network traffic, posing new challenges for accurate long-term forecasting. To address the limitations of traditional linear models in capturing nonlinear temporal dependencies, this paper proposes an improved TSM-Transformer model that introduces a Trend Attention module for long-term tendencies and a Seasonal Attention module for periodic variations. The model also optimizes encoder–decoder fusion to enhance information interaction. Experiments on the Traffic_One_Cell dataset demonstrate that the proposed model achieves the lowest MAE (1.2 × 10⁻3) and RMSE (2.9 × 10⁻3) with an R2 of 92.1%, outperforming ARIMA, GRU, and SVM baselines. The results confirm the model’s superiority in long-horizon network traffic prediction, providing reliable support for proactive resource allocation and network management.
Yuanxin Gao, Jianping Wu, Lei Liu et al.· 2026 IEEE International Conf...· 0 citations