D-CTNet: A Dual-Branch Channel-Temporal Forecasting Network with Frequency-Domain Correction

TL;DR

D-CTNet is a novel dual-branch neural network that improves multivariate time series forecasting by decoupling intra-channel patterns, modeling long-range dependencies, and correcting non-stationarity in the frequency domain, enhancing accuracy and robustness.

Contribution

The paper introduces D-CTNet, a dual-branch network with frequency-domain correction for better handling non-stationarity and complex dependencies in multivariate time series forecasting.

Findings

Outperforms state-of-the-art methods on seven benchmark datasets.

Effectively models long-range dependencies with global patch attention.

Successfully suppresses distribution shift impacts via spectrum alignment.

Abstract

Accurate Multivariate Time Series (MTS) forecasting is crucial for collaborative design of complex systems, Digital Twin building, and maintenance ahead of time. However, the collaborative industrial environment presents new challenges for MTS forecasting models: models should decouple complex inter-variable dependencies while addressing non-stationary distribution shift brought by environmental changes. To address these challenges and improve collaborative sensing reliability, we propose a Patch-Based Dual-Branch Channel-Temporal Forecasting Network (D-CTNet). Particularly, with a parallel dual-branch design incorporating linear temporal modeling layer and channel attention mechanism, our method explicitly decouples and jointly learns intra-channel temporal evolution patterns and dynamic multivariate correlations. Furthermore, a global patch attention fusion module goes beyond the local window scope to model long range dependencies. Most importantly, aiming at non-stationarity, a Frequency-Domain Stationarity Correction mechanism adaptively suppresses distribution shift impacts from environment change by spectrum alignment. Evaluations on seven benchmark datasets show that our model achieves better forecasting accuracy and robustness compared with state-of-the-art methods. Our work shows great promise as a new forecasting engine for industrial collaborative systems.