Cellular traffic prediction method based on multi-level signal decomposition and dual-branch deep network fusion

By combining multi-level signal decomposition with dual-branch deep network fusion, the problem of insufficient accuracy in cellular traffic prediction is solved, achieving high-precision and stable prediction of cellular traffic and improving the accuracy and stability of traffic prediction.

CN121531406APending Publication Date: 2026-02-13XUCHANG UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202511737352.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-25
Publication Date
2026-02-13

AI Technical Summary

Technical Problem

Existing cellular traffic forecasting methods have limited accuracy when dealing with nonlinear relationships, long-range dependencies, and sudden fluctuations. Furthermore, deep learning models are prone to gradient vanishing or exploding, making it difficult to achieve high-precision and stable traffic forecasting.

Method used

A method combining multi-level signal decomposition and dual-branch deep network is adopted. Multi-level signal decomposition extracts multi-scale features of traffic, and the BiTCN-MHA network and ResNet-18 branch are combined to form a dual-branch deep network to dynamically fuse features and achieve high-accuracy prediction.

Benefits of technology

It improves the accuracy and stability of cellular traffic forecasting, effectively captures long-term traffic trends and short-term details, and enhances the ability to express complex traffic patterns.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a cellular traffic prediction method based on multi-level signal decomposition and dual-branch deep network fusion. Aiming at the defects of non-stationarity, high volatility and noise aliasing existing in a cellular traffic sequence, the method comprises the following steps: firstly, standardizing acquired data through missing value interpolation, anomaly elimination and z-score standardization; then, through the flow sequence subjected to multi-level signal decomposition standardization processing, four links of TVFEMD decomposition, component screening, EWT decomposition and multi-channel splicing are sequentially carried out, and multi-channel feature tensors spliced along the time dimension are output; a double-branch deep network composed of an internal time sequence branch BiTCN-MHA and an external environment branch ResNet-18 is constructed on a model level; a branch A captures multi-scale bidirectional dependence of a multi-channel feature tensor through forward and reverse expansion causal convolution, gating dynamic fusion and a multi-head attention mechanism; the branch B is used for deeply extracting nonlinear features of the standardized environment feature matrix by using a residual structure; and after the features of the two branches are spliced, a standardized domain prediction value is output through a full connection layer, and a physical quantity outline is recovered through anti-standardization to obtain a final cellular traffic prediction result.
Need to check novelty before this filing date? Find Prior Art