A network traffic prediction method based on neural network and linear regression

By using the NA-MEMD algorithm to determine the correlation between gateway devices and constructing joint or classified neural networks and linear regression models, the accuracy problem caused by ignoring the impact between devices in network traffic prediction is solved, achieving higher prediction accuracy.

CN120342894BActive Publication Date: 2025-09-23FOSHAN UNIVERSITY
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510822922.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-19
Publication Date
2025-09-23
Estimated Expiration
2045-06-19

AI Technical Summary

Technical Problem

Existing technologies fail to effectively determine whether two gateway devices affect each other in network traffic prediction, resulting in reduced prediction accuracy.

Method used

The NA-MEMD algorithm is used to decompose historical network traffic data to determine whether there is a strong correlation between two gateway devices, and a joint or classification neural network and linear regression model are constructed based on the correlation for prediction.

Benefits of technology

The accuracy of network traffic prediction is improved, and targeted modeling is performed by considering the mutual influence between gateway devices, thereby improving the accuracy of prediction results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120342894B_ABST
    Figure CN120342894B_ABST
Patent Text Reader

Abstract

The present invention discloses a network traffic prediction method based on neural networks and linear regression, comprising the following steps: S1. For two gateway devices with a network connection, historical network traffic data within a first time period is collected to obtain historical network traffic sequences of the two gateway devices within the first time period; S2. NA-MEMD algorithm is used to decompose , and then determine whether there is a strong correlation between and ; S3. Based on whether there is a strong correlation between and , a network traffic prediction model is trained; S4. Network traffic prediction is performed using the trained network traffic prediction model. The present invention can access historical network traffic data, determine whether two gateway devices have a strong correlation, and perform targeted joint or classified modeling to achieve network traffic prediction, thereby improving the accuracy of the prediction.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Short-term power load prediction method based on long and short-term memory network combination

    CN115169703A

  • Network traffic prediction method, model training method and device

    CN116506305A