Wavelet-analysis based File-sharing P2P Traffic Prediction Algorithm

AbstractIn this paper, we propose a Gated Recurrent Unit(GRU) neural network traffic prediction algorithm based on transfer learning. By introducing two gate structures, such as reset gate and update gate, the GRU neural network avoids the problems of gradient disappearance and gradient explosion. It can effectively represent the characteristics of long correlation traffic, and can realize the expression of nonlinear, self-similar, long correlation and other characteristics of satellite network traffic. The paper combines the transfer learning method to solve the problem of insufficient online traffic data and uses the particle filter online training algorithm to reduce the training time complexity and achieve accurate prediction of satellite network traffic. The simulation results show that the average relative error of the proposed traffic prediction algorithm is 35.80% and 8.13% lower than FARIMA and SVR, and the particle filter algorithm is 40% faster than the gradient descent algorithm.

Download Full-text

A Novel P2P Business Traffic Prediction Algorithm

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.467-469.1339 ◽

2011 ◽

Vol 467-469 ◽

pp. 1339-1344

Author(s):

Min Wu ◽

Ru Chuan Wang ◽

Jing Li ◽

Zhi Jie Han

Keyword(s):

Traffic Management ◽

Simulation Experiment ◽

P2p Network ◽

Traffic Model ◽

Prediction Algorithm ◽

Traffic Prediction ◽

The Internet ◽

Network Congestion ◽

Time Performance ◽

High Prediction

The increasing P2P network traffic on the Internet has leaded to the problem of network congestion. In the consequence of the diversification of the P2P business and protocol, research on the management of P2P traffic has many problems to resolve. Prediction of the P2P traffic is the kernel problem in the P2P traffic management. Based on the existed P2P traffic characters, this paper structures a P2P traffic model, gives a traffic prediction algorithm bases on wavelet-analysis, and proves the accuracy of the algorithm. Simulation experiment figures that the algorithm has a high prediction precision and a superior real-time performance.

Download Full-text

A Traffic Prediction Algorithm Based on Converged Networks of LTE and Low Power Wide Area Networks

Simulation Tools and Techniques - Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ◽

10.1007/978-3-030-72792-5_6 ◽

2021 ◽

pp. 54-63

Author(s):

Huan Li ◽

Feng Sun ◽

Yang Liu ◽

Shuai Ren ◽

Yang Nan ◽

...

Keyword(s):

Low Power ◽

Wide Area ◽

Prediction Algorithm ◽

Wide Area Networks ◽

Traffic Prediction

Download Full-text

Study on Traffic Prediction Algorithm Based on Multi-Scale Bi-Orthogonal Wavelet

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.340.722 ◽

2013 ◽

Vol 340 ◽

pp. 722-726

Author(s):

Yan Li ◽

Yao Chen

Keyword(s):

Wavelet Decomposition ◽

Prediction Method ◽

Prediction Algorithm ◽

Traffic Prediction ◽

Actual Situation ◽

Prediction Problem ◽

Network Configuration ◽

Orthogonal Wavelet ◽

Multi Scale ◽

Wavelet Algorithm

The traffic prediction carried out in the communication enterprises is of great significance for the optimization of the network configuration and the improvement of the communication quality. To solve the inaccurate prediction problem under the actual situation, a traffic prediction method based on the bi-orthogonal multi-scale wavelet algorithm is developed. The process of the wavelet decomposition and reconstruction are studied, and the reconstruction results for the different scales wavelet are obtained. Take a set of the special actual samples as the object, the traffic prediction for the future dates is completed, and compared with the actual results. The results show that the relative error between the proposed traffic prediction model and the actual results is less than 10%. The bi-orthogonal multi-scale wavelet algorithm has some advantages as compared with other similar ones, which will provide the important technology means for the traffic prediction forecasting and assessing in the various types of communication enterprises.

Download Full-text