Network Traffic Prediction Using Radial Basis Function Neural Network Optimized by Ant Colony Algorithm
| Autor: | Liu Jun, Guo Zuhua |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Radial basis function (RBF) neural network
Ant colony algorithm Computer Science::Computational Engineering Finance and Science Computer Science::Neural and Evolutionary Computation lcsh:Technology (General) MathematicsofComputing_NUMERICALANALYSIS Basis function lcsh:T1-995 Network traffic prediction |
| Zdroj: | Sensors & Transducers, Vol 172, Iss 6, Pp 224-228 (2014) |
| ISSN: | 1726-5479 2306-8515 |
| Popis: | The disadvantages of the traditional radial basis function (RBF) neural network during the network traffic prediction process, such as a slow convergence rate and easy occurrence of local optima, result in low prediction precision. In this study, the ant colony optimization (ACO) algorithm is used to optimize the parameters of the RBF neural network for network traffic prediction. ACO is used to train the width and centre of the basis function of the RBF neural network, simplify the network structure, accelerate the convergence speed, prevent the occurrence of local optima, and improve the generalist ability of the RBF neural network. The experimental results show that compared with the genetic algorithm (GA)-RBF and particle swarm optimization (PSO)-RBF traffic prediction models, the proposed model exhibits higher prediction accuracy and can describe the varying trends in the network traffic well. The model used in this study exhibits strong generalization ability and good stability and therefore has practical value in network traffic prediction. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|