Network Traffic Prediction Algorithm based on Improved Chaos Particle Swarm SVM

Abstract

Abstract—Because network traffic is complexand the existingprediction models have various limitations, a new network traffic prediction model based on wavelettransform and optimized support vector machine(ChOSVM) is proposed.Firstly, the network traffic is decomposed to the scale coefficients andwavelet coefficients by non-decimated wavelet transform based on suitablewavelet base and decomposition level. Then they are sent individually intodifferent SVM with suitable kernel function for prediction. The parameters ofSVM are selected by chaos particle swarm optimization. Finally predictions arecombined into the final result by wavelet reconstruction. Experiments onnetwork traffic of different time granularity show that compared with othernetwork traffic prediction models, ChOSVM has better performance.

DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4802