多子種群PSO優(yōu)化SVM的網(wǎng)絡(luò)流量預(yù)測
發(fā)布時間：2018-12-25 07:41
【摘要】：針對網(wǎng)絡(luò)流量的時變性和非平穩(wěn)性特點(diǎn),為提高網(wǎng)絡(luò)流量預(yù)測精度,提出一種"多子種群"機(jī)制的粒子群算法和支持向量機(jī)的網(wǎng)絡(luò)流量預(yù)測模型(Multi-Subpopulation Particle Swarm Optimization and Support Vector Machine,MSPSO-SVM).首先支持向量機(jī)(Support Vector Machine,SVM)參數(shù)編碼成粒子位置串,并根據(jù)網(wǎng)絡(luò)訓(xùn)練集的交叉驗證誤差最小作為參數(shù)優(yōu)化目標(biāo),然后通過粒子間信息交流找到最優(yōu)SVM參數(shù),并引入"多子種群"機(jī)制,解決粒子群優(yōu)化(Particle Swarm Optimization,PSO)算法的早熟停滯缺陷,最后根據(jù)最優(yōu)參數(shù)建立網(wǎng)絡(luò)流量預(yù)測模型,并采用實際網(wǎng)絡(luò)流量數(shù)據(jù)進(jìn)行仿真測試.結(jié)果表明,相對于其他預(yù)測模型,MSPSO-SVM可以獲得更優(yōu)的SVM參數(shù),網(wǎng)絡(luò)流量預(yù)測精度得以提高,更加適用于復(fù)雜多變的網(wǎng)絡(luò)流量預(yù)測.
[Abstract]:In view of the time-varying and non-stationary characteristics of network traffic, in order to improve the accuracy of network traffic prediction, a particle swarm optimization (PSO) algorithm and a support vector machine (Multi-Subpopulation Particle Swarm Optimization and Support Vector Machine,) network traffic prediction model based on "multi-subpopulation" mechanism are proposed. MSPSO-SVM) Firstly, support vector machine (Support Vector Machine,SVM) parameters are encoded into particle position strings, and the minimum cross-validation error of network training set is used as the parameter optimization objective, and then the optimal SVM parameters are found through the information exchange between particles. The "multi-sub-population" mechanism is introduced to solve the premature stagnation defect of particle swarm optimization (Particle Swarm Optimization,PSO) algorithm. Finally, the network traffic prediction model is established according to the optimal parameters, and the actual network traffic data are used for simulation test. The results show that compared with other prediction models, MSPSO-SVM can obtain better SVM parameters and improve the precision of network traffic prediction, which is more suitable for complex and changeable network traffic prediction.
【作者單位】： 華東交通大學(xué)信息工程學(xué)院;
【基金】：江西省教育廳科學(xué)技術(shù)研究項目資助(GJJ12686)
【分類號】：TP393.06
[Abstract]:In view of the time-varying and non-stationary characteristics of network traffic, in order to improve the accuracy of network traffic prediction, a particle swarm optimization (PSO) algorithm and a support vector machine (Multi-Subpopulation Particle Swarm Optimization and Support Vector Machine,) network traffic prediction model based on "multi-subpopulation" mechanism are proposed. MSPSO-SVM) Firstly, support vector machine (Support Vector Machine,SVM) parameters are encoded into particle position strings, and the minimum cross-validation error of network training set is used as the parameter optimization objective, and then the optimal SVM parameters are found through the information exchange between particles. The "multi-sub-population" mechanism is introduced to solve the premature stagnation defect of particle swarm optimization (Particle Swarm Optimization,PSO) algorithm. Finally, the network traffic prediction model is established according to the optimal parameters, and the actual network traffic data are used for simulation test. The results show that compared with other prediction models, MSPSO-SVM can obtain better SVM parameters and improve the precision of network traffic prediction, which is more suitable for complex and changeable network traffic prediction.
【作者單位】： 華東交通大學(xué)信息工程學(xué)院;
【基金】：江西省教育廳科學(xué)技術(shù)研究項目資助(GJJ12686)
【分類號】：TP393.06
【參考文獻(xiàn)】
相關(guān)期刊論文 前6條
1 姜明;吳春明;張e，
本文編號：2390871
本文鏈接：http://sikaile.net/guanlilunwen/ydhl/2390871.html
最近更新
教材專著
