本文選題：網(wǎng)絡(luò)流量 + 正則極限學(xué)習(xí)機��； 參考：《激光雜志》2015年01期

【摘要】：網(wǎng)絡(luò)流量預(yù)測一直是網(wǎng)絡(luò)研究技術(shù)中的熱點,針對網(wǎng)絡(luò)流量變化的時變性、混沌性,提出一種相空間重構(gòu)和正則極限學(xué)習(xí)機的網(wǎng)絡(luò)流量預(yù)測模型。首先收集大量的網(wǎng)絡(luò)流量歷史樣本,并進行相應(yīng)的預(yù)處理,然后根據(jù)混沌理論確定最優(yōu)延遲時間和嵌入維數(shù),并重構(gòu)網(wǎng)絡(luò)流量學(xué)習(xí)樣本,最后采用正則極限學(xué)習(xí)機建立網(wǎng)絡(luò)流量預(yù)測模型,并進行仿真對比實驗。結(jié)果表明,相對于其它網(wǎng)絡(luò)流量預(yù)測模型,本文模型可以更加準(zhǔn)確描述網(wǎng)絡(luò)流量的非線性變化特點,提高網(wǎng)絡(luò)流量預(yù)測精度,預(yù)測結(jié)果具有一定實用價值。
[Abstract]:Network traffic prediction has always been a hot topic in network research technology. Aiming at the time-varying and chaotic nature of network traffic change, a network traffic prediction model based on phase space reconstruction and regular limit learning machine is proposed. Firstly, a large number of network traffic history samples are collected, then the optimal delay time and embedding dimension are determined according to chaos theory, and the network traffic learning samples are reconstructed. Finally, the network traffic prediction model is established by using the regular limit learning machine, and the simulation results are compared. The results show that compared with other network traffic prediction models, this model can more accurately describe the nonlinear characteristics of network traffic, improve the accuracy of network traffic prediction, and the prediction results have certain practical value.
【作者單位】： 常熟理工學(xué)院電氣與自動化工程學(xué)院;
【分類號】：TP393.06

【相似文獻】

相關(guān)期刊論文 前10條

1 姜明;吳春明;張e，

本文編號：2031878