本文選題：無線網(wǎng)絡(luò)　切入點：自回歸積分滑動平均模型　出處：《現(xiàn)代電子技術(shù)》2016年23期 　論文類型：期刊論文

【摘要】：無線網(wǎng)絡(luò)流量受到上網(wǎng)成本、上網(wǎng)行為等因素的綜合作用,具有隨機性和周期性變化的特點,針對單一模型不能全面描述該變化特點的難題,提出基于組合優(yōu)化理論的無線網(wǎng)絡(luò)流量預(yù)測模型。首先采用自回歸積分滑動平均模型進行建模,找出無線網(wǎng)絡(luò)流量的周期性變化規(guī)律,然后采用相關(guān)向量機進行建模,找出無線網(wǎng)絡(luò)流量的隨機性變化特點,最后將它們的預(yù)測結(jié)果組合在一起進行單步和多步的無線網(wǎng)絡(luò)流量預(yù)測實驗。實驗結(jié)果表明,該模型可以同時對隨機性和周期性變化特點進行描述,預(yù)測精度高于單一自回歸積分滑動平均模型或者相關(guān)向量機。
[Abstract]:Wireless network traffic is affected by the cost and behavior of the Internet, and has the characteristics of randomness and periodicity. In view of the problem that a single model can not fully describe the characteristics of the change, the wireless network traffic has the characteristics of randomness and periodicity. This paper presents a wireless network traffic prediction model based on combinatorial optimization theory. Firstly, the autoregressive integral moving average model is used to model the periodic variation of wireless network traffic, and then the correlation vector machine is used to model the model. The randomness characteristics of wireless network traffic are found out. Finally, the prediction results are combined to carry out single-step and multi-step wireless network traffic prediction experiments. The experimental results show that, The prediction accuracy of the model is higher than that of single autoregressive integral moving average model or correlation vector machine.
【作者單位】： 海南師范大學(xué)信息科學(xué)技術(shù)學(xué)院;海南廣播電視大學(xué)瓊海遠程教育學(xué)院;海南師范大學(xué)信息網(wǎng)絡(luò)與數(shù)據(jù)中心;
【分類號】：TN92
，

本文編號：1629456