發(fā)布時間：2019-04-19 22:38

【摘要】：為了準確預(yù)測云應(yīng)用負載以便及時執(zhí)行云應(yīng)用自適應(yīng)優(yōu)化,從而保證云應(yīng)用性能的穩(wěn)定,根據(jù)云環(huán)境下應(yīng)用負載預(yù)測問題的特點,提出了基于深度置信網(wǎng)絡(luò)的云應(yīng)用負載預(yù)測方法.首先給出能夠有效描述負載數(shù)據(jù)的顯式特征和隱式特征并定義了負載預(yù)測模型,進而給出基于深度置信網(wǎng)絡(luò)的負載預(yù)測算法.對算法進行了分析并在真實數(shù)據(jù)集上與相關(guān)算法進行了比較,結(jié)果表明,本文提出的方法能夠更加有效地解決云應(yīng)用負載預(yù)測問題.
[Abstract]:In order to accurately predict cloud application load in order to perform cloud application adaptive optimization in a timely manner, so as to ensure the stability of cloud application performance, according to the characteristics of application load prediction problem in cloud environment, A cloud application load prediction method based on deep confidence network is proposed. Firstly, the explicit and implicit characteristics which can describe the load data effectively are given, and the load prediction model is defined. Then, the load prediction algorithm based on the depth confidence network is given. The algorithm is analyzed and compared with the related algorithms on the real data set. The results show that the proposed method can solve the problem of cloud application load prediction more effectively.
【作者單位】： 東北大學(xué)計算機科學(xué)與工程學(xué)院;
【基金】：國家科技支撐計劃項目(2014BAI17B00) 國家自然科學(xué)基金資助項目(61572116,61572117,61502089)
【分類號】：TP393.09

【相似文獻】

相關(guān)期刊論文 前1條

1 趙一鉑;鄒恒明;;基于個人防火墻的自適應(yīng)優(yōu)化策略[J];計算機工程;2009年10期

相關(guān)碩士學(xué)位論文 前1條

1 趙一鉑;虛擬機信息攻防戰(zhàn)之防火墻自適應(yīng)優(yōu)化研究[D];上海交通大學(xué);2009年

，

本文編號：2461350