【摘要】：當(dāng)前,新型網(wǎng)絡(luò)應(yīng)用不斷涌現(xiàn),用戶對(duì)不同類型應(yīng)用的通信需求也呈現(xiàn)出多樣化和個(gè)性化的特點(diǎn).面向用戶頻繁產(chǎn)生和變化的通信需求,網(wǎng)絡(luò)服務(wù)提供商(Internet service provider,簡(jiǎn)稱ISP)通常以不斷地購買及部署大量新型的專用網(wǎng)絡(luò)設(shè)備的方式來應(yīng)對(duì),導(dǎo)致其運(yùn)營(yíng)成本高昂,資源浪費(fèi)嚴(yán)重,網(wǎng)絡(luò)建設(shè)與發(fā)展的可持續(xù)性差.對(duì)此,從軟件角度出發(fā),考慮路由功能重用,通過選擇合適的路由功能,在通信路徑上為應(yīng)用合成定制化的路由服務(wù),滿足用戶差異化的需求.基于網(wǎng)絡(luò)功能虛擬化(network function virtualization,簡(jiǎn)稱NFV)和軟件定義網(wǎng)絡(luò)(software-defined networking,簡(jiǎn)稱SDN),提出了一種自適應(yīng)路由服務(wù)合成機(jī)制,運(yùn)用軟件產(chǎn)品線技術(shù)構(gòu)建路由服務(wù)產(chǎn)品線,作為路由功能選擇和路由服務(wù)優(yōu)化的基礎(chǔ).基于機(jī)器學(xué)習(xí),運(yùn)用多層前饋神經(jīng)網(wǎng)構(gòu)建路由服務(wù)離線模式和在線模式兩階段學(xué)習(xí)模型,對(duì)路由功能選擇及組合進(jìn)行持續(xù)學(xué)習(xí)和優(yōu)化,實(shí)現(xiàn)路由服務(wù)的定制化目標(biāo),以提高用戶的服務(wù)體驗(yàn).進(jìn)行了仿真實(shí)現(xiàn),研究結(jié)果表明,所提出的模型是可行和有效的.
[Abstract]:At present, new network applications are emerging, and users' communication needs for different types of applications are diversified and individualized. Facing the frequent and changing communication demand of users, (Internet service provider, (ISP), a network service provider, usually deals with it by constantly purchasing and deploying a large number of new types of special network equipment, which results in high operating cost. The waste of resources is serious and the sustainability of network construction and development is poor. From the point of view of software, considering the reuse of routing function and selecting the appropriate routing function, the application composition customized routing service can be used in the communication path to meet the needs of user differentiation. Based on network function virtualization (network function virtualization,) and software defined network (SDN), an adaptive routing service composition mechanism is proposed, which uses software product line technology to construct routing service product line. As the basis of routing function selection and routing service optimization. Based on machine learning, a two-stage learning model of off-line and on-line mode of routing service is constructed by using multi-layer feedforward neural network. The continuous learning and optimization of routing function selection and composition are carried out to achieve the customized goal of routing service. To improve the user's service experience. The simulation results show that the proposed model is feasible and effective.
【作者單位】： 東北大學(xué)軟件學(xué)院;東北大學(xué)信息科學(xué)與工程學(xué)院;
【基金】：國家自然科學(xué)基金(61572123) 國家杰出青年科學(xué)基金(71325002)~~
【分類號(hào)】：TP393.09

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 陳霄;一種可變SaaS應(yīng)用的開發(fā)方法研究[D];復(fù)旦大學(xué);2013年

，

本文編號(hào)：2400303