本文關(guān)鍵詞： SDN網(wǎng)絡(luò) BP神經(jīng)網(wǎng)絡(luò)算法 負(fù)載均衡　出處：《吉林大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：近年來(lái),隨著移動(dòng)互聯(lián)網(wǎng)、電子商務(wù)的不斷發(fā)展,大數(shù)據(jù)和云計(jì)算成為新的發(fā)展趨勢(shì)。網(wǎng)絡(luò)流量壓力越來(lái)越大的同時(shí),流量模式逐漸變?yōu)楦叨葎?dòng)態(tài)化,按需提供帶寬的能力代替了總傳輸容量增益成為創(chuàng)造收益的關(guān)鍵。服務(wù)提供者基于業(yè)務(wù)的多樣化和建設(shè)成本考慮,對(duì)靈活優(yōu)化的管控能力更加渴求;IT基礎(chǔ)設(shè)施也要應(yīng)需而變,以全新的方式支持快速靈活的商業(yè)運(yùn)作。SDN(軟件定義網(wǎng)絡(luò))就是在這種情況下應(yīng)運(yùn)而生。它是一種新型的網(wǎng)絡(luò)架構(gòu),是對(duì)傳統(tǒng)tcp/ip網(wǎng)絡(luò)架構(gòu)的一種偉大的革新與突破。顧名思義,SDN的思想就是通過(guò)軟件定義和驅(qū)動(dòng)的方式實(shí)現(xiàn)對(duì)網(wǎng)絡(luò)的控制和管理。SDN架構(gòu)分為應(yīng)用層、控制層、數(shù)據(jù)層。數(shù)據(jù)層上的網(wǎng)絡(luò)設(shè)備專(zhuān)注于數(shù)據(jù)包的轉(zhuǎn)發(fā)從而提高轉(zhuǎn)發(fā)速度;控制層由SDN控制器通過(guò)編程來(lái)集中管理調(diào)度,可以結(jié)合當(dāng)前網(wǎng)絡(luò)狀態(tài)和用戶需求來(lái)制定轉(zhuǎn)發(fā)和調(diào)度策略;應(yīng)用層上的開(kāi)發(fā)人員通過(guò)SDN控制器獲知了網(wǎng)絡(luò)的全局視圖,可以靈活自由的部署業(yè)務(wù)。然而由此也引出了另一個(gè)新的問(wèn)題,如何在提供服務(wù)質(zhì)量的同時(shí),實(shí)現(xiàn)對(duì)資源的合理分配,實(shí)現(xiàn)在SDN網(wǎng)絡(luò)中進(jìn)行負(fù)載均衡。負(fù)載均衡也是近年來(lái)越來(lái)越熱門(mén)的話題。面對(duì)越來(lái)越多的新型應(yīng)用,越來(lái)越大的網(wǎng)絡(luò)流量,網(wǎng)絡(luò)承受的壓力也越來(lái)越大。要保證服務(wù)的質(zhì)量一方面需要提高數(shù)據(jù)處理能力和響應(yīng)速度,另一方面需要進(jìn)行負(fù)載均衡,實(shí)現(xiàn)網(wǎng)絡(luò)資源合理分配。那么在SDN網(wǎng)絡(luò)下以何種方式進(jìn)行路由決策來(lái)平衡負(fù)載提高網(wǎng)絡(luò)性能成為一個(gè)新的研究熱點(diǎn)。本文針對(duì)當(dāng)前網(wǎng)絡(luò)飽受各種壓力的現(xiàn)狀及傳統(tǒng)網(wǎng)絡(luò)架構(gòu)面臨的瓶頸,通過(guò)對(duì)新興網(wǎng)絡(luò)架構(gòu)SDN網(wǎng)絡(luò)的研究,提出了在SDN下基于BP神經(jīng)網(wǎng)絡(luò)算法的負(fù)載均衡方案。SDN網(wǎng)絡(luò)的一大特點(diǎn)是控制層和數(shù)據(jù)層分離,控制器能夠獲取整個(gè)網(wǎng)絡(luò)的拓?fù)浣Y(jié)構(gòu),同時(shí)能夠獲得交換機(jī)傳來(lái)的實(shí)時(shí)網(wǎng)絡(luò)狀態(tài)信息,包含鏈路負(fù)載、時(shí)延等等,我們便可以利用這一點(diǎn)在控制層上制定某種路由策略對(duì)數(shù)據(jù)包進(jìn)行轉(zhuǎn)發(fā),實(shí)現(xiàn)負(fù)載均衡。我們可以利用啟發(fā)式算法來(lái)獲得某種場(chǎng)景下的一個(gè)近似最優(yōu)解,但是由于它所需的時(shí)間成本很高,所以我們采取它的結(jié)果作為一個(gè)訓(xùn)練工具,一個(gè)中間產(chǎn)物。BP算法屬于人工神經(jīng)網(wǎng)絡(luò)中的一種算法,它的特點(diǎn)是具有自學(xué)習(xí)能力和泛化能力,能對(duì)輸入-輸出關(guān)系進(jìn)行模型訓(xùn)練,當(dāng)訓(xùn)練完成后對(duì)輸入具有快速預(yù)測(cè)輸出的能力。所以本文的方案就是將實(shí)時(shí)網(wǎng)絡(luò)狀態(tài)和Qo S請(qǐng)求作為BP算法的輸入,將啟發(fā)式算法求得的最佳路由作為BP算法的輸出,將此模型進(jìn)行訓(xùn)練,訓(xùn)練后的模型(路由決策)存放在SDN控制器中,當(dāng)有新的請(qǐng)求時(shí)可以快速預(yù)測(cè)出路徑,從而使得SDN網(wǎng)絡(luò)下負(fù)載均衡達(dá)到更好的效果。
[Abstract]:In recent years, with the continuous development of the mobile Internet and e-commerce, big data and cloud computing become a new development trend. The ability to provide bandwidth on demand replaces the total transmission capacity gain as the key to generating revenue. Service providers are more eager for flexible and optimized control capabilities based on business diversification and construction cost considerations; The IT infrastructure has to change as well, in a completely new way to support fast and flexible business operations. SDN (Software defined Network) emerged as the times require. It is a new network architecture. It is a great innovation and breakthrough to the traditional tcp/ip network architecture. The idea of SDN is to realize the control and management of network by software definition and drive. SDN architecture is divided into application layer and control layer. Data layer. The network devices on the data layer focus on the forwarding of data packets to improve the speed of forwarding; The control layer is managed centrally by the SDN controller through programming, and the forwarding and scheduling policies can be formulated according to the current network status and user requirements. Developers in the application layer know the global view of the network through the SDN controller, and can deploy the service flexibly and freely. However, this also leads to another new problem, how to provide the quality of service at the same time. Realize the rational allocation of resources and realize load balance in SDN network. Load balancing is also a hot topic in recent years. Facing more and more new applications, more and more network traffic. The network is under increasing pressure. To ensure the quality of services, on the one hand, we need to improve the data processing capacity and response speed, on the other hand, we need to balance the load. How to make routing decision in SDN network to balance load and improve network performance has become a new research hotspot. This paper aims at the current situation of network under various pressures. And the bottleneck of traditional network architecture. Through the research on the new network architecture, SDN network, a load balancing scheme based on BP neural network algorithm under SDN is proposed. One of the characteristics of the network is the separation of control layer and data layer. The controller can obtain the topology of the whole network and the real-time network state information from the switch, including link load, delay and so on. We can use this point in the control layer to formulate a certain routing policy to forward packets to achieve load balancing, we can use heuristic algorithm to obtain an approximate optimal solution in a certain scenario. But because the time cost is very high, so we take its result as a training tool, an intermediate product. BP algorithm belongs to an artificial neural network algorithm. It has the ability of self-learning and generalization, and can train the model of input-output relationship. When the training is completed, it has the ability to predict the input and output quickly. Therefore, the scheme of this paper is to use real-time network state and QoS request as the input of BP algorithm. The best route obtained by the heuristic algorithm is taken as the output of BP algorithm. The model is trained and the trained model (routing decision) is stored in the SDN controller. When there are new requests, the path can be predicted quickly, so that load balancing in SDN network can achieve better results.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP183;TP393.0

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鄢玉;楊潔明;;BP神經(jīng)網(wǎng)絡(luò)算法探討[J];科技情報(bào)開(kāi)發(fā)與經(jīng)濟(jì);2006年03期

2 張賽民;周竹生;陳靈君;;應(yīng)用一種改進(jìn)BP神經(jīng)網(wǎng)絡(luò)算法預(yù)測(cè)密度曲線[J];物探化探計(jì)算技術(shù);2007年06期

3 李淑慧;;改進(jìn)的進(jìn)化神經(jīng)網(wǎng)絡(luò)算法及其在入侵檢測(cè)中的應(yīng)用[J];現(xiàn)代電子技術(shù);2010年01期

4 王治國(guó);宋考平;張春鶴;劉剛;王愛(ài)明;;BP神經(jīng)網(wǎng)絡(luò)算法在單井流動(dòng)單元識(shí)別中的應(yīng)用[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2011年05期

5 ;BP神經(jīng)網(wǎng)絡(luò)算法的改進(jìn)[J];電腦開(kāi)發(fā)與應(yīng)用;1995年02期

6 賀興時(shí),劉宇;BP神經(jīng)網(wǎng)絡(luò)算法在數(shù)字識(shí)別中的應(yīng)用[J];西北紡織工學(xué)院學(xué)報(bào);2000年04期

7 李廣瓊,蔣加伏;關(guān)于對(duì)BP神經(jīng)網(wǎng)絡(luò)算法改進(jìn)的研究[J];常德師范學(xué)院學(xué)報(bào)(自然科學(xué)版);2003年02期

8 孫修東,李宗斌,陳富民;基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)算法的多指標(biāo)綜合評(píng)價(jià)方法的應(yīng)用研究[J];河南機(jī)電高等專(zhuān)科學(xué)校學(xué)報(bào);2003年01期

9 王青海;BP神經(jīng)網(wǎng)絡(luò)算法的一種改進(jìn)[J];青海大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年03期

10 左付均,蔡自興;基于神經(jīng)網(wǎng)絡(luò)算法的建設(shè)項(xiàng)目風(fēng)險(xiǎn)預(yù)測(cè)系統(tǒng)設(shè)計(jì)[J];廣西科學(xué)院學(xué)報(bào);2004年03期

相關(guān)會(huì)議論文 前10條

1 呂慶U，

本文編號(hào)：1474473