基于OpenStack的IaaS云中動(dòng)態(tài)資源分配策略研究
發(fā)布時(shí)間:2018-11-05 11:54
【摘要】:近年來(lái),隨著互聯(lián)網(wǎng)技術(shù)的不斷發(fā)展,基于互聯(lián)網(wǎng)技術(shù)的云計(jì)算應(yīng)用越來(lái)越趨于成熟。云計(jì)算平臺(tái)能夠通過(guò)因特網(wǎng),向用戶(hù)提供廉價(jià)的、可伸縮的分布式計(jì)算能力,通過(guò)提供虛擬資源的形式向用戶(hù)提供計(jì)算資源,滿足用戶(hù)的時(shí)變的計(jì)算需求。云服務(wù)提供商(Cloud computing service providers,簡(jiǎn)稱(chēng)CCSP)按照用戶(hù)使用量收費(fèi)。向用戶(hù)提供可用的、便捷的、按需的計(jì)算資源,如網(wǎng)絡(luò),服務(wù)器,存儲(chǔ),內(nèi)存,應(yīng)用軟件,具體服務(wù)等。 隨著云計(jì)算用戶(hù)的不斷增加,圍繞如何在保障用戶(hù)QoS需求前提下最小化用戶(hù)使用費(fèi)用的研究,這里的QoS參數(shù)包括過(guò)載率、延遲率、等待率、資源使用率等,已經(jīng)成為云計(jì)算研究中的重要研究方向。 近年來(lái),諸多開(kāi)源的云平臺(tái)不斷出現(xiàn),比如OpenNebula、Eucalyptus、 CloudStack、OpenStack等,其中以O(shè)penStack開(kāi)源云平臺(tái)的應(yīng)用最為廣泛。OpenStack是一個(gè)開(kāi)放源代碼的項(xiàng)目,是一個(gè)云平臺(tái)管理的項(xiàng)目。它由幾個(gè)主要的開(kāi)源組件組成,這些組件共同完成云平臺(tái)的各項(xiàng)具體功能。OpenStack開(kāi)源云平臺(tái)最顯著的特點(diǎn)就是能夠很好的簡(jiǎn)化云計(jì)算平臺(tái)的部署過(guò)程,為云計(jì)算平臺(tái)帶來(lái)良好的可擴(kuò)展性。 本文主要研究了云平臺(tái)中的動(dòng)態(tài)資源分配問(wèn)題,在總結(jié)目前已有研究成果的基礎(chǔ)之上,部署一個(gè)OpenStack開(kāi)源云平臺(tái),設(shè)計(jì)了一種云計(jì)算中動(dòng)態(tài)資源分配策略,實(shí)現(xiàn)在保障用戶(hù)QoS需求的前提下盡可能地減少用戶(hù)使用費(fèi)用的目的。
[Abstract]:In recent years, with the continuous development of Internet technology, cloud computing applications based on Internet technology are becoming more and more mature. Cloud computing platform can provide users with cheap scalable distributed computing power through the Internet and provide users with computing resources in the form of virtual resources to meet the time-varying computing needs of users. Cloud service provider (Cloud computing service providers, acronyms CCSP) charge according to user usage. Provide users with available, convenient, on-demand computing resources such as network, server, storage, memory, application software, specific services, etc. With the increasing number of cloud computing users, the research on how to minimize the cost of user use under the premise of protecting the user's QoS requirements is focused on. The QoS parameters here include overload rate, delay rate, waiting rate, resource utilization rate, etc. Cloud computing has become an important research direction. In recent years, many open source cloud platforms have been emerging, such as OpenNebula,Eucalyptus, CloudStack,OpenStack, among which OpenStack is the most widely used cloud platform. OpenStack is an open source project and a cloud platform management project. It consists of several major open source components that work together to complete the specific features of the cloud platform. The most significant feature of the OpenStack open source cloud platform is its ability to simplify the deployment process of the cloud computing platform. For cloud computing platform to bring good scalability. This paper mainly studies the dynamic resource allocation problem in cloud platform. On the basis of summarizing the existing research results, we deploy a OpenStack open source cloud platform and design a dynamic resource allocation strategy in cloud computing. The purpose is to reduce the cost of QoS as much as possible on the premise of protecting the user's QoS requirements.
【學(xué)位授予單位】:中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】:碩士
【學(xué)位授予年份】:2014
【分類(lèi)號(hào)】:TP393.09
[Abstract]:In recent years, with the continuous development of Internet technology, cloud computing applications based on Internet technology are becoming more and more mature. Cloud computing platform can provide users with cheap scalable distributed computing power through the Internet and provide users with computing resources in the form of virtual resources to meet the time-varying computing needs of users. Cloud service provider (Cloud computing service providers, acronyms CCSP) charge according to user usage. Provide users with available, convenient, on-demand computing resources such as network, server, storage, memory, application software, specific services, etc. With the increasing number of cloud computing users, the research on how to minimize the cost of user use under the premise of protecting the user's QoS requirements is focused on. The QoS parameters here include overload rate, delay rate, waiting rate, resource utilization rate, etc. Cloud computing has become an important research direction. In recent years, many open source cloud platforms have been emerging, such as OpenNebula,Eucalyptus, CloudStack,OpenStack, among which OpenStack is the most widely used cloud platform. OpenStack is an open source project and a cloud platform management project. It consists of several major open source components that work together to complete the specific features of the cloud platform. The most significant feature of the OpenStack open source cloud platform is its ability to simplify the deployment process of the cloud computing platform. For cloud computing platform to bring good scalability. This paper mainly studies the dynamic resource allocation problem in cloud platform. On the basis of summarizing the existing research results, we deploy a OpenStack open source cloud platform and design a dynamic resource allocation strategy in cloud computing. The purpose is to reduce the cost of QoS as much as possible on the premise of protecting the user's QoS requirements.
【學(xué)位授予單位】:中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】:碩士
【學(xué)位授予年份】:2014
【分類(lèi)號(hào)】:TP393.09
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 房秉毅;張?jiān)朴?程瑩;徐雷;;云計(jì)算國(guó)內(nèi)外發(fā)展現(xiàn)狀分析[J];電信科學(xué);2010年S1期
2 王海q,
本文編號(hào):2312005
本文鏈接:http://sikaile.net/guanlilunwen/ydhl/2312005.html
最近更新
教材專(zhuān)著