基于节点粘度的混合组网架构及性能优化算法研究

发布时间：2018-01-08 03:20

本文关键词：基于节点粘度的混合组网架构及性能优化算法研究　出处：《中国电力科学研究院》2014年博士论文　论文类型：学位论文

【摘要】：随着公司信息化水平不断提升,一些新的工作模式正在逐渐形成,如视频业务会议、信息配送以及远程教学等,大大提升了工作效率。此外,伴随3G、4G移动通信技术的不断成熟与逐步部署以及音视频编码技术的发展,使很多灵活的业务成为可能,应用诸如移动视频电话、视频音频直播、点播及移动视频监控等。上述业务对海量实时流媒体数据传输产生了广泛的需求。对于大型企业(员工超过万人),其实时流媒体应用不同与传统企业或互联网流媒体应用,具有自己的特点,主要是海量用户的在线接入和实时交互需求同时存在,但在线用户相对稳定,频繁上下线情况较少。另外,通信网络的性能及拓扑的感知性较好,可以更好的支撑流媒体传输。因此,根据大型企业实时流媒体应用的特点,研究实时流媒体传输及调度具有重要意义。国家电网公司拥有员工150万,国家电网公司注册的内网桌面终端60万,外网桌面终端20万,如果同时有超过数万、数十万的员工访问视频服务,面对海量用户的在线接入和实时交互需求,传统的流媒体传输系统面临巨大挑战。海量流媒体数据传输对电力通信网带来巨大冲击,当前的基础设施根本无法满足海量流媒体数据传输的需求,传输的实时性更加难以保证。这使各种实时流媒体传输业务的发展越到瓶颈,在此背景下,以视频会议直播为对象,研究大型企业海量实时流媒体数据的传输调度模式显得异常重要。将传统流媒体传输技术在应用于电力通信网时,存在很多问题：(1)目前存在多种传输技术,它们的特点和资源分配成本大不相同,因此选择何种技术需要深入研究。在应对大规模数据传输时,如果采用C/S模式,服务器承载能力受限,网络带宽存在瓶颈；而CDN技术可以解决带宽问题,但是服务器成本昂贵,维护代价较大；P2P技术虽然可以解决服务器负载问题,但是网络瓶颈没有解决,它会带来巨大的网络传输流量,尤其是带来了大量的跨网域的冗余流量,浪费宝贵的骨干网和网问互联带宽。因此,如何综合利用这些技术,扬长避短,是需要研究的问题。(2)长期以来在传统互联网中视频应用中,视频体验差是一个关键问题,视频启动延迟较大影响着用户的感受,阻碍了流媒体应用的发展。因此,如何降低视频启动延迟,提升系统服务质量(QoS)和用户体验(QoE)已是亟待解决的问题。(3)在电网系统中,终端的网络环境差异很大,有线、无线节点异构节点同时存在,异构节点对视频的数据传播方式带来了挑战,一方面移动终端是否能够满足电力业务需要进行进一步进行实际验证；另外,异构节点对视频质量的要求不一样,带宽性能不一样,视频数据传输调度如何满足不同接入终端的需要,是一个亟待解决的问题。论文基于复杂网络理论、数据分发、视频编解码等术对电力海量数据实时调度及传输进行研究,以电力视频会议直播为突破口,对实时流媒体数据分发的关键性能,包括视频质量、启动及传输延时、跨网流量、负载均衡等进行多目标优化。论文采用两层优化方法,一是对覆盖网拓扑进行优化；二是对数据传输与调度算法进行优化。论文首先对各种数据分发技术进行了全面的分析评价,构建了一种适合电力海量实时流媒体数据分发混合传输架构；对移动终端的接入能力进行验证,论证其应用于电力视频业务的可行性。基于复杂网络理论,搭建了一种基于节点粘度对等网拓扑模型(P2P-NMNV).并针对该模型拓扑度量指标进行了全面分析,结论表明该网络的节点度符合幂率分布,有较短的特征路径和较高的聚集系数,适合实时流媒体数据分发的,有利于降低传输延时,提高用户体验。结合P2P-NMNV模型,在电力系统首次引入P2P-CDN网络模式,并提出了一种基于自治域的混合组网架构HPCS。HPCS综合利用了P2P、CDN和分自治域传输的优点。通过采用分域传输的方式,有效降低骨干网流量,降低传输延时；采用P2P与CDN技术相结合混合组网模式,可以有效提高视频服务质量,提高网络承载能力；采用P2P核心节点与CDN网关互用的模式,大幅的降低设备部署成本。基于熵权分析法,提出了核心节点选举算法,优化了网络传输性能；采用CDN节点单域多核心的模式,核心节点互为备份,提高了网络的鲁棒性,提升了数据传输的效率；为了提高系统容错能力,在核心节点出现故障的情况下,通过采用跨网域连接的方式,提高系统鲁棒性,并得到了跨网流量的最佳配置比例。基于HPCS混合组网架构,构建一种适合于固网和移动混合环境下的视频直播调度模型,并基于熵权层次分析法提出了一种多目标数据调度算法。实验结果表明该算法可以在网络异构的情况下,实现了局部最优的数据调度,在P2P流媒体低延时播放、高视频质量和负载均衡之间达到一个局部最优的配置。综上所述,论文基于复杂网络理论、数据传输技术,在电力海量实时数据传输方面进行了创新,以视频会议直播为突破口,提出了传输模型和数据调度算法,并取得了丰硕的成果,有效解决实时视频数据传输存在的传输瓶颈,并获得了良好的用户体验。本成果适用于各种实时、非实时的海量数据传输应用,在电力系统和互联网领域具有广阔的应用空间。
[Abstract]:With the continuous improvement of the company ' s informatization level , some new modes of operation are being gradually formed , such as video business meeting , information distribution and distance teaching , so that the work efficiency is greatly improved . In addition , with the development of 3G and 4G mobile communication technologies and the development of audio and video coding technology , many flexible services are possible , such as mobile video telephone , video audio live broadcasting , on - demand and mobile video monitoring , etc . The above - mentioned services have a wide demand for massive real - time streaming media data transmission . In the case of large enterprises ( over ten thousand employees ) , the application of streaming media is different from that of traditional enterprises or Internet streaming media , and has its own characteristics , mainly in the presence of online access and real - time interactive demand of mass users , but online users are relatively stable and frequent up and down . In addition , the performance and topology of the communication network are relatively stable , and the streaming media transmission can be better supported . Therefore , according to the characteristics of the real - time streaming media application of large enterprises , it is important to study the transmission and scheduling of real - time streaming media . The State Grid Company has an employee of 1.5 million , the internal network desktop terminal registered by the State Grid Corporation is 600,000 , and the external network desktop terminal is 200,000 . If there are more than tens of thousands of employees accessing the video service at the same time , the traditional streaming media transmission system is faced with great challenges . The large amount of streaming media data transmission has great impact on the power communication network , and the real - time performance of the transmission is more difficult to guarantee . There are many problems in the application of traditional streaming media technology in power communication network : ( 1 ) There are many kinds of transmission technologies , which have different characteristics and resource allocation cost . On the basis of complex network theory , data distribution , video coding and decoding , real - time scheduling and transmission of power mass data are studied . The key performance of real - time streaming media data distribution , including video quality , start - up and transmission delay , cross - network traffic and load balance , is optimized . This paper makes a comprehensive analysis and evaluation of various data distribution technologies , and constructs a hybrid transmission architecture suitable for power - mass real - time streaming media data distribution . Based on the complex network theory , a new P2P - NMNV model is proposed . In conclusion , based on the complex network theory and the data transmission technology , the paper makes innovations in the real - time data transmission of power , proposes the transmission model and the data scheduling algorithm , and obtains the fruitful results , effectively solves the transmission bottleneck existing in the real - time video data transmission , and obtains a good user experience . The results are suitable for various real - time and non - real - time mass data transmission applications , and have wide application space in the power system and the Internet .

【学位授予单位】：中国电力科学研究院
【学位级别】：博士
【学位授予年份】：2014
【分类号】：TN919.8

【参考文献】