Based on the analysis of current Quality of Service (QoS) management on IP network, new genera-tion of QoS architecture QoSAF is proposed. QoSAF is divided into three layers: resource control layer, net-work service l...Based on the analysis of current Quality of Service (QoS) management on IP network, new genera-tion of QoS architecture QoSAF is proposed. QoSAF is divided into three layers: resource control layer, net-work service layer and business layer. QoS management is accomplished by interactivity of layers. In this ar-chitecture, mechanism of feedback control enhances the functions of resource management and system moni-toring. The principle of design and logical architecture of system is discussed in detail.展开更多
民用飞机后舱包括信息系统(Information System,IS)、客舱核心系统(Cabin Core System,CCS)、机载娱乐(In-Flight Entertainment,IFE)系统、外部通信系统(External Communication System,ECS)等,各系统飞行安全域等级不同且网络交联关...民用飞机后舱包括信息系统(Information System,IS)、客舱核心系统(Cabin Core System,CCS)、机载娱乐(In-Flight Entertainment,IFE)系统、外部通信系统(External Communication System,ECS)等,各系统飞行安全域等级不同且网络交联关系复杂,这对传输服务质量(Quality of Service,QoS)提出极高要求,传统的QoS算法难以达到最佳效果。针对上述问题,将公平队列调度(Fair Weight Queue,FWQ)算法和随机早期检测(Random Early Detection,RED)算法相结合,整合到QoS处理系统上,并利用优先级双因素(Two-Factor,TF)机制对数据流进行精细化描述,提出一种民用飞机后舱一体化网络改进型QoS算法,命名为双因素加权公平队列随机早期检测(Two Factor-Fair Weighted Queue-Random Early Detection,TF-FWQ-RED)算法,使用OPNET网络仿真工具对该算法进行仿真验证。仿真运行结果显示,通过该算法可有效降低后舱高优先级业务流在网络拥塞场景下受延迟或丢包率的影响,同时保证了网络的高效运行,表明了TF-FWQ-RED算法的正确性以及对民机后舱混合复杂网络环境下现实需求的适应性。展开更多
This paper presents introduction for a QoS verification of on-chip interconnection based on the new progress of the industry, which combined with an AMD processor chip design for big data. Some verification experience...This paper presents introduction for a QoS verification of on-chip interconnection based on the new progress of the industry, which combined with an AMD processor chip design for big data. Some verification experience in architectural modeling and simulation of on-chip interconnection is also introduced in this paper.展开更多
当前分布式多媒体系统技术在飞速发展,其核心问题是多媒体流的服务质量(QoS)保证。对于由QoS控制来实现QoS保证,国际上不同组织和团体提出了不同的控制机制和策略。比较著名的有:1)ISO/OSI提出的基于ODP分布式环境的QoS控制,但至今仍停...当前分布式多媒体系统技术在飞速发展,其核心问题是多媒体流的服务质量(QoS)保证。对于由QoS控制来实现QoS保证,国际上不同组织和团体提出了不同的控制机制和策略。比较著名的有:1)ISO/OSI提出的基于ODP分布式环境的QoS控制,但至今仍停留在只给出了用户层的QoS参数说明和编程接口阶段,具体实现QoS控制策略并未提出;2)ATM论坛也提出了QoS控制的策略和实现[3],ATM控制是“连接预定”型(connection and reservation)。展开更多
基于前期工作——可信可控网络体系结构TCNA(trustworthy and controllable network architecture),提出了一种QoS资源控制模型(resource control model for QoS,简称RCMQ).该模型从网络可控角度将QoS控制分为4层:QoS决策层面、QoS观测...基于前期工作——可信可控网络体系结构TCNA(trustworthy and controllable network architecture),提出了一种QoS资源控制模型(resource control model for QoS,简称RCMQ).该模型从网络可控角度将QoS控制分为4层:QoS决策层面、QoS观测层面、QoS接口层面和QoS资源层面,模型部署包括独立集中的域内控制和一致性分布式控制.RCMQ模型闭环控制结构保证了QoS控制的有效性,而独立集中的QoS决策层面使得模型具有可扩展性.最后,通过仿真实验验证了RCMQ资源控制模型与InterServ模型相比,能够提供更为稳定的QoS传输,并且极大地减少了QoS状态维护,同时也从侧面说明可信可控网络体系比传统TCP/IP网络具有更高的可控性.展开更多
基金Partially supported by the Research Fund for the Doc-toral Program of Higher Education (No.20010013003), the National Natural Science Foundation of China (No.90204003), the 863 program (No.2003AA121220), and the 973 program (No.2003CB314806).
文摘Based on the analysis of current Quality of Service (QoS) management on IP network, new genera-tion of QoS architecture QoSAF is proposed. QoSAF is divided into three layers: resource control layer, net-work service layer and business layer. QoS management is accomplished by interactivity of layers. In this ar-chitecture, mechanism of feedback control enhances the functions of resource management and system moni-toring. The principle of design and logical architecture of system is discussed in detail.
文摘民用飞机后舱包括信息系统(Information System,IS)、客舱核心系统(Cabin Core System,CCS)、机载娱乐(In-Flight Entertainment,IFE)系统、外部通信系统(External Communication System,ECS)等,各系统飞行安全域等级不同且网络交联关系复杂,这对传输服务质量(Quality of Service,QoS)提出极高要求,传统的QoS算法难以达到最佳效果。针对上述问题,将公平队列调度(Fair Weight Queue,FWQ)算法和随机早期检测(Random Early Detection,RED)算法相结合,整合到QoS处理系统上,并利用优先级双因素(Two-Factor,TF)机制对数据流进行精细化描述,提出一种民用飞机后舱一体化网络改进型QoS算法,命名为双因素加权公平队列随机早期检测(Two Factor-Fair Weighted Queue-Random Early Detection,TF-FWQ-RED)算法,使用OPNET网络仿真工具对该算法进行仿真验证。仿真运行结果显示,通过该算法可有效降低后舱高优先级业务流在网络拥塞场景下受延迟或丢包率的影响,同时保证了网络的高效运行,表明了TF-FWQ-RED算法的正确性以及对民机后舱混合复杂网络环境下现实需求的适应性。
文摘This paper presents introduction for a QoS verification of on-chip interconnection based on the new progress of the industry, which combined with an AMD processor chip design for big data. Some verification experience in architectural modeling and simulation of on-chip interconnection is also introduced in this paper.
基金Supported by the National Natural Science Foundation of China under Grant No.90412012 (国家自然科学基金)the China Postdoctoral Science Foundation under Grant No.20060400063 (中国博士后科学基金)the Orange France Telecom R&D Lab. (Beijing) (北京法国电信研发中心有限公司资助项目)
文摘当前分布式多媒体系统技术在飞速发展,其核心问题是多媒体流的服务质量(QoS)保证。对于由QoS控制来实现QoS保证,国际上不同组织和团体提出了不同的控制机制和策略。比较著名的有:1)ISO/OSI提出的基于ODP分布式环境的QoS控制,但至今仍停留在只给出了用户层的QoS参数说明和编程接口阶段,具体实现QoS控制策略并未提出;2)ATM论坛也提出了QoS控制的策略和实现[3],ATM控制是“连接预定”型(connection and reservation)。
文摘基于前期工作——可信可控网络体系结构TCNA(trustworthy and controllable network architecture),提出了一种QoS资源控制模型(resource control model for QoS,简称RCMQ).该模型从网络可控角度将QoS控制分为4层:QoS决策层面、QoS观测层面、QoS接口层面和QoS资源层面,模型部署包括独立集中的域内控制和一致性分布式控制.RCMQ模型闭环控制结构保证了QoS控制的有效性,而独立集中的QoS决策层面使得模型具有可扩展性.最后,通过仿真实验验证了RCMQ资源控制模型与InterServ模型相比,能够提供更为稳定的QoS传输,并且极大地减少了QoS状态维护,同时也从侧面说明可信可控网络体系比传统TCP/IP网络具有更高的可控性.
