The third-generation mobile system,or Universal Mobile Telecommunication System(UMTS),offers IP-based multimedia applications and services with end-to -end QoS guarantee.To support end-to-end QoS,the UMTS IP Multimedi...The third-generation mobile system,or Universal Mobile Telecommunication System(UMTS),offers IP-based multimedia applications and services with end-to -end QoS guarantee.To support end-to-end QoS,the UMTS IP Multimedia Subsystem(IMS) network should be scalable,reliable and flexible for interconnection with other UMTS IMS networks.End-to-end QoS requirements have prompted operators and the 3 GPP group to consider QoS provision in a multi-domain environment.In this tutorial,two scenarios are discussed for UE-UE connection via interconnected IMS networks.The first involves the transit of control and user traffic through the same intermediate network. The transit of control and user traffic through different intermediate networks shall be described in the second scenario.展开更多
A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorit...A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorithm for discretizing continuous numeric-values is brought forth to reshape these QoS metrics and contexts into their discrete forms. For QoS qualitative diagnosis, causal relationships between a QoS metric and its contexts are exploited with K2 Bayesian network （BN） structure learning by treating QoS metrics and contexts as BN nodes. A QoS metric node is qualitatively diagnosed to be causally related to its parent context nodes. To guarantee QoS quantitatively, those causal relationships are next modeled quantitatively by BN parameter learning. Then, BN inference can be carried out on the BN. Finally, the QoS metric is guaranteed to a specific value with certain probability by tuning its causal contexts to suitable values suggested by the BN inference. Our approach is validated to be sound and effective by simulations on a peer-to-peer （P2P） network.展开更多
为了提高网络路由性能,提出并设计了一种基于遗传-蚁群优化算法的服务质量(quality of service,QoS)组播路由算法。首先,设计了自适应变频采集策略用于采集网络与节点信息,以此获得网络和节点的状态,为后续路由优化提供数据支持;其次,...为了提高网络路由性能,提出并设计了一种基于遗传-蚁群优化算法的服务质量(quality of service,QoS)组播路由算法。首先,设计了自适应变频采集策略用于采集网络与节点信息,以此获得网络和节点的状态,为后续路由优化提供数据支持;其次,计算路径代价,将路径代价最小作为优化目标,建立QoS组播路由优化模型,并设置相关约束条件;最后,结合遗传算法和蚁群算法提出一种遗传-蚁群优化算法求解上述模型,输出最优路径,完成路由优化。实验结果表明,所提算法可有效降低路径长度与路径代价,提高搜索效率与路由请求成功率,优化后的路由时延抖动较小。展开更多
随着云计算技术的普及,云服务数量指数级增长,用户不再满足于功能性需求,服务质量(Quality of Service,QoS)成为比较服务优劣的关键性能指标.如何在动态、复杂的云环境中实时、准确地预测服务质量并为用户推荐高质量服务成为热点问题....随着云计算技术的普及,云服务数量指数级增长,用户不再满足于功能性需求,服务质量(Quality of Service,QoS)成为比较服务优劣的关键性能指标.如何在动态、复杂的云环境中实时、准确地预测服务质量并为用户推荐高质量服务成为热点问题.考虑到云服务器的负载、网络状态、用户接入云环境的偏好等随着时间变化,本文提出了基于多源特征和多任务学习的时序QoS预测方法(T-MST),它可以实时、准确地同时预测多种QoS属性.首先,TMST对用户、服务进行特征表示,通过Time2Vec刻画时序特征,再结合多种QoS属性的历史记录生成多源特征表示.其次,基于滑动窗口采用LSTM感知窗口内的时序关系,借助注意力机制细化窗口内不同时刻的关键性,从而构造待预测时刻的隐藏状态.最后,T-MST采用多任务预测层实现多种QoS属性的同时预测,它们共享上游模型,仅在预测层采用不同的感知模块以提升模型的鲁棒性和计算效率.本文基于真实世界的数据集进行了全面的实验验证,结果表明T-MST在吞吐量和响应时间的时序预测任务上平均绝对误差(Mean Absolute Error,MAE)分别平均提升了37.53%和20.38%,优于现有的时序QoS预测方法;而且TMST的计算效率更高,能够有效应对实时QoS预测的需求.展开更多
面对国内外大型公有云供应商的激烈竞争,中小云厂商的生存难度加大。为此,建立一个基于相互合作的云联盟成为了这些厂商的一种可行策略。然而,在追求个体最大利益和保障联盟整体服务质量(quality of service,QoS)之间存在着复杂的博弈...面对国内外大型公有云供应商的激烈竞争,中小云厂商的生存难度加大。为此,建立一个基于相互合作的云联盟成为了这些厂商的一种可行策略。然而,在追求个体最大利益和保障联盟整体服务质量(quality of service,QoS)之间存在着复杂的博弈关系。针对上述问题,一种基于QoS的云联盟模型被提出,其涵盖云计算的三层架构。在应用层至虚拟层,引入了一种基于差分进化(differential evolution,DE)算法的创新任务分配策略,专门用于处理多QoS任务分配问题。在虚拟层至物理层,设计了合作与竞争并存的虚拟机迁移模型,适用于在云联盟博弈计算环境下实现虚拟机迁移的能耗与QoS之间的平衡。实验结果表明,所提出的解决方案改进了云计算环境的服务质量,并揭示了在云联盟环境中,合作和竞争两种模式的相对优势。展开更多
To enhance the efficiency and expediency of issuing e-licenses within the power sector, we must confront thechallenge of managing the surging demand for data traffic. Within this realm, the network imposes stringentQu...To enhance the efficiency and expediency of issuing e-licenses within the power sector, we must confront thechallenge of managing the surging demand for data traffic. Within this realm, the network imposes stringentQuality of Service (QoS) requirements, revealing the inadequacies of traditional routing allocation mechanismsin accommodating such extensive data flows. In response to the imperative of handling a substantial influx of datarequests promptly and alleviating the constraints of existing technologies and network congestion, we present anarchitecture forQoS routing optimizationwith in SoftwareDefinedNetwork (SDN), leveraging deep reinforcementlearning. This innovative approach entails the separation of SDN control and transmission functionalities, centralizingcontrol over data forwardingwhile integrating deep reinforcement learning for informed routing decisions. Byfactoring in considerations such as delay, bandwidth, jitter rate, and packet loss rate, we design a reward function toguide theDeepDeterministic PolicyGradient (DDPG) algorithmin learning the optimal routing strategy to furnishsuperior QoS provision. In our empirical investigations, we juxtapose the performance of Deep ReinforcementLearning (DRL) against that of Shortest Path (SP) algorithms in terms of data packet transmission delay. Theexperimental simulation results show that our proposed algorithm has significant efficacy in reducing networkdelay and improving the overall transmission efficiency, which is superior to the traditional methods.展开更多
数字电视信号对传输质量有着十分严苛的要求,传统网际互连协议(Internet Protocol,IP)网络在提供端到端服务质量(Quality of Service,QoS)保障方面仍面临诸多挑战。对此,分析数字电视信号的业务特点和传输需求,梳理IP网络QoS领域的发展...数字电视信号对传输质量有着十分严苛的要求,传统网际互连协议(Internet Protocol,IP)网络在提供端到端服务质量(Quality of Service,QoS)保障方面仍面临诸多挑战。对此,分析数字电视信号的业务特点和传输需求,梳理IP网络QoS领域的发展脉络,提出一种端到端QoS保障解决方案的总体架构,从接入网、骨干网、综合管理平台三个层面给出优化措施。展开更多
随着网络通信行业的迅速发展,出现了各种各样的数字移动终端,用户对服务质量的要求也不断提高,QoS (Quality of Service)应运而生。时延是QoS的指标之一,通过研究时延可以进一步分析网络的性能。基于排队论,主要研究单一业务到达时的系...随着网络通信行业的迅速发展,出现了各种各样的数字移动终端,用户对服务质量的要求也不断提高,QoS (Quality of Service)应运而生。时延是QoS的指标之一,通过研究时延可以进一步分析网络的性能。基于排队论,主要研究单一业务到达时的系统性能,建立单一服务器服务的排队系统,在建模中,主要考虑突发性业务,使用突发性到达MMOO过程作为系统的输入,将服务过程建立为ALOHA。利用新的理论方法——鞅论,指数上鞅能够准确描述突发性到达对网络性能的影响,在鞅域中构建服务鞅和到达鞅的结构,通过鞅的停时定理,推导系统的时延违反概率不等式建模出在鞅结构下的时延违反概率界,利用MATLAB统计比较不同的负载率对应的时延违反概率界,发现在突发型的业务到达时,时延界随着负载率的减小更加紧致更加趋于真实值。展开更多
在网络世界中,网际互连协议(Internet Protocol,IP)承载网扮演着信息流动的骨干角色,其运行表现和服务水准至关重要。文章详细探讨了IP承载网中服务质量(Quality of Service,QoS)策略的设计与优化方法,重点涵盖分类服务与标记、流量控...在网络世界中,网际互连协议(Internet Protocol,IP)承载网扮演着信息流动的骨干角色,其运行表现和服务水准至关重要。文章详细探讨了IP承载网中服务质量(Quality of Service,QoS)策略的设计与优化方法,重点涵盖分类服务与标记、流量控制与优先级队列管理以及链路和节点策略的具体实现。通过流量分析与预测、智能资源分配与调度、动态策略调整以及故障检测与容错机制,提出一系列提升网络性能和用户体验的有效措施。展开更多
文摘The third-generation mobile system,or Universal Mobile Telecommunication System(UMTS),offers IP-based multimedia applications and services with end-to -end QoS guarantee.To support end-to-end QoS,the UMTS IP Multimedia Subsystem(IMS) network should be scalable,reliable and flexible for interconnection with other UMTS IMS networks.End-to-end QoS requirements have prompted operators and the 3 GPP group to consider QoS provision in a multi-domain environment.In this tutorial,two scenarios are discussed for UE-UE connection via interconnected IMS networks.The first involves the transit of control and user traffic through the same intermediate network. The transit of control and user traffic through different intermediate networks shall be described in the second scenario.
基金Supported by the National High Technology Research and Development Program of China （No. 2007AA010302, 2009AA012404） the National Basic Research Program of China （No. 2007CB307103）+1 种基金 the National Natural Science Foundation of China （No. 60432010, 60802034） the Specialized Research Fund for the Doctoral Program of Higher Education （No. 20070013026）.
文摘A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorithm for discretizing continuous numeric-values is brought forth to reshape these QoS metrics and contexts into their discrete forms. For QoS qualitative diagnosis, causal relationships between a QoS metric and its contexts are exploited with K2 Bayesian network （BN） structure learning by treating QoS metrics and contexts as BN nodes. A QoS metric node is qualitatively diagnosed to be causally related to its parent context nodes. To guarantee QoS quantitatively, those causal relationships are next modeled quantitatively by BN parameter learning. Then, BN inference can be carried out on the BN. Finally, the QoS metric is guaranteed to a specific value with certain probability by tuning its causal contexts to suitable values suggested by the BN inference. Our approach is validated to be sound and effective by simulations on a peer-to-peer （P2P） network.
文摘为了提高网络路由性能,提出并设计了一种基于遗传-蚁群优化算法的服务质量(quality of service,QoS)组播路由算法。首先,设计了自适应变频采集策略用于采集网络与节点信息,以此获得网络和节点的状态,为后续路由优化提供数据支持;其次,计算路径代价,将路径代价最小作为优化目标,建立QoS组播路由优化模型,并设置相关约束条件;最后,结合遗传算法和蚁群算法提出一种遗传-蚁群优化算法求解上述模型,输出最优路径,完成路由优化。实验结果表明,所提算法可有效降低路径长度与路径代价,提高搜索效率与路由请求成功率,优化后的路由时延抖动较小。
文摘随着云计算技术的普及,云服务数量指数级增长,用户不再满足于功能性需求,服务质量(Quality of Service,QoS)成为比较服务优劣的关键性能指标.如何在动态、复杂的云环境中实时、准确地预测服务质量并为用户推荐高质量服务成为热点问题.考虑到云服务器的负载、网络状态、用户接入云环境的偏好等随着时间变化,本文提出了基于多源特征和多任务学习的时序QoS预测方法(T-MST),它可以实时、准确地同时预测多种QoS属性.首先,TMST对用户、服务进行特征表示,通过Time2Vec刻画时序特征,再结合多种QoS属性的历史记录生成多源特征表示.其次,基于滑动窗口采用LSTM感知窗口内的时序关系,借助注意力机制细化窗口内不同时刻的关键性,从而构造待预测时刻的隐藏状态.最后,T-MST采用多任务预测层实现多种QoS属性的同时预测,它们共享上游模型,仅在预测层采用不同的感知模块以提升模型的鲁棒性和计算效率.本文基于真实世界的数据集进行了全面的实验验证,结果表明T-MST在吞吐量和响应时间的时序预测任务上平均绝对误差(Mean Absolute Error,MAE)分别平均提升了37.53%和20.38%,优于现有的时序QoS预测方法;而且TMST的计算效率更高,能够有效应对实时QoS预测的需求.
文摘面对国内外大型公有云供应商的激烈竞争,中小云厂商的生存难度加大。为此,建立一个基于相互合作的云联盟成为了这些厂商的一种可行策略。然而,在追求个体最大利益和保障联盟整体服务质量(quality of service,QoS)之间存在着复杂的博弈关系。针对上述问题,一种基于QoS的云联盟模型被提出,其涵盖云计算的三层架构。在应用层至虚拟层,引入了一种基于差分进化(differential evolution,DE)算法的创新任务分配策略,专门用于处理多QoS任务分配问题。在虚拟层至物理层,设计了合作与竞争并存的虚拟机迁移模型,适用于在云联盟博弈计算环境下实现虚拟机迁移的能耗与QoS之间的平衡。实验结果表明,所提出的解决方案改进了云计算环境的服务质量,并揭示了在云联盟环境中,合作和竞争两种模式的相对优势。
基金State Grid Corporation of China Science and Technology Project“Research andApplication of Key Technologies for Trusted Issuance and Security Control of Electronic Licenses for Power Business”(5700-202353318A-1-1-ZN).
文摘To enhance the efficiency and expediency of issuing e-licenses within the power sector, we must confront thechallenge of managing the surging demand for data traffic. Within this realm, the network imposes stringentQuality of Service (QoS) requirements, revealing the inadequacies of traditional routing allocation mechanismsin accommodating such extensive data flows. In response to the imperative of handling a substantial influx of datarequests promptly and alleviating the constraints of existing technologies and network congestion, we present anarchitecture forQoS routing optimizationwith in SoftwareDefinedNetwork (SDN), leveraging deep reinforcementlearning. This innovative approach entails the separation of SDN control and transmission functionalities, centralizingcontrol over data forwardingwhile integrating deep reinforcement learning for informed routing decisions. Byfactoring in considerations such as delay, bandwidth, jitter rate, and packet loss rate, we design a reward function toguide theDeepDeterministic PolicyGradient (DDPG) algorithmin learning the optimal routing strategy to furnishsuperior QoS provision. In our empirical investigations, we juxtapose the performance of Deep ReinforcementLearning (DRL) against that of Shortest Path (SP) algorithms in terms of data packet transmission delay. Theexperimental simulation results show that our proposed algorithm has significant efficacy in reducing networkdelay and improving the overall transmission efficiency, which is superior to the traditional methods.
文摘数字电视信号对传输质量有着十分严苛的要求,传统网际互连协议(Internet Protocol,IP)网络在提供端到端服务质量(Quality of Service,QoS)保障方面仍面临诸多挑战。对此,分析数字电视信号的业务特点和传输需求,梳理IP网络QoS领域的发展脉络,提出一种端到端QoS保障解决方案的总体架构,从接入网、骨干网、综合管理平台三个层面给出优化措施。
文摘随着网络通信行业的迅速发展,出现了各种各样的数字移动终端,用户对服务质量的要求也不断提高,QoS (Quality of Service)应运而生。时延是QoS的指标之一,通过研究时延可以进一步分析网络的性能。基于排队论,主要研究单一业务到达时的系统性能,建立单一服务器服务的排队系统,在建模中,主要考虑突发性业务,使用突发性到达MMOO过程作为系统的输入,将服务过程建立为ALOHA。利用新的理论方法——鞅论,指数上鞅能够准确描述突发性到达对网络性能的影响,在鞅域中构建服务鞅和到达鞅的结构,通过鞅的停时定理,推导系统的时延违反概率不等式建模出在鞅结构下的时延违反概率界,利用MATLAB统计比较不同的负载率对应的时延违反概率界,发现在突发型的业务到达时,时延界随着负载率的减小更加紧致更加趋于真实值。
文摘在网络世界中,网际互连协议(Internet Protocol,IP)承载网扮演着信息流动的骨干角色,其运行表现和服务水准至关重要。文章详细探讨了IP承载网中服务质量(Quality of Service,QoS)策略的设计与优化方法,重点涵盖分类服务与标记、流量控制与优先级队列管理以及链路和节点策略的具体实现。通过流量分析与预测、智能资源分配与调度、动态策略调整以及故障检测与容错机制,提出一系列提升网络性能和用户体验的有效措施。
