Tradeoffs in Designing Networks with End-to-End Statistical QoS Guarantees

Recent research on statistical multiplexing has provided many new insights into the achievable multiplexing gain in QoS networks. However, usually, these results are stated in terms of the gain experienced at a single switch, and evaluating the statistical multiplexing gain in a general network remains a difficult challenge. In this paper we describe two distinct network designs for statistical end-to-end delay guarantees, referred to as class-level aggregation and path-level aggregation. These designs illustrate an inherent trade-off between attainable statistical multiplexing gain and the ability to support delay guarantees. The key characteristic of both designs is that they do not require, and instead, intentionally avoid, consideration of the correlation between flows at multiplexing points inside the network. Numerical examples are presented for a comparison of the statistical multiplexing gain achievable by the two designs. The class-level aggregation design is shown to yield very high achievable link utilizations while simultaneously achieving desired statistical guarantees on delay.     

Aggregate Scheduling with Statistical Service Guarantees

1IntroductionAggregate scheduling in Differentiated Service(Diff-Serv) architecture , where core routers perform flowsaggregation operations can efficiently solve the scalabili-ty problemincurred in Integrated Service(IntServ) ar-chitecture .Compared with deterministic Quality of Ser-vice( QoS) guarantees in IntServ,statistical service inDiffServ significantlyincreases the efficiency of networkusage by allowingstatistical multiplexing of traffic .Sta-tistical services significantly incre…     

网络微积分中的最小加拟反卷积及其应用

网络微积分是一种对网络中的流量问题给出定量刻画的新型数学工具,其理论基础是最小加代数.文章围绕最小加运算中的反卷积问题进行讨论,定义了最小加拟反卷积和最小加强拟反卷积,并且通过具体的例子说明了所给定义的意义.最后,还讨论了最小加强拟反卷积在优化服务器设计中的应用.     

一种运营商物联网端到端业务质量分析方法

【】：物联网业务承载于无线网络之上,在提供丰富的行业应用的同时也面临着端到端业务流质量分析和监控的考验,本文通过建立物联网端到端指标体系、端到端问题分析定界方法、工单闭环管理等环节,实现对物联网主流业务客户感知问题的发现、处理、考核评估的闭环管理,确保用户业务感知。     

WCDMA网络端到端业务性能优化

互联网和无线网的融合极大地影响着WCDMA系统所承载的数据业务性能,因而扩展了无线网络运维与优化的问题域,仅关注空中接口的性能将很难满足端到端业务的需求.本文从网络层面、应用层面、数据链路层面、终端层面等角度系统介绍了有利于端到端业务性能优化的主要技术.     

Quality of Service and the End-to-End Argument

Audio-visual services are now commonly used on the Internet. Many of them are based on batch downloading of contents for later replay. Real-time interactive and streaming services are now rapidly becoming popular. These services would benefit from quality of service if it were widely provided. The purpose of this article is to show how QoS solutions may be introduced incrementally. Quality is obtained by means of a probe-based admission control that can be exerted outside the network. The introduction of QoS starts from self-admission control in the application layer, followed by transport layer service differentiation. These two steps do not require any change to the network. If motivated, scheduling for service class separation in the network may be added. We show by proof of concept how QoS may be provided in agreement with the end-to-end argument. The three steps of our proposal are compared and discussed with respect to the possibility of deployment.     

IPTV中的服务质量保证策略

IPTV是基于宽带高速IP网的流媒体服务,服务质量对于IPTV的成功是至关重要的.从IPTV的视频编码标准和内容分发技术等几方面探讨IPTV中的服务质量保证策略.     

端到端IP QoS业务平台网络架构

随着互联网的快速发展，基于IP的业务越来越丰富，未来各种业务统一到IP平台是网络发展的大趋势。以多媒体、语音、视频等为代表的应用对IP网的性能提出了更高的要求，要求网络提供服务质量(QoS)保证。当前IP网所提供的是“尽力而为”(best-effort)的服务，由于不具备服务质量保障特性，不能预留带宽，不能限定网络时延，因此无法支持许多新的应用。     

Analysis of Multi-Server Scheduling Paradigm for Service Guarantees during Network Mobility

Multi-server scheduling of traffic flows over heterogeneous wireless channels affix fresh concerns of inter-packet delay variations and associated problems of out-of-sequence reception, buffer management complexity, packet drops and re-ordering overhead. In this paper, we have presented an exclusive multi-server scheduling algorithm that is specifically tuned for mobile routers equipped with multiple wireless interfaces and has attained multiple care-of-address registrations with its home agent (HA). The proposed adaptive, Self-clocked, Multi-server (ASM) scheduling algorithm is based on predetermined transmission deadlines for each arrived packet at the mobile router. The mobile flows receive desired service levels in accordance with their negotiated service rates and are only constraint by the cumulative capacity of all active links. The major challenge lies in the handling of asymmetric channels to stitch into a unified virtual channel of higher capacity with reliable service guarantees during mobility. The sorted list of transmission schedules is used to assign physical channels in increasing order of their availability. This approach specifically encapsulates the physical layer disconnections during the handovers and ensures continuous service to ongoing flows. The proposed scheduling scheme is supplemented by an analytical model and simulations to verify its efficacy. The simulation results demonstrate higher degree of reliability and scalability of service provisioning to flows during mobility.     

Optimal Resource Allocation for Spectrum Sensing Based Cognitive Radio Networks with Statistical QoS Guarantees

Resource allocation under spectrum sensing based dynamic spectrum sharing strategy is a critically important issue for cognitive radio networks (CRNs), because they need to not only satisfy the interference constraint caused to the primary users (PUs), but also meet the quality-of-service (QoS) requirements for the secondary users (SUs). In this paper, we develop the optimal spectrum sensing based resource allocation scheme for the delay QoS constrained CRNs. Specifically, we aim at maximizing the maximum constant arrival rate of the SU that can be supported by the time-varying service process subject to the given statistical delay QoS constraint. In our derived power allocation scheme, not only the average transmit and interference power constraints are considered, but also the impact of the PUs?? transmission to the CRNs and the PUs?? spectrum-occupancy probability are taken into consideration. Moreover, the spectrum sensing errors are also taken into consideration. Simulation results show that, (1) the effective capacity of the secondary link decreases when the statistical delay QoS constraint becomes stringent; (2) given the QoS constraint, the effective capacity of the secondary link varies with the interference power constraint and the SNR of the primary link.     

数据业务端到端QoS参数映射与优化

在移动通信网内采用业务质量(QoS,Quality of Service)机制实现差异化的业务传输是近年的研究热点。端到端QoS包括非接入层用户和业务的识别、不同承载间QoS的一致性传递和接入层QoS的正确执行。这里以EDGE网络中数据业务传送机制为基础,全面研究了3GPP的QoS框架在UMTS网络的GERAN A/Gb模式和UTRAN Iu模式中的QoS映射,给出一个经过优化的端到端QoS参数映射表,并基于该表,在真实的EDGE网络中验证了QoS参数优化的可行性和参数映射的一致性。实验结果表明,根据不同业务的特点采用差异化的传输策略可以提升业务的感知。     

X.25 Interface and End-to-End Virtual Circuit Service Characteristics

Public packet switching networks around the world use CCITT Recommendation X.25, which is the standard device-independent interface between packet networks and user devices operating in the packet-mode. Since its development in 1976 and with four years of network operational experience, the X.25 interface specification has reached a high level of maturity. A revised version of X.25 has been approved by CCITT Study Group VII at its meeting in February 1980. The revised X.25 specification is more complete than its predecessor, eliminates a number of ambiguous areas which lead to network implementation differences, and has been enhanced by the addition of new capabilities both to the X.25 interface and to the end-to-end service. This paper presents a consolidated view of the end-to-end characteristics of the virtual-circuit-based services accessible through the X.25 interface. It then discusses the characteristics of the revised X.25 interface, with emphasis on areas that have been addressed in the revised Recommendation. The revised Recommendation leads the way to greater commonality among network implementations. The increased functionality of the end-to-end virtual-circuit services has impact on the relationship of X.25 to system architectures being discussed by international standards bodies.     

CORBA Notification Service and RSVP-Based Architecture to Provide QoS Guarantees

CORBA is an object-oriented middleware defined by the OMG. It is designed to support the development of distributed applications by separating interfaces from implementations. Unfortunately, CORBA does not consider QoS requirements inherent to new applications such as teleconferencing and telecommunication services. The Resource reSerVation Protocol (RSVP) is an IETF protocol that allows real-time applications to reserve necessary resources at routers along the transmission paths, so the requested bandwidth can be available when transmission actually takes place. In this paper, we discuss the use of Notification Service and RSVP to provide end-to-end QoS to applications supported by CORBA architecture.     

提供服务质量保证的多业务网络的计费策略

计费作为一种经济手段不仅关系到网络服务提供商的运营成本回收和盈利,而且也是一种提高网络资源利用率保证服务质量的有效措施。本文对提供服务质量保证的多业务网络的计费策略进行讨论,分析了不同业务对于服务质量的不同要求和网络计费组成两方面的问题,并示例到了一个基于提供服务质量保证的多业务网络计费方案。     

探讨移动互联网安全风险及端到端的业务安全评估

介绍了移动互联网体系架构及其面临的安全风险,讨论了业务安全评价指标系统,主要指标包括机密性、完整性、可用性、可靠性、保险性和可行性.另外,提出了一种端到端的业务安全评估方法.     

TDMA卫星通信系统中一种话音业务统计复用算法

本文提出了一种用于计算统计复用ＴＤＭＡ卫星通信系统中话音业务应申请时隙数的算法，给出了计算公式，并进行了分析、计算和模拟。结果证明，采用这种时隙计算算法可在用户能接受的信元丢失概率下，达到比传统ＴＤＭＡ／ＤＡ方案高许多的时隙利用率，同时具有差不多的时延性能。     

Quality of Service Modelling of Virtualized Wireless Networks: A Network Calculus Approach

Wireless network virtualization is an emerging technology that logically divides a wireless network element, such as a base station (BS), into multiple slices with each slice serving as a standalone virtual BS. In such a way, one physical mobile wireless network can be partitioned into multiple virtual networks each operating as an independent wireless network. Wireless virtual networks, as composed of these virtual BSs, need to provide quality of service (QoS) to mobile end user services. Key QoS parameters include buffer queue length, network delay and effective bandwidth, in particular their upper bound forms. This paper presents a QoS model for such a wireless virtual network addressing these parameters. This QoS model considers resources of both physical nodes and virtual nodes and provides a realistic modelling of the delay and bandwidth behaviours of wireless virtual networks. Network calculus (NC), which usually provides finer insight into a system, is utilized to fulfil the modelling task. The numerical results have shown the effectiveness of the proposed model. The model is useful for both off-line network planning and online network admission control.     

端到端重配置技术综述

端到端重配置(E2R)技术起源于软件无线电(SDR)技术,利用SDR终端和基站等可重配置实体为基础定义网络架构,结合先进的资源管理机制和灵活的空中接口实现技术,实现了对异构环境的灵活适应和对异构无线资源的有效利用。E2R技术研究中有3个关键点,包括E2R的体系结构、E2R的资源管理和E2R的空中接口实现,已取得较大成果。E2R技术作为一种具有高适变能力的技术,是使异构无线系统从目前的隔离态走向互通与协同、实现网络融合的最具发展潜质的无线网络技术。目前,E2R的研究已成为未来无线通信网络领域的关键课题之一。     

基于保证QoS的片上网络路由算法

为了解决满足多个约束条件的片上网络服务质量,提出了一种基于区域的路由算法,该算法根据数据包所在的节点将整个网络按照X维分为两个部分,正面部分采用东最后路由,负面部分采用西优先路由.仿真结果表明,区域路由算法比传统的维序算法和奇偶转向模型能够很好地保证片上网络的服务质量.