基于EDF调度算法的端到端延迟保证方法

EDF(EarliestDeadlineFirst)是一种高效的调度算法。为了将其应用于提供端到端延迟保证,提出了一种新的算法JT-EDF(JitterTunableEDF),并证明了所有的端到端EDF调度算法都可以在相同的条件下保证相同的端到端延迟界。     

基于流量隔离的公平聚集器

为实现对微流的最差延迟最早聚集,并对聚集完成的宏流进行过滤与排序,实现宏流公平调度,提出基于流量隔离的公平聚集器(FAFI)。FAFI解决了在基于流量聚集调度模式中,同一宏流内部各竞争微流之间的突发流量对数据包传输延迟产生影响的问题。通过严格的数学推理与演算,证明FAFI的有效性。仿真实验验证了对FAFI模型的定量分析结果和FAFI模型的性能。     

A framework for end-to-end deterministic-delay service provisioning in multiservice packet networks

The problem of providing end-to-end delay guarantees for deterministic-delay services in multiservice packet networks is addressed through a combination of dynamic resource reservation and routing. Our model is based on using rate-controlled earliest-deadline-first (RC-EDF) for providing hard bounds on end-to-end delays. With RC-EDF, a certain delay bound has to be allocated for a connection at each node in the selected path. The most commonly used resource reservation policy is uniform allocation which is based on dividing the end-to-end delay bound equally among the nodes in the selected path. This simple allocation policy could lead to nonuniform resource loading and subsequently lead to high blocking rates. Moreover, the most commonly used routing method is shortest-path first routing which is known to lead to network hotspots. We propose a set of dynamic nonuniform resource reservation policies and dynamic routing methods. One of the routing methods is the well-known widest-shortest path method and the other is a dynamic routing method that adaptively adjusts link costs and uses a similar algorithm to shortest-path routing (e.g., Dijkstra's algorithm). We show that for both uniform and nonuniform traffic loading of some example network topologies that the combination of the proposed resource reservation policies and dynamic routing can lead to significant reduction in the connection blocking ratio in all loading conditions except for excessively high loads.     

Deterministic delay analysis of AVB switched Ethernet networks using an extended Trajectory Approach

Audio Video Bridging (AVB) switched Ethernet is being considered as a promising network alternative solution for the automotive industry thanks to its high data transmission rate and dedicated bandwidth for real-time traffic. However, guaranteeing deterministic communications of an AVB switched Ethernet network remains a key issue for safety-critical applications in automotive domain. In order to ensure real-time timeliness constraints for any flow sent in AVB switched Ethernet networks, we establish new bounds on the worst-case end-to-end delay of any flow. Our contributions are the following: (i) We first develop a worst-case delay analysis in the context of AVB switched Ethernet network based on an extension of the Trajectory Approach. (ii) Then we take into account serialization constraints on frame transmissions to improve the computation of worst-case end-to-end delay bounds. (iii) Finally, we refine the proposed approach by taking into consideration the AVB traffic shaping characteristics. The performance of the proposed approach is illustrated on a set of representative automotive examples.     

Queuing network models of packet switching networks part 1: Open networks

An overview of the application of product-form queuing network models to the performance analysis of store-and-forward packet-switching networks is presented. Multiple routing chains are used to model the different routing behaviors of data packets. Queuing networks with open chains are considered in this paper. Kleinrock's formula for the mean end-to-end delay of packets is first derived. The application of this delay formula to optimal channel capacity assignment and optimal routing is discussed. Analytic results for the mean and distribution of the end-to-end delay of each chair are presented. The issue of fairness among chains is also addressed.The application of queuing networks with closed chains and population size constraints to the performance analysis of store-and-forward packet-switching networks is illustrated in a companion paper [1].     

网络链路时延统计量的层析成像方法

传统的连续时延分布估计往往需要假设时延满足某种分布,估计精度受制于假设分布与实际时延分布的相关性。Gianni Antichi等提出了一种链路时延累积量估计的方法,无需假设时延满足某种分布,但需要内部节点的协作。针对上述问题提出一种完全依靠端到端测量的链路时延累积量估计方法,根据端到端的时延构建端到端时延累积量与链路时延累计量的方程,最终利用最优化方法计算出链路时延累积量的最优解。ns-2仿真结果验证了该方法的有效性。     

一种低功耗无线传感器网络多径路由优化协议

针对无线传感器网络多媒体传输应用中,单通道路由方案无法获得理想效果的问题,提出了一种低功耗多径路由优化协议(EEOR)。在这个协议中,通过邻居之间的消息交互建立最大化多路径,并引入了多路径选择机制来剔除无意义的路径。在多路径建立过程中,首先考虑降低端到端延迟,其次维护网络的能量平衡。仿真结果显示,提出的方案与其他两种路由协议相比网络生命更长、可靠性更高、端到端的延迟和控制开销更低。     

Enhanced bulk scheduling for supporting delay sensitive streaming applications

Providing end-to-end delay guarantees for delay sensitive applications is an important packet scheduling issue with routers. In this paper, to support end-to-end delay requirements, we propose a novel network scheduling scheme, called the bulk scheduling scheme (BSS), which is built on top of existing schedulers of intermediate nodes without modifying transmission protocols on either the sender or receiver sides. By inserting special control packets, which called TED (Traffic Specification with End-to-end Deadline) packets, into packet flows at the ingress router periodically, the BSS schedulers of the intermediate nodes can dynamically allocate the necessary bandwidth to each flow to enforce the end-to-end delay, according to the information in the TED packets. The introduction of TED packets incurs less overhead than the per-packet marking approaches. Three flow bandwidth estimation methods are presented, and their performance properties are analyzed. BSS also provides a dropping policy for discarding late packets and a feedback mechanism for discovering and resolving bottlenecks. The simulation results show that BSS performs efficiently as expected.     

Scheduling and admission testing for jitter-constrained periodic threads

We present new admission tests for periodic real-time threads with explicitly stated deadlines scheduled according to the earliest deadline first (EDF) algorithm. In traditional real-time periodic scheduling, the deadline of a periodic thread is conventionally the end of the current period. In contrast, our tests support periodic threads in which the deadline may be earlier than the end of the current period. In the extreme case, the deadline may be specified as identical to the per period execution time, which results in perfectly isochronous periodic threads. The provision of such threads, which we refer to as jitter-constrained threads, helps end-systems to honour jitter as well as throughput-related QoS parameters in distributed multimedia systems. In addition, such threads can reduce end-to-end delay and buffer memory requirements as less buffering is needed to smooth excessive delay jitter.     

一种网络延迟精确控制的调度算法

在网络数据传输调度中，基于最早时限优先（EDF）的算法具有单点最优的延迟界限控制能力。现有的各种EDF改进算法，主要着眼于提供延迟上界的保证能力，而当采用机顶盒之类的缓冲能力较弱的设备作为客户终端时，还需要网络提供精确的延迟下界控制能力。在原有EDF改进算法的基础上提出了精确延迟界控制的最早时限优先算法。该算法不但能同时保证延迟上界和下界，还使得节点可以独立地决定为数据流分配的缓冲区大小，并增加了节点允许抖动量的取值范围，从而提高了节点数据的转发效率。     

低轨卫星网络中高效资源利用的组播算法

为了解决低轨卫星网络中现有典型源组播算法的信道资源浪费问题,提出了一套单核共享树组播算法,即核心群合并共享树(CCST)和加权CCST(w-CCST)算法.CCST算法包括动态近似中心(DAC)选核方法和核心群合并组播路径构建方法.DAC方法根据组成员在网络中的分布情况自适应选择最优核;在核心群合并方法中,以核节点作为初始核心群,通过核心群和剩余组成员的最短路径方法逐步扩展直至整棵组播树构建完成,从而使得组播树的树代价最小,大大提高了网络的传输带宽利用率和传输效率.在w-CCST算法中,可以通过调整加权因子来适度增大树代价、降低端到端传播时延以满足某些端到端时延要求苛刻的实时组播业务.最后,通过仿真与其它算法进行了性能对比,仿真结果说明CCST组播树的平均树代价比其它组播树显著降低,平均端到端传播时延比其它组播树稍高;w-CCST算法的平均端到端传播时延性能好于CCST算法,树代价性能稍差,说明使用加权因子可以在组播树的树代价和端到端传播时延性能之间作折中.     

An enhanced real-time routing protocol with load distribution for mobile wireless sensor networks

Mobile wireless sensor network (MWSN) is a wireless ad hoc network that consists of a very large number of tiny sensor nodes communicating with each other in which sensor nodes are either equipped with motors for active mobility or attached to mobile objects for passive mobility. A real-time routing protocol for MWSN is an exciting area of research because messages in the network are delivered according to their end-to-end deadlines (packet lifetime) while sensor nodes are mobile. This paper proposes an enhanced real-time with load distribution (ERTLD) routing protocol for MWSN which is based on our previous routing protocol RTLD. ERTLD utilized corona mechanism and optimal forwarding metrics to forward the data packet in MWSN. It computes the optimal forwarding node based on RSSI, remaining battery level of sensor nodes and packet delay over one-hop. ERTLD ensures high packet delivery ratio and experiences minimum end-to-end delay in WSN and MWSN compared to baseline routing protocol. In this paper we consider a highly dynamic wireless sensor network system in which the sensor nodes and the base station (sink) are mobile. ERTLD has been successfully studied and verified through simulation experiment.     

Assured end-to-end QoS through adaptive marking in multi-domain differentiated services networks

The issue of resource management in multi-domain Differentiated Services (DiffServ) networks has attracted a lot of attention from researchers who have proposed various provisioning, adaptive marking and admission control schemes. In this paper, we propose a Reinforcement Learning-based Adaptive Marking (RLAM) approach for providing assured end-to-end quality of service (QoS) in the form of end-to-end delay and throughput assurances, while minimizing packet transmission cost since ‘expensive’ Per Hop Behaviors like Expedited Forwarding (EF) are used only when necessary. The proposed scheme tries to satisfy per flow end-to-end QoS through control action,s which act on flow aggregates in the core of the network. Using an ns2 simulation of a multi-domain DiffServ network with multimedia traffic, the RLAM scheme is shown to be effective in significantly lowering packet transmission costs without sacrificing end-to-end QoS, when compared to the commonly used static marking scheme.     

一种基于支持向量回归的互联网端到端延迟预测算法

互联网端到端延迟是指IP分组沿着互联网中一条确定路径进行传输的延迟,端到端延迟的精确预测是大量网络活动的基础,从网络协议设计到网络监测,再从确保端到端QoS性能到各种实时业务性能提升。提出一种新的端到端延迟的预测方法,主要贡献有:a)将互联网端到端延迟预测的问题转换为多元回归的预测问题,提出了基于多元回归的端到端延迟预测框架;b)采用支持向量回归SVR方法来求解端到端延迟的多元回归问题,提出了基于SVR的互联网端到端延迟预测算法。最后使用互联网采集的RTT数据来验证提出的算法,实验结果表明,提出的预测算法具有快速和精确特点,是一种适合实际应用的预测算法。     

基于网络演算计算保证服务端到端延迟上界

归纳总结了网络演算,阐明了网络演算的两个基本工具——进入曲线和服务曲线,得出了服务曲线存在瓶颈效应、端到端延迟的理想与近似确定性上界、提供保证服务网络节点的服务曲线需求等结论,计算了服务曲线以速率等待时间及PGPS(packetizedgeneralizedprocessorsharing)形式表示的保证服务端到端延迟确定性上界.     

一种改善AFDX网络级联传输时延特性分析的方法

文中分析了AFDX级联网络中数据传输时间延迟的不确定性问题及造成该问题的内在原因,对传输时延的组成部分和影响因素进行描述,指出应用AFDX网络技术应先充分验证端到端时延上界值是否符合系统容限要求。介绍了计算时延上界值的网络演算方法的基本原理及其利用对虚拟链路进行分组优化的算法理论,将该算法应用到某实验环境中的AFDX级联网络配置实例中,计算出实例中各数据流的时延上界并对计算结果的悲观性进行分析,最后得出优化后的算法来分析传输时延更能趋近实际的上界值。     

Buffer Management for Colored Packets with Deadlines

We consider buffer management of unit packets with deadlines for a multi-port device with reconfiguration overhead. The goal is to maximize the throughput of the device, i.e., the number of packets delivered by their deadline. For a single port or with free reconfiguration, the problem reduces to the well-known packets scheduling problem, where the celebrated earliest-deadline-first (EDF) strategy is optimal 1-competitive. However, EDF is not 1-competitive when there is a reconfiguration overhead. We design an online algorithm that achieves a competitive ratio of 1−o(1) when the ratio between the minimum laxity of the packets and the number of ports tends to infinity. This is one of the rare cases where one can design an almost 1-competitive algorithm. One ingredient of our analysis, which may be interesting on its own right, is a perturbation theorem on EDF for the classical packets scheduling problem. Specifically, we show that a small perturbation in the release and deadline times cannot significantly degrade the optimal throughput. This implies that EDF is robust in the sense that its throughput is close to the optimum even when the deadlines are not precisely known.     

Tight end-to-end per-flow delay bounds in FIFO multiplexing sink-tree networks

Aggregate scheduling has been proposed as a solution for achieving scalability in large-size networks. However, in order to enable the provisioning of real-time services, such as video delivery or voice conversations, in aggregate scheduling networks, end-to-end delay bounds for single flows are required. In this paper, we derive per-flow end-to-end delay bounds in aggregate scheduling networks in which per-egress (or sink-tree) aggregation is in place, and flows traffic is aggregated according to a FIFO policy. The derivation process is based on Network Calculus, which is suitably extended to this purpose. We show that the bound is tight by deriving the scenario in which it is attained. A tight delay bound can be employed for a variety of purposes: for example, devising optimal aggregation criteria and rate provisioning policies based on pre-specified flow delay bounds.     

Discrete time-optimal command shaping

Finite impulse-response “input shapers” may be used to prefilter inputs to eliminate or minimize residual vibration when maneuvering flexible structures. Vibration is reduced at the expense of adding a delay equal to the length of the shaper. This paper first presents results that aid in the design of “single-input shapers” in the discrete domain. Next, MIMO shaping is considered. Given certain a priori information about the inputs, shorter shapers (which introduce less delay) can be derived. A time-optimal scheme is developed here, and existence of solutions is proved for both SISO and MIMO cases. The method is direct, general, easy to implement, and allows for the addition of derivative constraints to improve robustness. Finally, traditional optimal control and input shaping are compared, and it is shown that under certain conditions optimal discrete-time input shaping and discrete time-optimal control are equivalent.     

Optimizing end-to-end performance of data-intensive computing pipelines in heterogeneous network environments

Supporting high-performance data-intensive computing pipelines in wide-area networks is crucial for enabling large-scale distributed scientific applications that require minimizing end-to-end delay for single-input applications or maximizing frame rate for streaming applications. We formulate and categorize the data-intensive computing pipeline mapping problems into six classes with two optimization objectives, i.e. minimum end-to-end delay and maximum frame rate, and three network constraints, i.e. no, contiguous, and arbitrary node reuse. We design a dynamic programming-based optimal solution to the problem of minimum end-to-end delay with arbitrary node reuse and prove the NP-completeness of the rest five problems, for each of which, a heuristic algorithm based on a similar optimization procedure is proposed. These heuristics are implemented and tested on a large set of simulated pipelines and networks of various scales and their performance superiority is illustrated by extensive simulation results in comparison with existing methods.