Burst scheduling for differentiated services in optical burst switching WDM networks

Optical burst switching (OBS) is one of the most important switching technologies for future optical wavelength division multiplexing (WDM) networks and the Internet. The model of differentiated services has been proposed to support quality of service (QoS) in the IP‐based Internet. It is also very important to have differentiated service support in OBS networks. When the burst scheduling in an OBS network is set up appropriately, network can support differentiated services. In this paper, we proposed a new burst scheduling scheme, called differentiated scheduling with identical priority offset time (DSIPO). In DSIPO, the same priority offset time is used for all the bursts destined to the same edge node regardless of their priorities. Differentiated services in terms of burst loss probability are achieved by processing the control packets of higher priority class bursts, thus reserving resources for their data bursts, more promptly upon their arrival than those of lower priority class bursts. Each intermediate (core) node can adjust the burst loss probabilities of various burst classes by choosing its own differentiated processing delay value for each priority class or its own differentiated processing delay difference value between any pair of adjacent priority classes. We model and analyse DSIPO in terms of the burst loss probability for each priority class with simulation validation. The performance of DISPO is evaluated by simulation. Copyright © 2004 John Wiley & Sons, Ltd.     

Providing differentiated services for multi-class traffic in IP/MPLS over WDM networks

Providing differentiated services in IP/MPLS over WDM networks has attracted a lot of recent attention. This article extends the Path Inflation Control (PIC) policy recently proposed by us to provide differentiated services in IP/MPLS over WDM networks with traffic grooming. Three different algorithms are considered for provisioning differentiated services. The simulation results show that, with two of the three algorithms, the network cannot only provide differentiated services when the traffic load is high but also gives significantly lower blocking for the lower priority class traffic and for the overall traffic at low traffic loads.

Delay analysis for CBR traffic under static-priority scheduling

We examine the delay performance of packets from constant-bit-rate (CBR) traffic whose delay is affected by non-real-time traffic. The delay performance is analyzed by solving the nD/D/1 queue with vacations. We obtain an exact and closed form solution, hence obviating the need of any approximations or numerical Laplace inversions. We then provide various numerical results for low-bit-rate transmission links, in which packets can experience large delay. From our quantitative evaluation, we conclude that there exists an optimum packet size for a given delay bound. In extremely slow links, such as modem links, transmission control protocol (TCP) packets should be segmented to reduce the CBR delay. We therefore investigate the delay impact of TCP packet sizes as well     

An efficient network-switch scheduling for real-time applications

Bursts consist of a varying number of asynchronous transfer mode cells corresponding to a datagram. Here, we generalized weighted fair queueing to a burst-based algorithm with preemption. The new algorithm enhances the performance of the switch service for real-time applications, and it preserves the quality of service guarantees. We study this algorithm theoretically and via simulations.     

A differentiated optical services model for WDM networks

This article addresses the issues of scalable end-to-end QoS in metropolitan DWDM networks serving as transit networks for IP access networks. DWDM offering a few wavelengths has been deployed in the past in backbone networks to upgrade point-to-point transmission where sharing is based on coarse granularity. This type of DWDM backbone network, offering a few light-paths, provides no support for QoS services traversing the network. As DWDM networks with larger numbers of wavelengths penetrate the data-centric metro environment, specific IP service requirements such as priority restoration, scalability, dynamic provisioning of capacity and routes, and support for coarse-grain QoS capabilities will have to be addressed in the optical domain in order to achieve end-to-end QoS over a DWDM network. We propose a QoS service model in the optical domain called differentiated optical services (DoS) based on a set of optical parameters that captures the quality and reliability of the optical lightpath     

基于无线传感器网络汇聚传输实时性的分布式调度算法

在无线传感器网络多种应用中,各节点需要在短时间内将采集的数据传输至汇聚节点,从而形成多对一的汇聚传输。针对网络汇聚传输的实时性,提出了一种分布式的节点传输调度算法。各节点只需要根据一跳范围内的邻居信息进行传输调度。仿真和分析表明该算法可以有效避免数据碰撞,并使得完成一次全网数据收集所需要的时隙数基本在网络节点总数的1.6到1.8倍左右,比目前其他调度算法在实时性和复杂度方面更具有优势。     

区分服务网络中自适应加权调度方案的研究

针对现有区分服务网络中多服务间带宽公平性问题，提出了一种自适应加权调度方案。该方案通过对本地节点缓存区指标的定期测量，计算得到在各队列间公平分配剩余带宽的调度权值。仿真结果表明，该方案可以在网络负载变化时自适应的快速调整到理想调度值，有效改进了带宽分配的公平性。     

Proportional differentiated services: delay differentiation andpacket scheduling

The proportional differentiation model provides the network operator with the 'tuning knobs' for adjusting the per-hop quality-of-service (QoS) ratios between classes, independent of the class loads. This paper applies the proportional model in the differentiation of queueing delays, and investigates appropriate packet scheduling mechanisms. Starting from the proportional delay differentiation (PDD) model, we derive the average queueing delay in each class, show the dynamics of the class delays under the PDD constraints, and state the conditions in which the PDD model is feasible. The feasibility model of the model can be determined from the average delays that result with the strict priorities scheduler. We then focus on scheduling mechanisms that can implement the PDD model, when it is feasible to do so. The proportional average delay (PAD) scheduler meets the PDD constraints, when they are feasible, but it exhibits a pathological behavior in short timescales. The waiting time priority (WTP) scheduler, on the other hand, approximates the PDD model closely, even in the short timescales of a few packet departures, but only in heavy load conditions. PAD and WTP serve as motivation for the third scheduler, called hybrid proportional delay (HPD). HPD approximates the PDD model closely, when the model is feasible, independent of the class load distribution. Also, HPD provides predictable delay differentiation even in short timescales     

Adaptive connection admission control for differentiated services access networks

In our earlier work, we have proposed some modifications for the bandwidth broker framework. With our modifications, it is possible to use measurement-based admission control in addition to the more traditional parameter-based admission control. Moreover, we have presented a new flexible admission control scheme that has proven to be very efficient in terms of bottleneck link utilization. Two problems, however, have arisen: the use of scheduling weights in admission control and bursty connection arrivals. In this paper, we present that the former one can be dealt with the use of adaptive scheduling weights, while the latter one can be fought with adaptive reservation limits. The proposed new algorithms are validated through simulations and their performance is compared against the nonadaptive basic scheme.     

RSVP extensions for real-time services in wireless mobile networks

Currently, the RSVP model, which is efficient resource reservation in the fixed endpoints, becomes invalid under host mobility. We investigate the problems of standard RSVP in providing real-time services in wireless mobile networks. We also observe carefully how to interoperate IntServ services over DiffServ networks, and how to map IntServ QoS parameters into a wireless link. We then identify the advantages and drawbacks of the existing RSVP proposals to support QoS under both micromobility and macromobility. We finally propose a dynamic resource allocation scheme for reducing service disruption of real-time applications due to frequent mobility of a host     

Connection-based scheduling for supporting real-time traffic in wireless mesh networks

Packet transmission scheduling for supporting real-time traffic in a WMN is difficult, and one of the main challenges is to coordinate temporal operations of the mesh access points (APs) in order to provide strict latency guarantee while efficiently utilizing the radio resources. In this paper a connection-based scheduling (CBS) scheme is proposed. Connections with more hops are given a higher priority, and connections with a lower priority can only use resources remaining from serving all higher priority ones. For each multihop connection, the scheduling minimizes latency between successive hops. A connection-based optimization problem is formulated with an objective to minimize the amount of required AP resources, subject to the latency requirement of the connections. Numerical results show that the proposed scheduling scheme achieves close-to-optimum performance at both the connection and packet levels.     

Bandwidth aggregation for real-time applications in heterogeneous wireless networks

A variety of wireless interfaces are available for today's mobile user to access Internet content. When coverage areas of these different technologies overlap, a terminal equipped with multiple interfaces can use them simultaneously to improve the performance of its applications. In this paper, we motivate the advantages that can be had through simultaneous use of multiple interfaces and present a network layer architecture that enables diverse multiaccess services. In particular, we explore in depth one such service provided by the architecture: Bandwidth Aggregation (BAG) for real-time applications. An important aspect of the architecture when providing BAG services for real-time applications is the scheduling algorithm that partitions the traffic onto different interfaces such that the QoS requirements of the application are met. We propose one such algorithm Earliest Delivery Path First (EDPF), that ensures packets meet their playback deadlines by scheduling packets based on the estimated delivery time of the packets. We show through analysis that EDPF performs close to an idealized Aggregated Single Link (ASL) discipline, where the multiple interfaces are replaced by a single interface with same aggregated bandwidth. A prototype implementation and extensive simulations carried using video and delay traces show the performance improvement BAG with EDPF scheduling offers over using just the Highest Bandwidth Interface (HBI) and other scheduling approaches based on weighted round robin.     

A cost-based scheduling algorithm for differentiated service on WDM optical networks

One of the important issues in the design of future generation of high-speed networks is to provide differentiated services to different types of traffic with various time constraints. We propose an adaptive scheme to manage message transmission in single-hop passive-star coupler based wavelength-division multiplexing (WDM) optical networks. This study suggests that when scheduling message transmission in WDM networks a differentiated service should be considered in order to meet the time constraint to transmission of real-time messages while non real-time messages are being served so that the overall performance of the network could be improved.     

Jitter analysis of homogeneous traffic in differentiated services networks

A critical challenge for networking vendors and carrier companies is to be able to accurately estimate the quality of service (QoS) that will be provided based on the network architecture, router/switch topology, and protocol applied. In addition, due to the development of technologies like multiprotocol label switching (MPLS) and generalized MPLS (GMPLS), which can deploy differentiated services (DiffServ), the variation in QoS performance based on the priority assignment is of significant importance. In this focus, this paper provides a theoretical analysis of interarrival packet jitter of homogeneous traffic based on a nonpreemptive head-of-the-line (HOL) priority scheme.     

Dynamic inter-SLA resource sharing in path-oriented differentiated services networks

This paper proposes novel resource sharing schemes for differentiated services (DiffServ) networks, to achieve both high resource utilization and quality of service (QoS) guarantee. Service level agreements (SLAs) are negotiated at network boundaries and supported by path-oriented resource mapping within the network. The recently proposed SLA management scheme based on virtual partitioning (Bouillet et al., 2002) allows overloaded SLAs to exploit the spare capacity of underloaded SLAs for efficient resource utilization, however, at the the cost of possible SLA violation of the underloaders. In the bandwidth borrowing scheme proposed here, the dedicated bandwidth for underloaded SLAs is determined and adaptively adjusted at network boundaries according to the actual traffic load and QoS policies; the available spare capacity is then properly distributed to related links for lending to others. On the other hand, the traffic flows admitted with borrowed bandwidth are tagged and may be preempted later when the original bandwidth owner needs to claim back the resources. Through a detailed implementation design and extensive computer simulation results we show that, by bandwidth borrowing, both SLA compliance and high resource utilization can be achieved in various load conditions, with some side benefits such as call-level service differentiation, small admission overhead, and convenience for policy-based management. In addition, we propose a distributed bandwidth pushing scheme that can dynamically adjust the spare bandwidth distribution over the network. Combining bandwidth pushing with bandwidth borrowing, the resource utilization can be further improved.     

Frame-level asymptotic analysis of real-time scheduling policy for wireless networks

A wireless scheduling policy for real-time applications is proposed and analysed. In the short term, the policy is fairer than the near-optimal feasible earliest due date algorithm. Using the delay-model approach, a frame-level asymptotic analysis is presented. A simple and accurate approximate expression is also obtained.     

Joint utility function-based scheduling for two-way communication services in wireless networks

A type of joint utility function-based scheduling is proposed for two-way communication services in wireless networks. The scheduling of uplink and downlink services is done jointly so that the base station selects a user efficiently and fairly while considering the channel state of both the uplink and the downlink. Because a user generally has two communication links, an uplink and a downlink, the overall satisfaction with a communication service can be formulated as the sum of the quality of the uplink and downlink services. However, most of the previous types of scheduling for the uplink and downlink were designed separately and independently. This paper proposes a joint scheduling algorithm for integrated uplink and downlink services: a base station selects a user while simultaneously considering both the uplink channel state and the downlink channel state. An analytical model is developed for the purpose of determining the scheduling metric, the system throughput, and the level of fairness. The numerical and computer simulation results show that in comparison with conventional proportional fair scheduling the proposed joint scheduling achieves a better throughput while satisfying the fairness among users.     

Network traffic demand patterns for video over relative differentiated services networks

Relative service differentiation mechanisms such as DiffServ Assured Forwarding are promising techniques for future delivery of video services due to their desirable scalability properties and the ability to trade-off cost and loss rate. This trade-off is important since the loss of certain parts of a video bitstream (e.g. motion information) has a catastrophic effect on the quality of the decoded sequence whereas the loss of other information (e.g. high-frequency transform coefficients) does not. We investigate the performance of these systems under realistic conditions where per-packet tariffs must remain fixed for relatively long periods of time but the network conditions may change over short timescales. We also consider how the presence of many users on a network, each with their own unique notions of utility interact in the context of a single shared network. We show that so long as the network behaves in a certain way as the overall load fluctuates the distribution of traffic among service classes remains largely unchanged. An essential consideration is not simply the mapping of video packets to service classes but also the rate of generation of video packets and thus the amount of protection that can be given to each packet. This is an important result as it demonstrates that such a network “makes sense” and will not simply regress to behave like a best-effort network.     

Efficient channel borrowing strategy for real-time services inmultimedia wireless networks

An efficient resource sharing strategy is proposed for multimedia wireless networks. We assume the channel resource in a wireless system is partitioned into two sets: one for voice calls and one for video calls. In the proposed channel borrowing strategy, voice calls can borrow channels from those pre-allocated to video calls temporarily when all voice channels are busy. A threshold type decision policy is designed such that the channel borrowing request will be granted only if the quality of service (QoS) requirement on video call blocking will not be violated during the duration of channel lending. An analytical model is constructed for evaluating the performance of the channel borrowing strategy in a simplified wireless system and is verified by computer simulations. We found that the proposed channel borrowing scheme can significantly reduce the voice call blocking probability while the increase in video call blocking probability is insignificant     

Performance evaluation of eventing web services in real-time applications

The objective of this research is to study the application of Web services technology in distributed real-time data delivery systems, as well as to determine the appropriate contexts in which such a design can be considered. We focus on distributed real-time systems and more specifically, on distributed soft real-time systems, which stand to benefit most from the use of Web services technology. We provide a means to evaluate the inclusion of Web services-based middleware in real-time system design. The decision to use the standardized data representation and communications protocols of Web services can bring tremendous value and benefit to both the service provider and the end user of a real-time system; however, the temporal performance of such systems is a critical factor. This research examines the most significant general performance considerations applicable to such systems and more specifically, provides a model to be used in the determination of whether a given system configuration can meet a specific soft real-time performance target.