MPLS (Multi-Protocol Label Switching) has recently emerged to facilitate the engineering of network traffic. This can be achieved by directing packet flows over paths that satisfy multiple requirements. MPLS has been ...
详细信息
ISBN:
(纸本)0819446475
MPLS (Multi-Protocol Label Switching) has recently emerged to facilitate the engineering of network traffic. This can be achieved by directing packet flows over paths that satisfy multiple requirements. MPLS has been regarded as an enhancement to traditional ip routing, which has the following problems: (1) all packets with the same ip destination address have to follow the same path through the network;and (2) paths have often been computed based on static and single link metrics. These problems may cause traffic concentration, and thus degradation in quality of service. In this paper, we investigate by simulations a range of routing solutions and examine the tradeoff between scalability and performance. At one extreme, ip packet routing using dynamic link metrics provides a stateless solution but may lead to routing oscillations. At the other extreme, we consider a recently proposed Profile-based Routing (PBR), which uses knowledge of potential ingress-egress pairs as well as the traffic profile among them. Minimum lnterference Routing (MIRA) is another recently proposed MPLS-based scheme, which only exploits knowledge of potential ingress-egress pairs but not their traffic profile. MIRA and the more conventional widest-shortest path (WSP) routing represent alternative MPLS-based approaches on the spectrum of routing solutions. We compare these solutions in terms of utility, bandwidth acceptance ratio as well as their scalability (routing state and computational overhead) and load balancing capability. While the simplest of the per flow algorithms we consider, the performance of WSP is close to dynamic per-packet routing, without the potential instabilities of dynamic routing.
We consider a multimedia CDMA uplink where there are multiple classes of users with different Quality-of-Service (QoS) requirements. Each user is modeled as an ON-OFF source, where in the ON state., the user transmits...
详细信息
ISBN:
(纸本)081944250X
We consider a multimedia CDMA uplink where there are multiple classes of users with different Quality-of-Service (QoS) requirements. Each user is modeled as an ON-OFF source, where in the ON state., the user transmits a fixed number of bits in each time slot and in the OFF state, the user is silent. The probability of being in the ON state. known as the activity factor, could be different for different users. Assuming a constant channel gain, we first characterize the set of transmit power levels, activity factors and number of users in each class that can be supported by a system with a given spreading gain under the constraint that each user's QoS requirement must be met. Using this characterization, we then present a utility function-based algorithm for choosing the activity factors of elastic users in the network.
TCP(alpha,beta) protocols parameterize the congestion window increase value alpha and decrease ratio beta, motivated by the QoS requirements of multimedia applications for smooth rate adjustments. Based on a projectio...
详细信息
ISBN:
(纸本)0819446475
TCP(alpha,beta) protocols parameterize the congestion window increase value alpha and decrease ratio beta, motivated by the QoS requirements of multimedia applications for smooth rate adjustments. Based on a projection of the expected throughput of standard TCP(l, 1/2), modified versions of the protocol have been designed to generate smoother traffic patterns and to maintain a friendly behavior. In this paper, we study the design assumptions of TCP(alpha,beta) and we discuss the impact of equation-based modulation of alpha and beta on application efficiency. We confirm experimentally that, in general, smoothness and responsiveness constitute a tradeoff;however, we uncover undesirable dynamics of the protocols when the network is heterogeneous (wired/wireless) or the flow characteristics do not follow a prescribed and static behavior. For example, we show that smooth backward adjustments confine the protocol's capability to exploit resources that become available rapidly after a handoff in mobile network, and embarrass the fair and efficient growth of incoming flows. Furthermore, we show that in the context of wireless networks with high error rate, a low alpha dictates a conservative behavior that degrades the protocol performance with both best-effort and real-time applications;and in the context of high contention of heterogeneous flows, a low alpha does not contribute to efficiency and friendliness.
In ip over WDM multilayer optical networks, ip routers are interconnected by all-optical channels called lightpaths, of typical rates of 10, 40, or, more recently, 100 Gb/s. In this context, lightpath bundling (LB) an...
详细信息
In ip over WDM multilayer optical networks, ip routers are interconnected by all-optical channels called lightpaths, of typical rates of 10, 40, or, more recently, 100 Gb/s. In this context, lightpath bundling (LB) and anycast switching (AS) are control plane and data plane techniques, respectively, both of them to be implemented in the ip routers. LB permits grouping a set of lightpaths between two nodes that follow a common route so that they are perceived by the ip layer as a single virtual link of aggregated capacity. In its turn, AS consists of instructing the router to implement a per-packet-granularity balancing of the traffic among the lightpaths in the bundle, reducing the packet delay and the buffering requirements in the node. This happens transparently to the ip layer, which, because of the LB configuration, sees the bundled lightpaths as a single entity. In this article, we propose the combined application of the LB and AS techniques as a new paradigm (LB+AS) for optical networks. Applying the LB+AS concept requires seamless changes in the electronic equipment and no changes in the optical infrastructure. We present a case study that shows the significant performance and cost benefits LB+AS can bring to the network and its inherent scalability. In addition, we discuss other potential advantages of LB+AS and related open research lines.
In this paper we propose a new fluid model approach in which a different description of the dynamics of traffic sources is adopted, exploiting partial differential equations. This new description of the source dynamic...
详细信息
In this paper we propose a new fluid model approach in which a different description of the dynamics of traffic sources is adopted, exploiting partial differential equations. This new description of the source dynamics allows the natural representation of short-lived as well as long-lived TCP connections, with no sacrifice in the scalability of the model. In addition, the use of partial differential equations permits the description of distributions, instead of averages, thus providing better accuracy in the results. The comparison between the performance estimates obtained with fluid models and with ns-2 simulations proves the accuracy of the proposed modeling approach.
Next-generation networks (NGNs) will support quality of service over a mixed wired and wireless ip-based infrastructure. A relative model of service differentiation in differentiated services architecture is a scalabl...
详细信息
Next-generation networks (NGNs) will support quality of service over a mixed wired and wireless ip-based infrastructure. A relative model of service differentiation in differentiated services architecture is a scalable solution for delivering multimedia traffic. However, considering the dynamic nature of radio channels specifically, it is difficult to achieve a given service provisioning working at the ip and lower layers separately as in the classical approach without a run-time adaptation of the system towards the target quality. This work describes an ip cross-layer scheduler able to support a Proportional Differentiation Model (PDM) for delay guarantees also over wireless. The key idea is to leverage feedbacks from the lower layers about the actual delays experienced by packets in order to tune at run-time the priority of the ip service classes in a closed-loop control with the objective of supporting a PDM at the interface on the whole, considering the cumulative latency across multiple layers, as relevant for the end-user. A simulation analysis demonstrates the prominent improvements in reliability and robustness of the proposal in the case of time-variant performance of the MAC and PHY layers with respect to the classical non-cross-layer approach and open-loop control. Furthermore, considerations on the required functionality and likely deployment scenarios highlight the scalability and backward compatibility of the designed solution, addressing a sustainable approach and smooth migration to NGNs.
Internet traffic on a network link can be modeled as a stochastic process. After detecting and quantifying the properties of this process, using well known tools from statistics, as well as some variants, a series of ...
详细信息
ISBN:
(纸本)0819446475
Internet traffic on a network link can be modeled as a stochastic process. After detecting and quantifying the properties of this process, using well known tools from statistics, as well as some variants, a series of mathematical models is developed, culminating to one which is able to generate "traffic" that exhibits-as a key feature-different behavior in different time scales, similar to real traffic, and is moreover indistinguishable from real traffic by other statistical tests as well. Tools inspired from the models are then used to determine and calibrate the type of activity taking place in each of the time scales. The above procedure does not require any detailed information originating from either the network dynamics, or the decomposition of the total traffic into its constituent user connections, but rather only the compliance of these connections to very weak conditions.
In a sense, the ip Diffserv concept 'exploits' important technological trends like growing processing and transmission speeds and decreasing costs of bandwidth. This enables QoS provisioning with less complex ...
详细信息
ISBN:
(纸本)0819438766
In a sense, the ip Diffserv concept 'exploits' important technological trends like growing processing and transmission speeds and decreasing costs of bandwidth. This enables QoS provisioning with less complex traffic management mechanisms than used in other broadband multi-service networks like ATM and ip Intserv. Roughly, one can say that the need for traffic management on small time scales (e.g. sophisticated packet scheduling) becomes smaller, while the role of traffic management on larger time scales (e.g. bandwidth provisioning based on network load measurements) becomes more important. In particular, pre argue that admission control in ip Diffserv can be performed on aggregate how level (important for scalability!) instead of on individual hows as in ATM or ip Intserv, while still guaranteeing suitable QoS levels. We also discuss the related issue of network dimensioning: and point out possible dimensioning approaches for ip Diffserv networks.
A shift in customer requirements together with a growth in more demanding applications has exposed the limitations of the best-effort service offered in ipnetworks. This paper presents a novel approach to managing tr...
详细信息
ISBN:
(纸本)0780381459
A shift in customer requirements together with a growth in more demanding applications has exposed the limitations of the best-effort service offered in ipnetworks. This paper presents a novel approach to managing traffic demand across ipnetworks by modifying existing routing algorithms and employing agent-based intelligence. A hybrid multi-agent architecture to manage quality of service (QoS) provisioning in the Internet is detailed. This achieves a balance between centralisation and distribution to improve both robustness and scalability. Intelligent agents are employed in this system to anticipate congestion and respond to changes in traffic patterns and other network stresses. A pseudo-delay mechanism is used to reroute less vital traffic from optimal routes. Results indicate that routing such traffic along sub-optimal paths enhances traffic performance in multi-class networks.
We propose a first-time in-operation ip-over-optical network planning method that offers optical path provisioning criteria under temporal and geographical iptraffic changes. Simulations show the proposed method can ...
详细信息
ISBN:
(纸本)9781479930661
We propose a first-time in-operation ip-over-optical network planning method that offers optical path provisioning criteria under temporal and geographical iptraffic changes. Simulations show the proposed method can support traffic transitions with less additional optical path provisioning.
暂无评论