This paper explains how DiffServ has been implemented in an ip network simulator using an asynchronous conservative parallel discrete event simulation (PDES) kernel. DiffServ provides quality of service (QoS) function...
详细信息
This paper explains how DiffServ has been implemented in an ip network simulator using an asynchronous conservative parallel discrete event simulation (PDES) kernel. DiffServ provides quality of service (QoS) functionality for ipnetworks and is designed to provide greater scalability and lower overhead than previous ip based QoS schemes. The paper explains the DiffServ components that have been implemented, focusing on the implementation of the preemptive network buffers required to provide DiffServ functionality. Certain optimisations possible for non-preemptive network buffers are not possible here. The paper explores which will work in the preemptive case. In particular, exploiting lookahead is more difficult leading to reduced performance in some cases. Optimisation schemes are described for two different preemptive buffering strategies and performance results demonstrating the costs of using these buffers are presented.
In TDMA-based MAC (media access control) protocols for satellite network access, slotted ALOHA which has been widely deployed in Very Small Aperture Terminal (VSAT) systems. More recently, Generalized Retransmission A...
详细信息
ISBN:
(纸本)0780378024
In TDMA-based MAC (media access control) protocols for satellite network access, slotted ALOHA which has been widely deployed in Very Small Aperture Terminal (VSAT) systems. More recently, Generalized Retransmission Announcement Protocol (GRAP) was proposed in [5], which regroups the immediate access by contention at low loads and the reservation access at higher loads to achieve a better efficiency. Inspired by GRAP, we propose a new MAC protocol (CA-GRAP) using cumulative acknowledgment (CA) technique to further improve the success probability of reservation request. Furthermore, the efficiency of random access in CA-GRAP is improved by introducing contention index. Our proposal does not require collision or error detection but is based only on correctly received packets, dramatically simplifying the procedure. The impact of all these protocols on TCP traffic is investigated and an upper bound of TCP throughput at high loads is derived for GRAP-based protocols. Simulation results show that our new method significantly outperforms GRAP.
Although the Optical Transport Network, based on technologies such as Wavelength Division Multiplexing and Optical Cross-Connects, offers tremendous transportation capacity, its management requires frequent manual int...
详细信息
ISBN:
(纸本)0819451304
Although the Optical Transport Network, based on technologies such as Wavelength Division Multiplexing and Optical Cross-Connects, offers tremendous transportation capacity, its management requires frequent manual intervention. However, as the traffic pattern offered to today's transport networks is subject to continuous changes due to the Internet traffic dominance, an optical transport network with a smart, automatic and real-time control system, denoted as Intelligent Optical Network (ION) or Automatic Switched Optical Network (ASON), is desired by network operators. Duly and correctly retrieving the changing traffic load information is a very important factor for the successful deployment of an ION. In this paper, we discuss the influence of the observation window size used for collecting the traffic load information, on the performance of an ION. By comparing the performance of an ION using different traffic observation window sizes, we show that a smaller observation window harms the network stability;while a too large observation window worsens the network reliability. We demonstrate that a suitable traffic observation window size improves the offered Quality of Service (QoS) by reconfiguring the logical layer network at the right time and in the right way.
This paper proposes a translator which maps QoS parameters between Intserv/RSVP and DiffServ such that it guarantees end-to-end QoS. This translator is placed at the interface between those two networks. For traffic f...
详细信息
This paper proposes a translator which maps QoS parameters between Intserv/RSVP and DiffServ such that it guarantees end-to-end QoS. This translator is placed at the interface between those two networks. For traffic from Intserv/RSVP network to DiffServ network, the translator checks whether resources are reserved for the traffic. If reserved, the translator marks with an appropriate DiffServ Code Point (DSCP) value the ip header of each transmitted packet. In the reverse direction, however, the translator does nothing because the change of the DSCP value does not affect the traffic handling mechanism in Intserv/RSVP network. Based on these principles, a prototype of the translator was implemented and run on a network consisting of Intserv/RSVP and DiffServ networks. Experimental results show that the proposed translator provides end-to-end QoS with good scalability and significantly improves network performance with respect to throughput and packet loss.
Integration of satellite access networks with the Internet is seen as a strategic goal to achieve in order to provide ubiquitous broadband access to Internet services in Next Generation networks (NGNs). One of the mai...
详细信息
Integration of satellite access networks with the Internet is seen as a strategic goal to achieve in order to provide ubiquitous broadband access to Internet services in Next Generation networks (NGNs). One of the main interworking aspects which has been most studied is an efficient management of satellite resources, i.e. bandwidth and buffer space, in order to satisfy most demanding application requirements as to delay control and bandwidth assurance. In this context, resource management in DVB-S/DVB-RCS satellite technologies, emerging technologies for broadband satellite access and transport of ip applications, is a research issue largely investigated as a means to provide efficient bi-directional communications across satellites. This is in particular one of the principal goals of the SATip6 project, sponsored within the 5th EU Research Programme Framework, i.e. IST. In this paper we present a possible approach to efficiently exploit bandwidth, the most critical resource in a broadband satellite access network, while pursuing satisfaction of delay and bandwidth requirements for applications with guaranteed QoS through a trafficcontrol architecture to be implemented in ground terminals. Performance of this approach is assessed in terms of efficient exploitation of the uplink bandwidth and differentiation and minimization of queuing delays for most demanding applications over a time-varying capacity. Opnet simulations is used as analysis tool.
Multi-protocol label switching extends the ip destination-based routing protocols to provide new and scalable routing capabilities in connectionless networks using relatively simple packet forwarding mechanisms. MPLS ...
详细信息
Multi-protocol label switching extends the ip destination-based routing protocols to provide new and scalable routing capabilities in connectionless networks using relatively simple packet forwarding mechanisms. MPLS networks carry traffic on virtual connections called label switched paths. This paper considers path selection and bandwidth allocation in MPLS networks in order to optimize the network quality of service. The optimization is based upon the minimization of a non-linear objective function which under light load simplifies to OSPF routing with link metrics equal to the link propagation delays. The behavior under heavy load depends on the choice of certain parameters. It can essentially be made to minimize maximal expected utilization, or to maximize minimal expected weighted slacks (both over all links). Under certain circumstances it can be made to minimize the probability that a link has an instantaneous offered load larger than its transmission capacity. We present a model of an MPLS network and an algorithm which optimally distributes the traffic among a set of active paths and reserves a set of back-up paths for carrying the traffic of failed or congested paths. The algorithm is an improvement of the well-known flow deviation non-linear programming method. The algorithm is applied to compute optimal LSPs for a 100-node network carrying a single traffic class. A link carrying some 1400 routes fails. The back-up paths are activated and we compare the performance of the path sets before and after the back-up paths are deployed. (C) 2002 Elsevier Science B.V. All rights reserved.
Real-time application is one of the dominant types of traffic transported through mobile Internet protocol (Mip). The performance of the network is very dependent on the non real-time applications. Provisioning qualit...
详细信息
Real-time application is one of the dominant types of traffic transported through mobile Internet protocol (Mip). The performance of the network is very dependent on the non real-time applications. Provisioning quality of service (QoS) architecture by using differentiated service (DiffServ) has proven to be more scalable in handling real-time traffic. This paper shows how to provide an acceptable fairness for better QoS support for real-time traffic transfer in Internet. The study of the proposed scheduling algorithm named round robin priority queuing (RRPQ) in DiffServ network has been carried out through simulation work using ns2.
GMPLS, being developed by IETF and OIF, has been proposed to address traffic engineering to a variety of networking technology, and to serve in a variety of network signaling layers, extending capabilities beyond thos...
详细信息
GMPLS, being developed by IETF and OIF, has been proposed to address traffic engineering to a variety of networking technology, and to serve in a variety of network signaling layers, extending capabilities beyond those networks that are only packet-based. GMPLS is an extension of MPLS and it provides a control plane for devices that switch in the time, packet, wavelength, and fiber domains. This common control plane promises to simplify network operation and management by automating end-to-end provisioning of connections, managing network resources, and providing QoS. One of the main architecture enhancements proposed by GMPLS is the complete separation of the control and data planes, allowing high performance, intelligent networking while simplifying networks by combining transport and multiservice switching into a single layered network.
The paper proposes a new QoS framework, called on-demand QoS path (ODP), which provides end-to-end QoS guarantees to individual flows with minimal overhead, while keeping the scalability characteristic of DiffServ. OD...
详细信息
The paper proposes a new QoS framework, called on-demand QoS path (ODP), which provides end-to-end QoS guarantees to individual flows with minimal overhead, while keeping the scalability characteristic of DiffServ. ODP exercises per-flow admission control and end-to-end bandwidth reservation at the edge of the network and only differentiates service types in the core of the network. In addition, to be adaptive to traffic load, ODP monitors the bandwidth utilization status of the network and performs dynamic bandwidth reconfiguration in the core based on the network status. Through extensive simulations, the performance of the proposed architecture is investigated and compared with that of IntServ and DiffServ architectures. The simulation results clearly show that ODP could provide end-to-end QoS guarantees to individual flows with. much less overhead than IntServ.
The DiffServ architecture provides a scalable mechanism for QoS introduction in a TCP/ip network. The idea of DiffServ is based on the aggregation of traffic flows at an ingress (or egress) point of a network and the ...
详细信息
The DiffServ architecture provides a scalable mechanism for QoS introduction in a TCP/ip network. The idea of DiffServ is based on the aggregation of traffic flows at an ingress (or egress) point of a network and the ip packet marking for different priority flows, according to several classification criteria. Two approaches exist in the DiffServ architecture: the absolute and the relative. In absolute DiffServ, an admission control scheme is used to provide QoS guarantees as absolute bounds of specific QoS parameters. The relative DiffServ model provides QoS guarantees per class expressed with reference to guarantees given to the other classes defined. Our study targets at providing relative proportional delay differentiation service based on class based queue (CBQ) scheduler. The main idea is to frequently adjust the service rates allocated to classes of a CBQ scheduler in order to achieve relative delay spacing among classes. The simulation experiments conducted show that our model can attain relative delay, provided that the required delay differentiation parameters (DDPs) are feasible.
暂无评论