In this letter, we propose an OpenFlow (OF)-based SCAlable Routing strategy (OSCAR) for modular data center networks (DCN) using a hybrid addressing mechanism. Each module in the DCN constitutes a segment in the netwo...
详细信息
In this letter, we propose an OpenFlow (OF)-based SCAlable Routing strategy (OSCAR) for modular data center networks (DCN) using a hybrid addressing mechanism. Each module in the DCN constitutes a segment in the network. Inter-segment routing is performed using virtual MAC (VMAC) ids assigned to the segments and intra-segment routing is done using ip addresses. OF provides central control over the network but it suffers from limited scalability in DCNs due to high controltraffic. In OSCAR, the controltraffic is minimized to achieve high scalability and flexibility in DCN routing.
Recently, ip satellite networks have attracted considerable interest as a technology to deliver high-bandwidth ip-based multimedia services to nationwide areas. In particular, ip satellite networks seem to be one of t...
详细信息
Recently, ip satellite networks have attracted considerable interest as a technology to deliver high-bandwidth ip-based multimedia services to nationwide areas. In particular, ip satellite networks seem to be one of the most promising technologies for connecting users in rural areas, where a wired high-speed network (e.g., xDSL) is not foreseen to be used. However, one of the main problems arising here is to guarantee specific quality of service constraints in order to have good performance for each traffic class. Among various QoS approaches used in the Internet, recently the DiffServ technique has become the most promising solution, mainly for its scalability with respect to the IntServ approach. Moreover, in satellite communication systems, DiffServ computational capabilities are placed at the edge points, reducing the implementation complexity of the satellite onboard equipment. This article deals with the problem of QPS provisioning for packet traffic by considering some resource allocation schemes, including bandwidth allocation techniques and priority-driven onboard switching algorithms. As to the first aim, the proposed technique takes advantage of proper statistical traffic modeling to predict future bandwidth requests. This approach,takes into consideration DiffServ-based traffic management to guarantee QoS priority among different users. Moreover, the satellite onboard switching problem has been addressed by considering a suitable implementation of the DiffServ policy based on a cellular neural network.
In this paper, we address the congestion control multicast routing problem in wireless ad hoc networks through the medium access control (MAC) layer. We first introduce the Broadcast Medium Window (BMW) MAC protocol, ...
详细信息
ISBN:
(纸本)081944250X
In this paper, we address the congestion control multicast routing problem in wireless ad hoc networks through the medium access control (MAC) layer. We first introduce the Broadcast Medium Window (BMW) MAC protocol, which provides reliable delivery to broadcast packets at the MAC layer. We then extend the wireless On-Demand Multicast Routing Protocol (ODMR-P) to facilitate congestion control in ad hoc networks using BMW. Through simulation, we show that ODMRP with congestion control adapts well to multicast sources that are aggressive in data transmissions.
traffic engineering has become a central topic in contemporary public ipnetworks, driven by economic considerations and the competitive aspiration on the part of network service providers to reduce operational expend...
详细信息
ISBN:
(纸本)0819446475
traffic engineering has become a central topic in contemporary public ipnetworks, driven by economic considerations and the competitive aspiration on the part of network service providers to reduce operational expenditures, improve service quality, and increase revenue. Internet traffic engineering deals with the performance optimization of operational ipnetworks, encompassing the application of technology and scientific principles to network planning, dimensioning, and dynamic control. The key concepts developed in this paper center around the notion of "integrated traffic engineering," which embraces a broader and more holistic view of operational network performance enhancement when compared with conventional traffic engineering, especially in ip over Optical (ipO) networks. Integrated traffic engineering refers to a new philosophy of collaborative decision making geared towards operational network performance optimization that involves simultaneous consideration of various control and management capabilities at different levels in the network hierarchy. Integrated traffic engineering is intended to increase network capacity, performance, efficiency, and survivability while reducing costs. This paper discusses the fundamental concepts of integrated traffic engineering in ipO networks.
A traffic matrix (TM) is a succinct representations of traffic exchanges between nodes in a communication network. Such a representation is of major interest to ISPs since it is needed to design the network topology, ...
详细信息
ISBN:
(纸本)0819446475
A traffic matrix (TM) is a succinct representations of traffic exchanges between nodes in a communication network. Such a representation is of major interest to ISPs since it is needed to design the network topology, perform capacity planning, configure network routing policies, and assist in traffic engineering. Research on TMs has taken off only recently and significant efforts are underway to reach solutions that enable network operators to obtain TMs systematically, either by measurement or inference approaches. In this paper we take a step toward defining a common framework for describing TMs. We introduce a two-level taxonomy of TMs based on the spatial representation of network traffic used and the aggregation level for the sources and destinations engaging in traffic exchanges. We show that conversion between traffic matrix types depends on the level of aggregation. Using the defined taxonomy, we show the relationship between traffic matrix types and their size complexity, that is, the number of elements in them. We enumerate important network engineering and management applications and use the taxonomy to clearly specify which type of traffic matrix is needed for each application. We briefly discuss scalability issues related to the methods for obtaining traffic matrices in the context of the defined taxonomy.
In order to facilitate convergence of networks and services, this article investigates a new hybrid and integrated QoS control scheme that combines electrical ip layer features with reconfigurable optical layer, and a...
详细信息
In order to facilitate convergence of networks and services, this article investigates a new hybrid and integrated QoS control scheme that combines electrical ip layer features with reconfigurable optical layer, and addresses cross-layer design on QoS control in optical Internet (i.e., ip/WDM networks). The proposed integrated QoS control scheme can not only provide appropriate transport service for various types of traffic relating to different service categories in a cost-effective way, but also maintain high flexibility/scalability for integrated services provisioning, which seems to be preferred for QoS provisioning in the next-generation multiservice integrated optical Internet.
In this paper we study regenerator placement and traffic engineering of restorable paths in Generalized Multiprotocol Label Switching (GMPLS) networks. Regenerators are necessary in optical networks due to transmissio...
详细信息
ISBN:
(纸本)0819446475
In this paper we study regenerator placement and traffic engineering of restorable paths in Generalized Multiprotocol Label Switching (GMPLS) networks. Regenerators are necessary in optical networks due to transmission impairments. We study a network architecture where there are regenerators at selected nodes and we propose two heuristic algorithms for the regenerator placement problem. Performances of these algorithms in terms of required number of regenerators and computational complexity are evaluated. In this network architecture with sparse regeneration, offline computation of working and restoration paths is studied with bandwidth reservation and path rerouting as the restoration scheme. We study two approaches for selecting working and restoration paths from a set of candidate paths and formulate each method as an Integer Linear Programming (ILP) problem. traffic uncertainty model is developed in order to compare these methods based on their robustness with respect to changing traffic patterns. traffic engineering methods are compared based on number of additional demands due to traffic uncertainty that can be carried. Regenerator placement algorithms are also evaluated from a traffic engineering point of view.
A framework for resource management of MPLS label-switched routes (LSRs) over a diffserv Internet domain is described. A "traffic management" problem is formulated in which the LSRs are not statically alloca...
详细信息
ISBN:
(纸本)081944250X
A framework for resource management of MPLS label-switched routes (LSRs) over a diffserv Internet domain is described. A "traffic management" problem is formulated in which the LSRs are not statically allocated an amount of bandwidth and buffers per node. A very limited amount of information is passed on to the diffserv nodes about the traffic characteristics and QoS requirements using the LSR. The diffserv node can use this information and on-line queue measurements for dynamic resources (bandwidth and buffer) management. In this general context, a suitable "shaped" weighted round-robin (SWRR) bandwidth scheduling mechanism is specified. Performance and implementation issues are explored for SWRR. Finally, how SWRR can approximate weighted fair queueing (WFQ) is discussed.
Internet measurements show that the size distribution of Web-based transactions is usually very skewed;a few large requests constitute most of the total traffic. Motivated by the advantages of scheduling algorithms wh...
详细信息
ISBN:
(纸本)0819446475
Internet measurements show that the size distribution of Web-based transactions is usually very skewed;a few large requests constitute most of the total traffic. Motivated by the advantages of scheduling algorithms which favor short jobs, we propose to perform differentiated control over Web-based transactions to give preferential service to short web requests. The control is realized through service semantics provided by Internet traffic Managers, a Diffserv-like architecture. To evaluate the performance of such a control system, it is necessary to have a fast but accurate analytical method. To this end, we model the Internet as a time-shared system and propose a numerical approach which utilizes Kleinrock's conservation law to solve the model. The numerical results are shown to match well those obtained by packet-level simulation, which runs orders of magnitude slower than our numerical method.
While the integrated services (IntServ) solution to Internet QoS can achieve a strong service model that guarantees flow throughputs and loss rates, it places excessive burdens on high-speed core routers to signal, sc...
详细信息
While the integrated services (IntServ) solution to Internet QoS can achieve a strong service model that guarantees flow throughputs and loss rates, it places excessive burdens on high-speed core routers to signal, schedule, and manage state for individual flows, Alternatively, the differentiated services solution achieves scalability via aggregate control, yet cannot ensure a particular QoS to individual flows. To simultaneously achieve scalability and a strong service model, we have designed and implemented a novel architecture and admission control algorithm termed egress admission control. In our approach, the available service on a network path is passively monitored, and admission control is performed only at egress nodes, incorporating the effects of cross traffic with implicit measurements rather than with explicit signaling. In this paper, we describe our implementation of the scheme on a network of prototype routers enhanced with ingress-egress path monitoring and edge admission control. We report the results of testbed experiments and demonstrate the feasibility of an edge-based architecture for providing IntServ-like services in a scalable way. (C) 2001 Elsevier Science B.V. All rights reserved.
暂无评论