Showing papers on "Traffic classification published in 2000"

The complementary roles of RSVP and differentiated services in the full-service QoS network

Abstract: With the growth of the Internet and intranets, QoS technology that has been developed over a span of several years is quickly becoming more relevant. This article first defines QoS and introduces a taxonomy for QoS mechanisms. The evolution of several major QoS mechanisms is described with a special focus on RSVP and differentiated services. Special attention is paid to the role of the IETF in developing QoS mechanisms. We describe a QoS network that combines RSVP and differentiated services in a manner that realizes the benefits of each. We show that, in general, the adoption of increasingly sophisticated QoS mechanisms can enhance the ability of a network to offer high-quality service guarantees while simultaneously making efficient use of raw network resources. These mechanisms carry a cost in the form of increased overhead, which must be weighed against the benefits of the mechanism.

Internet Traffic Data

Abstract: (2000). Internet Traffic Data. Journal of the American Statistical Association: Vol. 95, No. 451, pp. 979-985.

Network traffic analyzer

Abstract: A system for and method of analyzing packet traffic in a packet-switched network, including collecting traffic logs from a network operations center, wherein the traffic logs are representative of packet traffic passing through an actual configuration of the network, and wherein each traffic log includes the time the traffic log was created and an associated packet's network entry and exit points. The collected traffic logs are stored in a computer such that the traffic logs can be replayed. A computer file is thereafter created and is representative of a modified network configuration that is different from the actual configuration of the network. The traffic logs are replayed in coordination with the modified network configuration to generate a histogram file representative of packet traffic passing through or via at least one of a host, node or link in the modified network configuration.

On traffic types and service classes in the Internet

Abstract: In today's Internet, various traffic types having different characteristics and requirements (e.g., voice, video, best effort) share the same resources. In order to provide services that an appropriate to each, both the IETF and IEEE 802 have proposed a support for traffic differentiation. In both cases, service classes corresponding to separate queues an identified, and packets an marked according to their class, which in turn defines the treatment they will get at each hop in the network. Using realistic models to represent each of the various traffic types, we identify those that can be mixed in the same queue without bearing a significant loss in throughput; correspondingly, we make recommendations on how to map different traffic types to the available service classes.

Multicommodity flow method for designing traffic distribution on a multiple-service packetized network

Abstract: A method is described for solving traffic engineering problems in a network. In one aspect, the invention is used in a network that has at least one QoS service class and at least one class of service that is not a QoS class. Bandwidth is allocated to service routes in the QoS service class so as to optimize a figure of merit such as network revenue. Then a new allocation is made so as to minimize network usage without departing too far from the optimal value of the figure of merit. A residual network consists of that bandwidth that remains unallocated, on each link of the network. Bandwidth for non-QoS traffic is allocated to routes on the residual network. In a second aspect, the invention involves the use of optimization techniques to allocate bandwidth among service routes in one or more service classes in response to a set of demands in each class. The demands are calculated so as to take into account an effective bandwidth associated with the pertinent class, and so as to make allowance for the stochastic behavior of the traffic demands that occur in practice.

Providing quality of service in the internet

Abstract: This dissertation presents a framework for providing quality of service (QoS) in the Internet. This framework consists of traffic directing and load balancing at the application layer, differentiated services (Diffserv) at the transport layer, traffic engineering and fast reroute at the network layer. Traffic directing is to utilize the high-performance part of a network as much as possible and avoid using the low performance part. Load balancing is to distribute client requests to multiple servers so that service availability and responsiveness is increased. Approaches for traffic directing and load balancing are briefly described. Diffserv is to divide traffic into different classes and treat them differently, especially when there is a shortage of network resources. Mechanisms needed at the edge and at the core of the network are described. These mechanisms can be used to achieve the desired per-hop behaviors (PHBs). By concatenating all these PHBs together, a certain level of QoS can be provided end to end. A conflict between Diffserv and TCP is also described, and a solution for resolving this conflict is proposed. This solves a significant problem in the Internet. Traffic engineering is an iterative process of network planning and network optimization. Network planning is to improve the architecture (topology and link capacity) of a network in a systematic way so that the network is easy to operate, robust, and adaptive. Network optimization is to control the mapping and distribution of traffic over the existing network infrastructure to avoid and/or relieve congestion, and thus to optimize resource efficiency. The issues of designing a traffic engineering systems are discussed. A national traffic engineering system with multi-protocol label switching (MPLS) is then presented, and its performance evaluated. Based on the experience of implementing this system, a generic procedure is proposed for deploying large-scale traffic engineering systems. An approach for performing inter-domain traffic engineering in a quantitative way is then described. We also propose an offline constraint-based routing algorithm for computing the paths for MPLS label switched paths (LSPs), and describe how to provide Diffserv in an MPLS environment. Two emerging technologies that are closely related to traffic engineering, multi-protocol lambda switching (MPLmS) and fast reroute , are also discussed. Constraint-based routing is one of the most important tools for traffic engineering. The issues related to constraint-based routing are discussed in detail. Heuristics for computing paths with propagation delay constraint, and for QoS routing on the top of virtual networks constructed in the traffic engineering process, are proposed. In order to reduce the computation complexity of constraint-based routing, an algorithm is proposed for reducing the routing table computation cost for OSPF. The correctness of the algorithm is illustrated. Similar idea can also be applied to IS-IS. In summary, this dissertation not only discusses on all major issues related to QoS, but also presents a systematic approach for providing QoS in the Internet.

QOS In Wide Area Networks

Abstract: 1 Introduction Why QOS? What Is qos? Congestion: Death Knell to Effective QOS Provisioning and Supporting QOS Flow Longevity Cooperative and Noncooperative Networks The Internet: An Noncooperative Network Applications' Natural Bit Rate The QOS Models Functional Equivalence Class (FEC) Scope of QOS Service and QOS Domains Qualitative and Quantitative Service Levels Genesis of QOS: X25 Service Level Agreements (SLAs) Policy-Based Networking SLA Monitoring Points Summary Appendix 1:A Characteristics of the Internet Round-Trip Time (RTT) Traffic Loss Fixed vs Dynamic Routing 2 QOS Concepts and Operations Statistical Multiplexing Congestion Problems Flow Control Mechanisms Explicit and Implicit Flow Control Problems with Internet Flow Control Services Solutions to the Problem Congestion, Traffic Control, and Connection Admission Control Arrival Rate and Traffic Load Queue Management Operations Operations at the Final Destination Buffer Size, Packet Size, and Traffic Loss Data "In Flight" Error Recovery in High-Speed Networks Monitoring and Traffic Tagging Associating Labels with QOS Operations Controlling Data Traffic Summary 3 QOS Evolution Network Interfaces (Reference Points) Value of the Interface Concept Evolution of the Interface/Reference Point Concept The QOS Layered Model Connection-Oriented and Connectionless Interfaces QOS in Connection-oriented and Connectionless Networks Connection Management vs Payload Integrity Management Payload Integrity Management Evolution of Payload Integrity Services Link-by-Link Operations UNI Operations End-to-End Operations Evolution of Switching and Relaying Technologies Circuit Switching Message Switching Packet Switching Frame Relay Cell Relay Network Availability: A Crucial QOS Feature Evolution of Switching and Routing Technologies Technology Comparisons Labels: The Key to Fast Forwarding Labels for Connection-Oriented Networks The Protocol Stacks The X25 Legacy Summary 4 X25 Major Features of X25 X25 Virtual Circuit and Connection Options Permanent Virtual Circuit (PVC) Operations Switched Virtual Call (SVC) Operations Fast Select Operations Call Refusal X25 Packets The General Format Identifier (GFI) Field The Packet Identifier Data Packets Flow Control and Reject Packets Diagnostic Packet Interrupt Packet Registration Packet Example of an X25 Data Transfer The X2 Recommendation The X25 QOS Operations: Facilities Calls Barred Facilities Closed User Group (CUG) Facilities Reverse Charging Facilities Network User Identification (NUI) Facilities Charging Facility Non-Standard Packet Sizes Non-Standard Window Size Facility Example of Facility Negotiations Throughput Facility Transit Delay and Indication Facility Packet Retransmission Facility Extended Packet Sequencing Hunt Group Facility Call Redirection and Deflection Facilities Online Facility Registration Facility Recognized Private Operating Agencies (RPOA) Facility Summary 5 Frame Relay Frame Relay Features The Frame Relay Frame Congestion Notification Discard Eligibility The CIR Flow Control and Congestion Management The CIR Revisited The Bellcore Model Committed and Burst Rate Management Measurement at Intervals Examples of Bc and CIR Operations Relationship of CIR, Frame Size, and Link Speed CIR and Tc Guidelines on Use of FECN and BECN FECN Usage BECN Usage Use of Windows Other QOS Operations and Measurements Throughput Transit Delay Virtual Circuit Transit Delay Residual Error Rate (RER) Emission and Discard Priorities Other Parameters Other Frame Relay Specifications The Consolidated Link Layer Management (CLLM) Specification Switched Virtual Calls (SVCs) Asymmetrical QOS The Other SVC Messages Message Format Additions to Frame Relay Operations Fragmentation Voice over Frame Relay (VoFR) Multilink Frame Relay (MFR) Multicasting Frame Relay Forum's Service Level Definitions SL Measurement Domains The SL Parameters and Algorithms Summary 6 ATM ATM Features ATM Specifications The Anchorage Accords The ATM Cell Service Classes and the AAL The AAL Data Units Voice Support in ATM Protecting the Connection Performance Parameters Congestion, Traffic Control, and Connection Admission Control QOS Measurements and Degradation Factors Traffic Shaping Cell Emission for CBR Traffic Connection Admission Control (CAC) Usage Parameter Control (UPC) Virtual Scheduling and Continuous-State Leaky Bucket Algorithms Basic Concepts of the Leaky Bucket Generic Cell Rate Algorithm (GCRA) Examples of the Leaky Bucket Operation The ARB and UBR Service Classes Approaches to ABR Implementations ATM Forum ABR Operations Performance Management Using Connections on Demand to Negotiate QOS Connection Management Messages Other Signaling Messages Summary 7 Internet QOS Protocols Why IPv6? Scarcity of QOS in IPv4 and IPv6 Summary of Changes The IPv6 Address The IPv6 Datagram IPv4 and IPv6 Headers IPv6 Extension Headers Fragmentation Header Hop-by-Hop Options Header Security Extension Headers Routing Header Destination Options Header Internet Control Management Protocol (ICMP) for IPv6 Interworking IPv4 and IPv6 TCP and its Effect of QOS How TCP Handles User Traffic Interactive Traffic Bulk Traffic Example of TCP Traffic Accounting Operations The TCP Timer Timer Values The Nagle Algorithm Slow Start Role of UDP in the QOS Picture Role of Multicasting, RTP, RTCP, and RSVP in the QOS Picture Summary 8 Differentiated Services (DiffServ) DiffServ Architecture DiffServ: Control Plane and Data Plane Comparison of QOS Technologies DS Domains DS Regions Traffic Classification and Conditioning Classification Operations Metering Operations Average Rate Meter Exponential Weighted Moving Average (EWMA) Meter Token Bucket Meter Representations of the Meters More Ideas on Marking and Shaping Operations Another Look at the Traffic Conditioning Block (TCB) The DS Codepoint (DSCP) DS Guaranteed Rate (GR) Assured and Expedited Forwarding PHBs Summary Appendix 8:A Differentiated Services (DiffServ) 9 IP-Based Layer 2 and 3 Switching and Routing Label Switching Assigning Labels A Switching/Routing Taxonomy What Is Next? Position of Protocols Encapsulation Headers Summary 10 Internetworking IP, X25, Frame Relay, and ATM ATM vs IP Internetworking Frame Relay and ATM Network Interworking and Service Interworking Comparison of Frame Relay and ATM AAL 5 Operations for Frame Relay Support Mapping QOS Between ATM and Frame Relay Congestion Management Mapping Frame Relay and ATM Connection Identifiers Correlation of SVC Operations Mapping the Congestion Notification Bits Discarding Frames or Cells Segmentation and Reassembly (SAR) Functions Sequencing Operations Mapping QOS between Frame Relay and ATM ACKs and NAKs Encapsulation Rules IP and FR/ATM Summary Abbreviations Index

Network interconnection apparatus for interconnecting a LAN and an ATM network using QoS adjustment

Abstract: Network interconnection apparatus and method capable of efficiently guaranteeing optimum QoS suited to the status of actual traffic and network, whereby high-performance network interconnection is achieved without entailing lost calls. Routing information managing means manages routing information of an ATM network, and statistical information managing means manages statistical information on the traffic of a LAN. QoS setting means sets QoS which the ATM network ought to guarantee, based on the statistical information, and QoS guarantee determining means determines based on the routing information whether or not the set QoS can be guaranteed. If it is judged that the QoS cannot be guaranteed, QoS adjusting means adjusts the QoS so that the QoS can be guaranteed. Call connection control means connects call according to the QoS which can be guaranteed.

Quality of service provisioning framework for multimedia traffic in wireless/mobile networks

Abstract: We propose a quality of service (QoS) provisioning framework for multimedia traffic in wireless/mobile networks. We classify the services into three categories: bandwidth guaranteed (BG) service, bandwidth not-guaranteed (BNG) service, and best effort (BE) service. BG service is for non-adaptive multimedia traffic or non-multimedia traffic; BNG service is for adaptive multimedia traffic, whereas BE service is for computer data or multimedia traffic that can be suspended and reactivated. For each of the above three categories, traffic descriptors and QoS parameters are defined and specified. In addition, there are multiple classes for each of the above three categories. For all service categories we present, analytically, an optimal call admission control that guarantees the QoS parameters and traffic descriptors, and maximizes the revenue. Simulation results reveal that the proposed optimal call admission control scheme is very promising.

Broadband wireless networks: an investigation into the traffic behavior, control, and QoS guarantees

Abstract: We investigate the behavior of multiplexed traffic streams of different traffic classes in the radio environment, and study the effect of such behavior on the performance of the D-TDMA MAC protocol. Based on such traffic behavior, we investigate a traffic/network management set for improving the overall performance of the network.

Traffic specification for MPEG video transmission over the Internet

Abstract: The "new Internet" will allow individual application sessions to request different QoS parameters to the network Two QoS classes have been specified by the IETF: guaranteed services and controlled-load services For both of them, it is necessary to provide users with the capability of calculating the traffic characteristics, Tspec, to be declared to the network, on the basis of a limited set of parameters statistically characterizing the data source and the required level of QoS The target of this paper is to realize an analytical framework modeling the source and the access network nodes, with the purpose of calculating the Tspec parameters for MPEG video traffic To this end the video source is modeled with a switched batch Bernoulli process (SBBP), and performance in the source smoother is analytically evaluated Then the token bucket at the network access point, loaded by the output traffic of the smoother, is modeled to calculate the probability of marking nonconforming data packets

Kawaihiko and the third-quartile day [traffic management]

Abstract: The Kawaihiko network, linking the New Zealand universities to the Internet, pioneered traffic measurement as a tool for network management and cost recovery. Its history and its use of the real-time traffic flow measurement architecture to measure its traffic are described. The Kawaihiko members wanted a "measured bandwidth" metric which would be a good indicator of the bandwidth required to carry each site's traffic. Kawaihiko developed such a metric-the third-quartile day-based on a daily usage profile or third-quartile profile. The 3QP and 3QD are described in detail, and illustrated with typical plots from several of the Kawaihiko sites. The Kawaihiko members found 3QD to be an effective bandwidth measure, and 3QP a useful traffic management tool.

Two classes - Sufficient QoS for Multimedia Traffic?

Abstract: An actual trend in networking is the aggregation of traffic streams. This allows not only to keep the core equipment simple ‐ while increasing the complexity at the network edge ‐ but also to overcome scalability issues in the core network. However, traffic flows within aggregates are not distinguishable any more and therefore experience all fairly the same service quality which can be harmful in multi-service networks. In this paper several different strategies for traffic aggregation are compared in an enterprise network scenario. In order to apply realistic traffic sources, we carried out measurements of multimedia traffic streams, the results of which are presented and discussed in detail with respect to different traffic characteristics. Finally, we performed extensive simulations on several different aggregation strategies in order to show that it is possible to satisfy the individual QoS requirements of all real-time flows while maintaining an overall high load ‐ even with only two classes.

QoS constrained resource allocation for multimedia wireless networks

Abstract: To deliver high bandwidth demanding video traffic over the resource limited wireless systems is becoming a challenge issue. To control quality of service (QoS) of the delivery is even more difficult. A QoS constrained multilevel resource allocation scheme (QML-RA) is proposed to tackle the problem of how to flexibly allocate wireless network resources for carrying video traffic with certain QoS guarantees. This scheme utilizes the layer property of MPEG frames and considers the QoS requirements of different data sections within a video stream. It also takes the advantage of the channel allocation flexibility provided by CDMA/TDD systems and statistically assigns bandwidth to video traffic according to their QoS requirements. Moreover, an optimal smoothing technique is used to preprocess the video traffic so that bit-rate variability could be reduced, which enhances performance of QML-RA. The scheme significantly improves the channel utilization and increases the network throughput.

LINK-STATE AWARE DYNAMIC TRAFFIC SCHEDULING FOR PROVIDING PREDICTIVE QoS IN WIRELESS MOBILE MULTIMEDIA NETWORKS

Abstract: The performance of a centralized traffic priority based dynamic burst-level cell scheduling scheme is investigated in a correlated fading channel. The scheduling scheme is designed for the transmission of multiservice traffic over TDMA (Time Division Multiple Access)/TDD (Time Division Duplex) channels in a WATM (Wireless ATM) network. In this scheme, the number of slots allocated to a VC (Virtual Circuit) during a frame-time is changed dynamically depending on the traffic type, system traffic load, TOE (Time of Expiry) value of the data burst and data burst length. While allocating bandwidth, the channel error status is also taken into consideration. SR-ARQ (Selective Repeat - Automatic Repeat Request)-based link-level error control is assumed for all the traffic types in a multiservice traffic environment. The performance of the proposed scheme under correlated Rayleigh fading is evaluated using computer simulation for realistic voice, video and data traffic models and the QoS (Quality of Service) requirements of different traffic classes in a wireless mobile network. Simulation results show that the proposed scheduling framework can provide reasonably high channel utilization with predictive QoS guarantee in a multiservice traffic environment. The channel utilization and the perceived QoS for different services is highly affected by the traffic burstiness of the corresponding traffic type. Such a scheme can result in an energy efficient TDMA/TDD medium access control protocol for broadband wireless access.

Improving QoS for real-time traffic in a shared link

Abstract: We study the link-sharing between the assured real-time traffic and the throughput intensive best-effort services. Our simulation shows that the throughput intensive best-effort services can degrade the QoS performance of real-time services if both are forwarded to a single FIFO queue. Therefore, it is advantageous to assign separate queues for individual classes of traffic. A novel link-sharing scheme (delay-sensing) is proposed to improve the QoS measures such as delay and jitter for the real-time traffic while preserving the fairness among different traffic classes. The new method guarantees an explicit delay bound for the real-time traffic when bandwidth borrowing is allowed. Another advantage of the method is that it can offer different priority classes with user specified fairness.

Evolutive Modeling of TCP/IP Network Traffic for Intrusion Detection

Abstract: The detection of intrusions over computer networks can be cast to the task of detecting anomalous patterns of network traffic. In this case, patterns of normal traffic have to be determined and compared against the current network traffic. Data mining systems based on Genetic Algorithms can contribute powerful search techniques for the acquisition of patterns of the network traffic from the large amount of data made available by audit tools. In this paper we compare models of data traffic acquired by a system based on a distributed genetic algorithm with the ones acquired by a systembased on greedy heuristics. Also we discuss representation change of the network data and its impact over the performances of the traffic models.

Design and analysis of traffic control for guaranteed services on the Internet

Abstract: Real-time communications services will be one of the most promising applications on the Internet. Real-time traffic usually utilizes a significant amount of resources while traversing through the network. To provide guaranteed service for delay-sensitive real-time applications, both resource reservation and effective traffic control are necessary. The resource reservation protocol (RSVP) was developed to deal with the former problem while various approaches have been proposed to solve the latter one. It is crucial for guaranteed services to maintain satisfactory performance through effective traffic control, which must be implemented in a feasible way and be able to work with RSVP. In this article, we present a flexible and effective traffic-control approach with a resource reservation scheme to accommodate delaysensitive services on the Internet. We demonstrate that our approach features proven bounded end-to-end queueing delay for delay-sensitive applications and good resilience for resource allocation. In addition, our packet transmission discipline achieves significant improvement in end-to-end delay control.