Showing papers on "Network traffic simulation published in 1992"

A Best-Case Network Performance Model

Abstract: Network performance measures usually focus on average through-put. We, however, were concerned with best-case behavior: how fast could a packet traverse the network if there were no contention for resources. By subtracting the path time to a node from the path time through the node, we were able to develop a simple best-case delay model. This model was sensitive enough to determine the board-level connguration of a router 750 miles away.

Performance analysis of a method for high level prevention of traffic analysis

Abstract: One of the stated goals of communications security is the prevention of traffic analysis. A model to prevent traffic analysis by rerouting and padding the traffic matrix, so that the apparent final traffic matrix is neutral, is analyzed. The objective of this analysis is to justify the claims of the model and to show that rerouting of traffic via intermediate nodes with minimum padding is indeed a cost effective method to prevent traffic analysis. Simulation results supporting the above claim are also presented. The requirement that final traffic matrix be neutral may be too restrictive in some cases, and various modifications to the model are suggested, while still ensuring prevention of traffic analysis. Prevention of traffic analysis in real time is addressed briefly. >

In-vehicle information systems for network traffic control: a simulation framework to study alternative guidance strategies

Abstract: Efforts are underway around the world to use advanced telecommunication and information technologies for improving the traffic quality in congested urban areas through new approaches to effect better traffic patterns. However, these efforts to date have proceeded without much insight on several key elements with profound effect on the resulting system performance. This research develops a simulation framework to study certain aspects that influence the performance of traffic networks under information. A framework is developed that integrates the modelling of three key elements of traffic systems under information, namely, the traffic flow simulation, the path-processing aspects and the driver response to information. The simulation moves the vehicles using macroscopic traffic flow relations in discretized network segments, while tracking their positions. The boundedly rational behavioral model assumed for the driver response captures the driver decisions to stay on suboptimal but sufficing paths despite the provided route information. The framework is applied to candidate networks under information, to study the system performance under difference levels of usage of technology and different driver behavior parameters. Two different programs were developed: one for networks with parallel highways towards a single destination, and one for networks of general shapes and multiple destinations. The former model with faster path processing is also used for studying an idealized corridor for its stochastic-dynamic equilibration behavior under information using iterative simulations with available utility functions. The latter model is used for a realistic city network similar to the core network of Austin, Texas. The path processing component is developed carefully, and is flexible enough to model the driver behavior of selecting from a few paths under non-mandatory guidance. Efficient data structures are used to the efficient enumeration and updating the k-shortest paths. If these paths are not updated every simulation time step, the trip times of the existing k-paths are updated by efficient routines using two possible algorithms: one intended for sequential processors and another for a processor with vectorization capabilities. The results provide important insights on the effectiveness of in-vehicle information. Only a relatively small fraction (less than 30%) of the drivers may need to be equipped to obtain almost all of the advantages of guidance, and the system could get worse for higher percentages depending on the network context.

Architecture design for regulating and scheduling user's traffic in ATM networks

Abstract: The asynchronous transfer mode (ATM) technique provides a standardized and flexible scheme to transport and switch traffic effectively for different services. To provide satisfactory quality of service (QOS) to all users on the network, it is necessary to control the user's traffic so that network resources can be efficiently and fairly utilized by all the users while still meeting the individual QOS requirement. In this paper, we propose to control the user's traffic at two places in the network: at the user-network interface (UNI) by a traffic shaper or a traffic enforcer, and at the network-node interface (NNI) by a traffic regulator and a traffic scheduler. The traffic shaper/enforcer adopted in our work contains a buffer to delay and shape the violating cells that do not comply with some agreed-upon traffic parameters. The traffic regulator regulates cells at each network node to avoid long bursts being formed which may increase the network congestion probability. A traffic scheduler that follows the traffic regulator schedules the cells' departure sequences based on their delay priorites. We have proposed a general, feasible architecture to implement the traffic shaper, regulator, and scheduler, at various places in the network. A key component, the Sequencer chip, which contains 150k CMOS transistors, has been implemented to realize the architecture.

An assessment of state and lookup overhead in routers

Abstract: The current internet is based on a stateless (datagram) architecture. However, many recent proposals rely on the maintenance of state information within network routers, leading to the authors' interest in the implications of a stateful network layer. They collected internetwork traffic traces at the border routers of stub and transit networks, and used these data to evaluate, or predict, the effects of design alternatives for stateful architectures. They present an estimate of the number of active conversations at a router, and from this derive the storage requirements for the associated conversation state table. The analysis shows that, at the network periphery, fine-grain control over the traffic may be possible. However, deeper within the network, it may be more efficient to manage the conversations at a coarser level. The network traffic traces are used to perform trace driven simulations of an LRU cache, for different conversation granularities. Results show that locality exists for each of the conversation types investigated. >

Integration of neurocomputing and system simulation for modeling continuous improvement systems in manufacturing

Abstract: The use of a neural network embedded in a larger general-purpose simulation system (GPSS) simulation used to model continuous improvement systems (CIS) policies in a factory setting is described. The neural network is used to accelerate the identification of an effective CIS policy by providing a more realistic simulation framework. The interface between general simulation theory and neural network simulation is examined. Neural networks, when embedded in larger general-purpose simulations, are found to offer the potential for improving on the capabilities of those simulations, in particular manufacturing simulations for continuous improvement of production processes.

NETPLAN-a telecommunications network planning support system

Abstract: A software system, NETPLAN, for supporting telecommunications network planning has been developed. It is implemented using Prolog with a user-friendly graphical interface based on X Windows and Motif. The three basic activities of network planning (routing design, one-way and both-way junction circuit design, and signaling network design for circuit-switched networks) are fully supported. The dimensioning of the junction circuits is optimized by considering noncoincidental busy hour traffic characteristics of the various routes using the 24-hour traffic profile. The object-oriented approach adopted by NETPLAN eliminates the need for defining traffic and routing matrices as required by conventional approaches. The usefulness of the system is illustrated by its application to the planning of a network with ten switching nodes and twenty interconnected links. >

A flexible port traffic planning model

Abstract: This paper reports on a comprehensive simulation model developed to assist in future growth planning for the Port of Long Beach, California. The model simulates truck, auto, and rail traffic in a single model, using techniques developed to control complexity and run time, allowing the model to be implemented on a “386” class PC. Traditional traffic modeling practices (based on queuing models from traffic flow and capacity research reports) were integrated with discrete modeling techniques, resulting in a “hybrid” model that tracks individual vehicles, yet produces system wide performance measures consistent with generally accepted traffic flow modeling and reporting practices.

Advanced traffic management system: real-time network traffic simulation methodology with a massively parallel computing architecture

Abstract: The advent of parallel computing architectures presents an opportunity for transportation professionals to simulate a large-scale traffic network with sufficiently fast response time for real-time operation. However, it necessitates a fundamental change in the modeling algorithm to take full advantage of parallel computing. Such a methodology to simulate traffic network with the Connection Machine, a massively parallel computer, is described. The basic parallel computing architectures are introduced, along with a list of commercially available parallel computers. This is followed by an in-depth presentation of the proposed simulation methodology with a massively parallel computer. The proposed traffic simulation model has an inherent path-processing capability to represent drivers' route choice behavior at the individual-vehicle level. It has been implemented on the Connection Machine with 16,384 processors. Preliminary simulation experiments indicate that massively parallel computers are a practicable alternative for achieving real-time application. The experiment shows that the Connection Machine with 16k processors can simulate 32,000 vehicles for 30 min at 2-sec intervals within 2 min of running time.

A fuzzy controller of traffic systems and its neural network implementation

Abstract: In this paper, a neural network implemented fuzzy controller for single crossroad traffic signal control systems is presented, which is based on the summarization of the main characteristics of the traffic systems. The controller can cope with the fast changing of the arriving traffic flow and is suitable for all kinds of single crossroads and has a quite simple structure. The decision - making process is rapid as well as reasonable, with no need of any prediction of traffic flow. The simulation result is given, which verifies the effectiveness of this control method.

Performance simulation of congestion control mechanisms for intelligent networks

Abstract: Some congestion control aspects of intelligent networks (IN) are being investigated by simulation of simple network models. In particular the overload caused by mass-calling events driven by mass-media programs is studied under the activation of two control mechanisms. ACG (Automatic Call Gapping) prevents the IN service node from being overloaded by traffic directed towards it. FDOC (Focused Destination Overload Control) protects the public switched telephone network from calls all directed to specific subscriber codes. >

A unified framework for survivable telecommunications network design

Abstract: A unified framework for telecommunications switched traffic and transmission facility network design for survivability is presented. This design is considered for backbone nonhierarchical teletraffic networks with dynamic routing capabilities which use at most two traffic links for connecting a call. The facility network is considered to be sparse. The approach addresses the survivable design by considering both the traffic network and facility network explicitly in an integrated mathematical model/algorithm. >

Using traffic network models to assess site impact traffic.

Abstract: This paper covers experience gained in using traffic network models as a site traffic analysis tool, including problems encountered in developing an appropriate zone system and coded highway network that are compatible with turn movements; approaches to future forecasting (e.g., factoring between base and future movements; 'distributing' link approach volumes versus using explicitly calculated turn movements); and automating data transfer between the network model output and level of service (LOS) analysis software.

Progress in simulation

Abstract: A simulation approach to evaluate alternative designs of manufacturing systems using simulation generators for modelling flexible manufacturing systems digital control loading and motion for flight simulation simulation and AI in aviation training modelling qualitative issues in military simulations with the RANDABEL language cocktail party simulation modelling and simulation of LAN database systems using simulations to evaluate consistency protocols for replicated data discrete simulation in an extended actor context.

Sapporo, towards an intelligent integrated traffic management system

Abstract: The SAPPORO project deals with the research and development of a knowledge- based urban road traffic modeling and management system. It integrates within a unique object-oriented architecture various tools and modules for network design, geometric layout, network object editing, interactive rule- based signal plan construction, qualitative modeling and simulation of traffic, floating car simulation and an Actor-based contract net architecture for distributed traffic control.

Characterizing DS0-rate traffic using neural networks

Abstract: Current in-service nonintrusive measurement devices (INMDs) measure speech and noise levels, speech echo path loss, and speech echo path delay. Work on extending these measurements to include the automatic characterization of traffic on DS0-rate lines, i.e., 64 kbit/s PCM in the public switched network, is described. The ability to correctly identify speech and various types of data traffic could be used to gather more accurate statistics of local exchange traffic and could eventually serve to differentially route or tariff calls. In laboratory experiments, neural networks are used to distinguish speech from modem traffic, as well as differentiating between modems speeds. Classification is made on 14-ms segments of the signal with an overall accuracy of over 98%. The two-layered nonlinear neural networks performed better than both a linear-discrimination technique and a template-matching technique. >

A simulation study of traffic control procedures at highway work zones

Abstract: Construction zones often cause considerable inconveniences in highway traffic. They are often in the form of the closure of one or more lanes. Two major effects of these lane closures are traffic delays and safety hazards to drivers. The objective of this research is to study the traffic behavior at freeway work zones and come up with recommendations for the control procedures at such sites. This goal has been accomplished through completion of two tasks: 1) Development of a microscopic traffic simulation model to reflect the actual traffic flow patterns at and upstream from the construction site. 2) Validation of the model by means of data collection and comparison of the results with those of the model for a number of dtiferent traffic volumes. The data was used not only to test the microscopic traftlc behavior, but the macroscopic as well, and in both easesthe results were satisfactory. The model was then used as a means of experimentation to reach an optimum location for a control sign to result in the minimum traffic delay.

Measurements and characterization of traffic in a university environment

Abstract: In this paper we characterize the traffic seen in a university environment, especially on the broadband medium which serves as the backbone. The traffic is characterized based on parameters such as the volume of traffic generated, the packet inter-arrival times, the packet size and the protocol type and application that generated the traffic. We use the packet train model to analyze and characterize the traffic. Network traffic being inherently bursty, we propose a practical definition for burstiness and evaluate the burstiness of the traffic measured. Finally we compare the appropriateness and relative efficiency of some of the tools used to measure network traffic and compare their performance.

Design analysis of a satellite SCPC-DAMA VSAT network

Abstract: SCPC-DAMA VSAT networks (single channel per carrier-demand assignment multiple access very small aperture terminal) are usually adopted where many small remote stations are present, each with a low traffic intensity. This represents the typical scenario of a developing country, from which the alternative expression of 'rural satellite networks'. The authors started by building a simulation model of the communication system. The design of signalling management protocol (SMP), which is the strategy used by the remote station for signalling management and scheduling, is very important in order to improve the network performance. Three different SMPs are proposed and compared by means of simulation results. A second important aspect in the network design is to minimize the communication resources without modifying global performance. To this end they have defined a method which allows a suitable sizing of the modem number per station. An analysis of the network behaviour under standard and overload traffic conditions is presented and discussed. >

Simulation of multiple access protocols for real-time control

Abstract: The simulation activity described in this paper was undertaken for the design of a hierarchical multiple access communication network for a distributed real-time control system. The network consisted of multiple busses hierarchically connected by bridges. High bandwidth control loops were closed over local busses. Lower rate loops and status information were shared between busses.Multiple simulation methodologies were employed to design and valdate the communications protocol for the network. The methodologies included mathematical analysis, functional simulation, and physical simulation. Each method elucidated a separate aspect of the protocol's behavior. The unique contribution of each method yielded a comprehensive understanding of the proposed design and perrnitted model validation by cross-checking the results.The ortginal traffic load for this study included messages with maximurn acceptable delays between 0.001 and 1.0 seconds. The speed of the network was limited to less than 1.0 megabit per secon...

A mixed integer-linear programming model for dynamic traffic assignment

Abstract: In this report, a problem of dynamic traffic assignment, in which the authors seek to determine the time-dependent traffic volumes and link travel times that occur in a spatial traffic network with known topology and time-dependent origin-destination travel demands, is studied.

Evolution of an intelligent network

Abstract: An intelligent network structure, its original technology, and the advanced services it can provide are described. The issues of traffic control, customized processing, multi-connection control and virtual network service control points (NSPs) are addressed. >

Simulation of packet and cell-based communication networks

Abstract: This thesis investigates, using simulation techniques, the practical aspects of implementing a novel mobility protocol on the emerging Broadband Integrated Services Digital Network standard. The increasing expansion of telecommunications networks has meant that the demand for simulation has increased rapidly in recent years; but conventional simulators are slow and developments in the communications field are outstripping the ability of sequential uni-processor simulators. Newer techniques using distributed simulation on a multi-processor network are investigated in an attempt to make a cell-level simulation of a non-trivial B.-I.S.D.N. network feasible. The current state of development of the Asynchronous Transfer Mode standard, which will be used to implement a B.-I.S.D.N., is reviewed and simulation studies of the Orwell Slotted Ring protocol were made in an attempt to devise a simpler model for use in the main simulator. The mobility protocol, which uses a footprinting technique to simplify hand- offs by distributing information about a connexion to surrounding base stations, was implemented on the simulator and found to be functional after a few 'special case' scenarios had been catered for.

Performance and traffic characterization of a class of graphics-intensive X-applications

Abstract: The traffic generated by a class of graphics-intensive X Window System applications is characterized, and the effects the hardware processing platform has on the characteristics of the generated traffic are studied. The effect of running graphics-intensive applications on network performance is examined, and the network capabilities and limitations are determined. The experimental results show that the communications requirements of graphics-intensive applications are very high. Moreover, these requirements may depend on the processing power of the hardware platform that runs these applications. >

Realization of a Multimedia Traffic Generator Based on (μ,σ) Buffer Occupancy Analysis

Abstract: Carefully selected traffic generators enable accurate simulation of integrated broad-band networks. Simulation tools are crucial in analysis of traditional as well as new protocols and algorithms designed for optimum network management in the era of high-speed integrated ATM-based networks. In this paper, we survey proposed ATM traffic models and traffic generators derived from them for the purposes of representing voice, data, and video traffic. We then compare (μ, σ) buffer occupancy levels at a statistical multiplexer due to traffic generated from various traffic generators and show that the generator based on K-superposition of identical On/Off sources (K-ON-OFF model) possesses desirable characteristics as a general multimedia traffic model. The K-ON-OFF generator has been implemented and used to represent voice, data, or video sources as well as aggregated traffic behavior.

New traffic entropy functions to quantify spatial traffic flow conditions and intelligent control logic of isolated signals

Abstract: The authors propose new traffic functions to estimate space-mean-speed and traffic volume a few seconds ahead. They are based on the entropy parameter and traffic density which are obtained in the processing of a traffic flow image taken by a TV camera. The space-mean-speed and traffic volume estimated by the functions the authors proposed are very close to those of the actual traffic flows; the correlation coefficient between them showed more than 0.9. They have developed a control logic of isolated signals to change the signal timely, for which the information is given by the function they proposed. The effectiveness of the proposed logic has been examined by a theoretical approach and simulation analysis. The authors conclude that the proposed logic is more efficient than that of the time-gap-seeking as the traffic volume increases and the average cycle length approximates to the minimum. >

A switching architecture for congestion control in high-speed networks

Abstract: This paper proposes a new switching architecture to improve congestion control in high-speed networks. The architecture divides network into partitions. Every partition has a switch with a buffer that can absorb surges of bursty traffic within the network partition. The buffer size depends on the type of the network and the incoming traffic. The partition size depends on the network bandwidth, network traffic, packet size and buffer size. Examples of different networks are used to show the applications of the proposed architecture. >