The Experts below are selected from a list of 117 Experts worldwide ranked by ideXlab platform

B. Sengupta - One of the best experts on this subject based on the ideXlab platform.

  • Modeling and analysis of a single server queue with autocorrelated traffic
    Proceedings of INFOCOM'95, 1995
    Co-Authors: B. Melamed, B. Sengupta
    Abstract:

    In performance analysis of computer and communication systems, the designer is often faced with two challenges: modelling an input process accurately and then solving a resulting queueing problem. The authors present a modelling methodology called QTES (quantized transform-expand-sample) which can be used to model the Interarrival Distribution (histogram) accurately and to capture the effect of autocorrelations approximately. They then show that a difficult queueing problem (using a QTES input with autocorrelations) can be solved. The method is analytically tractable and numerically robust as shown by various examples.

  • INFOCOM - Modeling and analysis of a single server queue with autocorrelated traffic
    Proceedings of INFOCOM'95, 1995
    Co-Authors: B. Melamed, B. Sengupta
    Abstract:

    In performance analysis of computer and communication systems, the designer is often faced with two challenges: modelling an input process accurately and then solving a resulting queueing problem. The authors present a modelling methodology called QTES (quantized transform-expand-sample) which can be used to model the Interarrival Distribution (histogram) accurately and to capture the effect of autocorrelations approximately. They then show that a difficult queueing problem (using a QTES input with autocorrelations) can be solved. The method is analytically tractable and numerically robust as shown by various examples.

P. Banerjee - One of the best experts on this subject based on the ideXlab platform.

  • Performance measurement and trace driven simulation of parallel CAD and numeric applications on a hypercube multicomputer
    [1990] Proceedings. The 17th Annual International Symposium on Computer Architecture, 1990
    Co-Authors: P. Banerjee
    Abstract:

    The performance evaluation, workload characterization, and trace-driven simulation of a hypercube multicomputer running realistic workloads are presented. Six representative parallel applications were selected as benchmarks. Software monitoring techniques were then used to collect execution traces. On the basis of the measurement results, the authors investigated both the computation and communication behavior of these parallel programs, including CPU utilization, computation task granularity, message Interarrival Distribution, the Distribution of waiting times in receiving messages, and message length and destination Distributions. The localities in communication were also studied. A trace-driven simulation environment was developed to study the behavior of the communication hardware under real workloads. Simulation results on DMA and link utilizations are reported.

  • ISCA - Performance measurement and trace driven simulation of parallel CAD and numeric applications on a hypercube multicomputer
    Proceedings of the 17th annual international symposium on Computer Architecture - ISCA '90, 1990
    Co-Authors: P. Banerjee
    Abstract:

    This paper presents the performance evaluation, workload characterization and trace driven simulation of a hypercube multi-computer running realistic workloads. Six representative parallel applications were selected as benchmarks. Software monitoring techniques were then used to collect execution traces. Based on the measurement results, we investigated both the computation and communication behavior of these parallel programs, including CPU utilization, computation task granularity, message Interarrival Distribution, the Distribution of waiting times in receiving messages, and message length and destination Distributions. The localities in communication were also studied. A trace driven simulation environment was developed to study the behavior of the communication hardware under real workload. Simulation results on DMA and link utilizations are reported.

U. Narayanan - One of the best experts on this subject based on the ideXlab platform.

  • Approximate modeling of multiple priority congestion control in signalling system no. 7
    Fifth IEEE International Workshop on Computer-Aided Modeling Analysis and Design of Communication Links and Networks, 1994
    Co-Authors: B. Jabbari, A. Savas, U. Narayanan
    Abstract:

    This talk presents analytical and simulation models that attempt to capture the behavior of a structured common channel Signalling System Number 7 network during congestion conditions. In particular, the objective of these models is to study and evaluate the steady state performance of the congestion control protocol operation of Message Transfer Part - level 3 independent of interac tions in the backbone transport network. Therefore, our performance metric deals with messages in contrast to calls. Our analytical model incorporates multiple priority message sources at the signaling points and studies congestion at a single outgoing link of a signaling transfer point. Rea sonable simplifying assumptions are made in order to develop a Markov model to approximate the performance. Two simulation models are also presented to substantiate the assumptions and verify the analytical model. Through the Markov model and simulations we investigate the normalized throughput and blocking probabilities for each of the two priority messages, as well as other mea sures odel, e.g. offered load, buffer onset threshold ratio, ratio of traffic from different priority classes, and timers are varied. We also compare the multiple priority congestion control scheme with the no-priority case. In addition, by using the second set of simulations, we show that the basic timer of the congestion control mechanism, though a deterministic value in real implementa tion, may be approximated to obey an exponential Interarrival Distribution without causing major errors. These simulations also show that the mean Interarrival time between the expirations of this timer is a function of the offered load, and becomes essentially constant after a critical value of the offered load is exceeded. Since the behavior of this timer is critical to the imbedded Markov chain analysis, where the process is observed after each departure epoch, formulation of the imbedded Ma;rkov chain then becomes possible.

  • CAMAD - Approximate modeling of multiple priority congestion control in signalling system no. 7
    Fifth IEEE International Workshop on Computer-Aided Modeling Analysis and Design of Communication Links and Networks, 1994
    Co-Authors: B. Jabbari, A. Savas, U. Narayanan
    Abstract:

    This talk presents analytical and simulation models that attempt to capture the behavior of a structured common channel Signalling System Number 7 network during congestion conditions. In particular, the objective of these models is to study and evaluate the steady state performance of the congestion control protocol operation of Message Transfer Part - level 3 independent of interac tions in the backbone transport network. Therefore, our performance metric deals with messages in contrast to calls. Our analytical model incorporates multiple priority message sources at the signaling points and studies congestion at a single outgoing link of a signaling transfer point. Rea sonable simplifying assumptions are made in order to develop a Markov model to approximate the performance. Two simulation models are also presented to substantiate the assumptions and verify the analytical model. Through the Markov model and simulations we investigate the normalized throughput and blocking probabilities for each of the two priority messages, as well as other mea sures odel, e.g. offered load, buffer onset threshold ratio, ratio of traffic from different priority classes, and timers are varied. We also compare the multiple priority congestion control scheme with the no-priority case. In addition, by using the second set of simulations, we show that the basic timer of the congestion control mechanism, though a deterministic value in real implementa tion, may be approximated to obey an exponential Interarrival Distribution without causing major errors. These simulations also show that the mean Interarrival time between the expirations of this timer is a function of the offered load, and becomes essentially constant after a critical value of the offered load is exceeded. Since the behavior of this timer is critical to the imbedded Markov chain analysis, where the process is observed after each departure epoch, formulation of the imbedded Ma;rkov chain then becomes possible.

B. Melamed - One of the best experts on this subject based on the ideXlab platform.

  • Modeling and analysis of a single server queue with autocorrelated traffic
    Proceedings of INFOCOM'95, 1995
    Co-Authors: B. Melamed, B. Sengupta
    Abstract:

    In performance analysis of computer and communication systems, the designer is often faced with two challenges: modelling an input process accurately and then solving a resulting queueing problem. The authors present a modelling methodology called QTES (quantized transform-expand-sample) which can be used to model the Interarrival Distribution (histogram) accurately and to capture the effect of autocorrelations approximately. They then show that a difficult queueing problem (using a QTES input with autocorrelations) can be solved. The method is analytically tractable and numerically robust as shown by various examples.

  • INFOCOM - Modeling and analysis of a single server queue with autocorrelated traffic
    Proceedings of INFOCOM'95, 1995
    Co-Authors: B. Melamed, B. Sengupta
    Abstract:

    In performance analysis of computer and communication systems, the designer is often faced with two challenges: modelling an input process accurately and then solving a resulting queueing problem. The authors present a modelling methodology called QTES (quantized transform-expand-sample) which can be used to model the Interarrival Distribution (histogram) accurately and to capture the effect of autocorrelations approximately. They then show that a difficult queueing problem (using a QTES input with autocorrelations) can be solved. The method is analytically tractable and numerically robust as shown by various examples.

R.p. Malhame - One of the best experts on this subject based on the ideXlab platform.

  • Stochastic optimal control under Poisson-distributed observations
    IEEE Transactions on Automatic Control, 2000
    Co-Authors: M. Ades, P.e. Caines, R.p. Malhame
    Abstract:

    Optimal control problems for linear, stochastic continuous-time systems are considered, in which the time domain is decomposed into a finite set of N disjoint random intervals of the form [t/sub i/, t/sub i+1/), in which a complete state observation is taken at each instant t/sub i/, 0/spl les/i/spl les/N-1. Two optimal control problems termed, respectively, the (piecewise) time-invariant control and time-variant control are considered in this framework. Concerning the observation point process, we first consider the general situation in which the increment intervals are i.i.d.r.v.s with unspecified probabilistic Distributions. The (piecewise) time-invariant solution is thoroughly developed in this general case, and computations are illustrated using Erlang as the observations Interarrival Distribution. Next, the problem is specialized so increments are exponentially distributed, and the particular optimal control structure that results from this assumption is presented. Finally, and still under the Poisson assumption and for the time-variant case, we show that the control problem is closely related to linear quadratic Gaussian regulation with an exponentially discounted cost. The optimal control is made again of a sequence of piecewise open-loop controls corresponding, in this case, to linear feedback of the state predictor based on the most recent information on each interval. The feedback gains are time-varying matrices obtained from a sequence of algebraic Riccati equations, which are also computed off-line.