Importance sampling for stochastic simulations
Management Science
Effective bandwidths for multiclass Markov fluids and other ATM sources
IEEE/ACM Transactions on Networking (TON)
The Markov-modulated Poisson process (MMPP) cookbook
Performance Evaluation
Fast simulation of the leaky bucket algorithm
WSC '94 Proceedings of the 26th conference on Winter simulation
Fast simulation of packet loss rates in communication networks with priorities
WSC '94 Proceedings of the 26th conference on Winter simulation
Effective bandwidth and fast simulation of ATM intree networks
Performance '93 Proceedings of the 16th IFIP Working Group 7.3 international symposium on Computer performance modeling measurement and evaluation
Likelilood ratio gradient estimation: an overview
WSC '87 Proceedings of the 19th conference on Winter simulation
Introduction to Simulation Using SIMAN
Introduction to Simulation Using SIMAN
| Hi-index | 0.00 |
In this paper, we introduce a set of SIMAN/ARENA language constructs. These constructs are intended to add correlated variate generation and importance sampling capabilities to the SIMAN/ARENA simulation environment. It is our purpose to demonstrate that such enhancements are feasible in virtually all simulation languages. These extensions are useful in the analysis of rare events and/or in systems driven by processes exhibiting some degree of correlation. Models arising in communications, manufacturing, physics, and biology may require this type of simulation capability. We describe how the constructs function, including activation, parameter specification, and behavior. In the case of the correlated variate construct, we describe the Markov modulation used to generate our correlations. For the importance sampling construct, we discuss the class of "exponentially twisted" changes-of-measure implemented within our construct, and provide some explanatory theoretical background.