ACM Transactions on Programming Languages and Systems (TOPLAS)
Efficient distributed event-driven simulations of multiple-loop networks
Communications of the ACM
The cost of conservative synchronization in parallel discrete event simulations
Journal of the ACM (JACM)
Control flow graphs as a representation language
WSC '94 Proceedings of the 26th conference on Winter simulation
Simulation for intra- and inter-organisational business process modelling
WSC '96 Proceedings of the 28th conference on Winter simulation
Verification and validation of simulation models
Proceedings of the 30th conference on Winter simulation
Business process modelling and analysis using discrete-event simulation
Proceedings of the 30th conference on Winter simulation
Asynchronous distributed simulation via a sequence of parallel computations
Communications of the ACM - Special issue on simulation modeling and statistical computing
Parallel and Distribution Simulation Systems
Parallel and Distribution Simulation Systems
Computer Simulation in Management Science
Computer Simulation in Management Science
Simulation Modeling and Analysis
Simulation Modeling and Analysis
SIMULATION OF PACKET COMMUNICATION ARCHITECTURE COMPUTER SYSTEMS
SIMULATION OF PACKET COMMUNICATION ARCHITECTURE COMPUTER SYSTEMS
Hi-index | 0.00 |
This paper describes the development of a parallel simulation model for analysis of a business process system. Today's increasing complexity of such systems, together with the need for more accurate results means that the task of simulation of business processes frequently outgrows the computational power of economically viable single process systems. One solution is to partition the computational task into sub-tasks and implement them on a parallel or distributed processing computers. This paper describes the process of modelling and execution of a simulation model in the context of a database development process and investigates the performance of the parallel execution of the model. The simulation computes the staff utilisation in various departments and the throughput of the system. The result of the parallel execution demonstrates that conservative parallel simulation algorithm using deadlock avoidance can provide significant speedup over a sequential simulation. Also the results of some experiments indicate that lookahead plays an important role in the performance of the simulation and, therefore, selecting the right lookahead generation technique can make a substantial difference.