Direct methods for sparse matrices
Direct methods for sparse matrices
Multilevel hypergraph partitioning: application in VLSI domain
DAC '97 Proceedings of the 34th annual Design Automation Conference
Large power grid analysis using domain decomposition
Proceedings of the conference on Design, automation and test in Europe: Proceedings
Validity of the single processor approach to achieving large scale computing capabilities
AFIPS '67 (Spring) Proceedings of the April 18-20, 1967, spring joint computer conference
More Effective C#: 50 Specific Ways to Improve Your C# (Effective Software Development Series)
More Effective C#: 50 Specific Ways to Improve Your C# (Effective Software Development Series)
Electronic Circuit & System Simulation Methods (SRE)
Electronic Circuit & System Simulation Methods (SRE)
Using Attached Processors to Achieve High-Speed Real-Time Simulation
SIMUL '10 Proceedings of the 2010 Second International Conference on Advances in System Simulation
Benchmarking different direct solution methods for large power system simulation
Proceedings of the 2010 Conference on Grand Challenges in Modeling & Simulation
GCMS '09 Proceedings of the 2009 Grand Challenges in Modeling & Simulation Conference
Hi-index | 0.00 |
This paper presents an approach to accelerate the simulation of shipboard power systems. A common issue in the ship research community is the simulation run time of large-scale shipboard power systems. A contributor to lengthy run times is that PC-based power system simulators do not exploit multicore technology, which stems from the fact that software trails advances in hardware. The Center for Electromechanics at the University of Texas at Austin (UT-CEM) is developing a multicore power system solver (CEMSolver) to simulate shipboard power system models in significantly less time. The simulation run time is reduced by first partitioning power system models and then creating simulations at the subsystem level. This accelerates the simulation of shipboard power systems. A general overview of CEMSolver and a comparison of its run times against those of SimPowerSystems are presented. The results demonstrate that CEMSolver can speed up the simulation of shipboard power system models built with SimPowerSystems up to 80 times, and that, despite common belief, multicore desktop computers are capable of executing complex simulation scenarios.