Title | ||
---|---|---|
Slash simulation analysis time with neural networks - Systematic experimentation, optimization, distributed simulation and parameter forecasting |
Abstract | ||
---|---|---|
Discrete event simulation has become an invaluable online decision tool in the fields of production and logistics. This requires fast results based on real and complex data. To satisfy these optimization and forecasting requirements several tools have been integrated. This improves simulation functionality and allows the evaluation and optimization of stochastic models including systematic experimentation. An Artificial Neural Network can be trained using the results of experiments. This enables the traditional working procedure to be reversed. Previously, simulation parameters had to be defined up-front. Now, the simulation and the Artificial Neural Network can identify the parameters necessary to reach a given goal. Also, the total duration of simulation runs can be reduced by distributing individual simulation runs on to different CPUs. The following article will give an overview of the state of the art toolset in Plant Simulation for complex experiment handling, statistical evaluation, genetic-algorithm-based optimization and forecasting of model properties using Artificial Neural Networks.. |
Year | Venue | Keywords |
---|---|---|
2008 | SimVis | discrete event simulation,stochastic model,complex data,neural network,genetic algorithm,satisfiability,artificial neural network |
Field | DocType | Citations |
Computer science,Stochastic neural network,Artificial intelligence,Artificial neural network,Network traffic simulation,Dynamic simulation,Machine learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peter-Michael Schmidt | 1 | 3 | 1.66 |
Matthias U. Heinicke | 2 | 9 | 1.78 |