Citation
Armin Wasicek, Edward A. Lee, Hokeun Kim, Lev Greenberg, Akihito Iwai, Ilge Akkaya. "System simulation from operational data". Proceedings of the Design Automation Conference (DAC), June, 2015.

Abstract
System simulation is a valuable tool to unveil inefficiencies and to test new strategies when implementing and revising systems. Often, simulations are parameterized using offline data and heuristic knowledge. Operational data, i.e., data gained through experimentation and observation, can greatly improve the fidelity between the actual system and the simulation. In a traffic scenario, for example, different road conditions or vehicle types can impact the outcome of the simulation and have to be considered during the modeling stage. This paper proposes using machine learning techniques to generate high fidelity simulation models. A traffic simulation case study exemplifies this approach by generating a model for the SUMO traffic simulator from vehicular telemetry data.

Electronic downloads

• WasicekEtAl_Data_DAC_15.pdf · application/x-octet-stream · 344 kbytes

• HTML

  Armin Wasicek, Edward A. Lee, Hokeun Kim, Lev Greenberg,
  Akihito Iwai, Ilge Akkaya. <a
  href="http://chess.eecs.berkeley.edu/pubs/1097.html"
  >System simulation from operational data</a>,
  Proceedings of the Design Automation Conference (DAC), June,
  2015.

• Plain text

  Armin Wasicek, Edward A. Lee, Hokeun Kim, Lev Greenberg,
  Akihito Iwai, Ilge Akkaya. "System simulation from
  operational data". Proceedings of the Design Automation
  Conference (DAC), June, 2015.

• BibTeX

  @inproceedings{WasicekLeeKimGreenbergIwaiAkkaya15_SystemSimulationFromOperationalData,
      author = {Armin Wasicek and Edward A. Lee and Hokeun Kim and
                Lev Greenberg and Akihito Iwai and Ilge Akkaya},
      title = {System simulation from operational data},
      booktitle = {Proceedings of the Design Automation Conference
                (DAC)},
      month = {June},
      year = {2015},
      abstract = {System simulation is a valuable tool to unveil
                inefficiencies and to test new strategies when
                implementing and revising systems. Often,
                simulations are parameterized using offline data
                and heuristic knowledge. Operational data, i.e.,
                data gained through experimentation and
                observation, can greatly improve the fidelity
                between the actual system and the simulation. In a
                traffic scenario, for example, different road
                conditions or vehicle types can impact the outcome
                of the simulation and have to be considered during
                the modeling stage. This paper proposes using
                machine learning techniques to generate high
                fidelity simulation models. A traffic simulation
                case study exemplifies this approach by generating
                a model for the SUMO traffic simulator from
                vehicular telemetry data.},
      URL = {http://chess.eecs.berkeley.edu/pubs/1097.html}
  }
  

Posted by Mary Stewart on 6 Apr 2015.
For additional information, see the Publications FAQ or contact webmaster at chess eecs berkeley edu.