1 / 16

Buildings in software And Software in buildings

Buildings in software And Software in buildings . (A discussion about Physical simulation and Empirical modeling). Jason Trager. “ FeedForward ”: Tweet # SDBKickOff. Feedback : TinyURL.com / SDBkickoff. Why do we make Building energy models? . To estimate energy usage in a new building

iden
Download Presentation

Buildings in software And Software in buildings

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Buildings in softwareAndSoftware in buildings (A discussion about Physical simulation and Empirical modeling) Jason Trager “FeedForward”: Tweet #SDBKickOff Feedback : TinyURL.com/SDBkickoff

  2. Why do we make Building energy models? • To estimate energy usage in a new building • To evaluate efficacy of a retrofit • To explore a theoretical design • To match the building code • MPC – Reduced order model

  3. How good are these models?

  4. Retrofit using B.E. modeling • Model building • Simulate changes • Initiate changes • Calibrate model • Re-simulate • Change more building settings • Recalibrate

  5. What does a model look like? • Building Geometry Slide credit : Ronxgin Yin, DRRC

  6. Model Calibration

  7. Does it make sense to use sensors to create better building models? How is this different than information that could be gleaned from sensors alone?

  8. Empirical building adjustment • Analyze data from sources • Make intelligent choices about adjusting building settings • Measure results • Produce counterfactual from data • Compare actual to predicted • Make more adjustments

  9. Actual DR Event

  10. What does an empirical model look like?

  11. What does an empirical model look like?

  12. How good is empirical analysis? MAE: Mean Absolute Error RMSE: Root Mean Squared Error MAPE : Mean Absolute Percent Error RMSPE: Root Mean Squared Percent Error RelBias: Relative Bias

  13. empirical modeling and software control • Measure, predict responses of sensor streams • Search for faults • Search for mis-labeled streams • Institute rule based control? • Apply machine learning? • Apply Model Predictive Control?

  14. How do we use data richness to develop better quantative ways to control the building? How will this succeed over the need for simulating the building and adjusting it manually?

  15. Where does the pareto optimum occur with respect to sensor and data density in a building? When does additional data not yield more benefit?

  16. Baseline Measures Fault Detection Sensor Augmentation Automated Control Production Scale

More Related