EBOSS- Evolutionary Building Operations Systems Solver

dc.contributor.advisorMeek, Christopher
dc.contributor.authorDavis, John Dylan
dc.date.accessioned2017-08-11T22:44:47Z
dc.date.available2017-08-11T22:44:47Z
dc.date.issued2017-08-11
dc.date.submitted2017-07
dc.descriptionThesis (Master's)--University of Washington, 2017-07
dc.description.abstractAn individual wakes up every morning and prepares themselves for the day by checking the daily forecast either through their phone or by the news. In response to either the hot or cold temperature, amount of precipitation, or wind speed, he or she will apply the correct number of layers in accordance with the day's weather conditions. This is done to achieve a maximum amount of comfort during the whole day and gives the person a sense of flexibility to the changes within a day. If a building could respond like a person, by checking the daily forecast and countering with passive and active systems as needed, then it would reduce the building's reliance on active systems that would require more energy use. How can Building Automation Systems utilize these predictive climate technologies to circumvent current oversights and environmental control errors? EBOSS, or Evolutionary Building Operations Systems Solver, is a grasshopper definition developed specifically to help an existing building foster more appropriate responses to changing weather conditions that create oversights and environmental control errors. EBOSS provides simple, interactive systems selection for the building that utilizes an Artificial Neural Network for a more intelligent Building Automation System. This methodology was devised after observing that there is a lack in the amount of depth and understanding of how and why systems are being used which limits each system within a building to stationary setpoints that are unable to adjust to changing weather. EBOSS will instead think of each system not as a single stationary element, but will control and maintain the building’s systems based off past, present, and future data.
dc.embargo.termsOpen Access
dc.format.mimetypeapplication/pdf
dc.identifier.otherDavis_washington_0250O_16976.pdf
dc.identifier.urihttp://hdl.handle.net/1773/39783
dc.language.isoen_US
dc.relation.haspartDavis_Artificial Neural Network_Grasshopper_Definition.gh; code/script; Grasshopper Script of EBOSS.
dc.rightsnone
dc.subjectArchitecture
dc.subjectArtificial Neural Network
dc.subjectBuilding Systems
dc.subjectDesign Computing
dc.subjectGrasshopper
dc.subjectPredictive Control
dc.subjectArchitecture
dc.subject.otherArchitecture
dc.titleEBOSS- Evolutionary Building Operations Systems Solver
dc.typeThesis

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Davis_washington_0250O_16976.pdf
Size:
7.88 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
Davis_Artificial Neural Network_Grasshopper_Definition.gh
Size:
428.78 KB
Format:
Unknown data format

Collections