automatic collection of building metadata
DESCRIPTION
Towards Automated Building Metadata Collection. Automatic collection of Building Metadata. Arka Bhattacharya, David Culler. Motivation. Architecture. Modeling Uncertainty. PROBLEM. TWO MAJOR TYPES OF UNCERTAINTY VALUE UNCERTAINTY - PowerPoint PPT PresentationTRANSCRIPT
Automatic collection of Building Metadata
Motivation
APPROACHAPPROACH
Modeling UncertaintyArchitecture
PROBLEMPROBLEM
• Each commercial building is unique and has 1000s of sensors in custom layouts.
• Currently Building metadata (HVAC, zone information, sensor locations, etc) information is fractured and do not exist in a standard representation.
• This prevents scalable deployment of building application services
• Automated collection of building metadata from various information sources into a common representation format
• Reduce uncertainty in representation with increase in ingested information.
TWO MAJOR TYPES OF UNCERTAINTY
•VALUE UNCERTAINTY• Uncertainty in attribute values due to imperfect
information• Modeled by
• distribution and distribution parameters; or• PDF .
•RELATIONSHIP UNCERTAINTY• Uncertainty in relationships between physical
objects (e.g VAV ‘X’ maybe fed by AirHandler ‘Y’ or AirHandler ‘Z’)
• Sets of relationships in a building should be captured by a m x n probability lattice, which shrinks in size as we have more certainty.
Perform some algebra when new information is available to update uncertainty
Towards Automated Building Metadata Collection
Arka Bhattacharya, David Culler
Automation : Example 1
INGESTION :
RENDERER :
Automation : Example 2
EMPERICALLY FIGURING OUT ORIENTATION OF ROOMS:
East / South InteriorWest/North
Simple Classifier Ideal Classifier
1. To separate North & West from all other rooms:• Use June evening temp. rise
2. To separate West from North:• Temp. gradient at 5am in June
3. To separate East & South from Interior:• August morning temp. rise
Classification accuracy : 86% for all rooms on 6th and 7th floors81% for all rooms on 5th, 6th and 7th floors
Uncertainty Reduction through feedback
A1(SDH.S4-01) A2(SDH.S4-02) ….. Prob.
Z1 Z2 Z21
p1
Z3 Z14 Z1 p2
…… p21!
Example 1:
• Return maximum likelihood actuator i for the VAV for the zone j.• If returned mapping is correct, then we have nailed down the mapping• If returned mapping is incorrect, then remove all the mappings of Ai -> Zj
, normalize the remaining probabilities• If Zone extent boundaries are perfect , then it will require O(n2)
actuations to get the mapping right.
Example 2:
Zone Prob.
Z1 p1
Z2 P2
… ….
Z21 p21
If zone boundary information is imperfect
Calculate most likely zone and most likely VAV for that zone.Given the user feedback, update the probabilty matrices using Bayes Rule.
Research Questions1. GbXML is weak in representing relationships. Explore other ways of representing building metadata.2. How to represent incompleteness of data in the representation 3. How useful are PL “learning-by-example” techninques , and where can they be applied ?