Generation of occupant activities based on recorded occupant behavior

Patent metadata

Field	Value
Publication number	US-10586181-B2
Application number	US-201213440952-A
Country	US
Kind code	B2
Filing date	Apr 5, 2012
Priority date	Apr 12, 2011
Publication date	Mar 10, 2020
Grant date	Mar 10, 2020

Abstract

A method and apparatus for simulating occupant behavior in buildings may be used to predict the energy use of a building structure. The activities of actual building occupants are recorded and provided as an input to the occupant behavior simulation. The occupant behavior simulation generates simulated occupant schedules with similar behavioral patterns. An arbitrary set of factors can be used to select plausible activity types, durations, and numbers of participants during an occupant behavior simulation. The simulated occupant schedules may then be incorporated into a building performance simulation to help architects predict the energy demand associated with different building design options.

First claim

The invention claimed is:

1. A computer-implemented method for simulating occupant behavior for a target building structure, the method comprising:
receiving, via a simulation engine, recorded occupant behavior data associated with a representative building structure;
constructing a histogram of at least two dimensions that is populated with the recorded occupant behavior data;
smoothing the recorded occupant behavior data to fully populate the histogram, wherein the smoothing comprises:
determining a smoothing parameter value for each of one or more factors that influences the one or more attributes, and
computing a smoothing coefficient for each of the plurality of bins based on the smoothing parameter values and a number of neighboring bins;

computing normalized arrays of occupant behavior feature values based on the histogram;
generating one or more attributes of occupant behavior for a simulated occupant of the target building structure based on the normalized arrays of occupant behavior feature values; and
generating a simulation of occupant behavior based on the generated one or more attributes of occupant behavior, wherein the simulation indicates a predicted energy demand of the target building structure.

2. The method of claim 1 , wherein the one or more attributes include a task performed by the simulated occupant of the target building structure.

3. The method of claim 1 , wherein the one or more attributes include a time duration during which a task is performed by the simulated occupant of the target building structure.

4. The method of claim 1 , wherein the one or more attributes include a number of participants associated with a simulated task performed by the simulated occupant of the target building structure.

5. The method of claim 1 , wherein generating one or more attributes comprises:
computing a probability table based on the normalized arrays of occupant behavior feature values;
computing one or more gamma distribution parameters based on the normalized arrays of occupant behavior feature values; and
generating a first occupant behavior attribute for a sub interval based on the probability table or the gamma distribution parameters.

6. The method of claim 1 , wherein a number of dimensions of the histogram equals a number of factors that influence the one or more attributes.

7. The method of claim 6 , wherein the factors comprise at least one of time of day, the previous task performed by an actual occupant, time elapsed since a task was performed by the actual occupant, and a number of occupants participating in a task.

8. The method of claim 1 , wherein computing the normalized arrays further comprises:
calculating a probability value of the occupant performing another task based, at least in part, on performing a previous task that is performed before the another task, wherein the another task, a next task, and the previous task each comprise different tasks and the probability value is calculated based, at least in part, on the recorded occupant behavior data.

9. The method of claim 1 , wherein computing the normalized arrays further comprises:
calculating a probability value of the occupant performing a next task based, at least in part, on performing a previous task that is performed before the next task, wherein the next task and the previous task comprise different tasks and the probability value is calculated based, at least in part, on the recorded occupant behavior data.

10. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause a computer system to perform an operation for simulating occupant behavior for a target building structure, the operation comprising:
receiving recorded occupant behavior data associated with a representative building structure;
constructing a histogram of at least two dimensions that is populated with the recorded occupant behavior data;
smoothing the recorded occupant behavior data to fully populate the histogram, wherein the smoothing comprises:
determining a smoothing parameter value for each of one or more factors that influences the one or more attributes, and
computing a smoothing coefficient for each of the plurality of bins based on the smoothing parameter values and a number of neighboring bins;

computing normalized arrays of occupant behavior feature values based on the histogram;
generating one or more attributes of occupant behavior for a simulated occupant of the target building structure based on the normalized arrays of occupant behavior feature values; and
generating a simulation of occupant behavior based on the generated one or more attributes of occupant behavior, wherein the simulation indicates a predicted energy demand of the target building structure.

11. The non-transitory computer-readable storage medium of claim 10 , wherein the one or more attributes include a task performed by the simulated occupant of the target building structure.

12. The non-transitory computer-readable storage medium of claim 10 , wherein the one or more attributes include a time duration during which a task is performed by the simulated occupant of the target building structure.

13. The non-transitory computer-readable storage medium of claim 10 , wherein the one or more attributes include a number of participants associated with a simulated task performed by the simulated occupant of the target building structure.

14. The non-transitory computer-readable storage medium of claim 10 , wherein generating one or more attributes comprises:
computing a probability table based on the normalized arrays of occupant behavior feature values;
computing one or more gamma distribution parameters based on the normalized arrays of occupant behavior feature values; and
generating a first occupant behavior attribute for a sub interval based on the probability table or the gamma distribution parameters.

15. The non-transitory computer-readable storage medium of claim 10 , wherein a number of dimensions of the histogram equals a number of factors that influence the one or more attributes.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the factors comprise at least one of time of day, the previous task performed by an actual occupant, time elapsed since a task was performed by the actual occupant, and a number of occupants participating in a task.

17. A computing system configured to simulate occupant behavior for a target building structure, comprising:
a memory configured to store an application program and recorded occupant behavior data associated with a representative building structure associated with the application program; and
a processor that is configured to:
receive the recorded occupant behavior data associated with the representative building structure,
construct a histogram of at least two dimensions that is populated with the recorded occupant behavior data,
smoothing the recorded occupant behavior data to fully populate the histogram, wherein the smoothing comprises:
determining a smoothing parameter value for each of one or more factors that influences the one or more attributes; and
computing a smoothing coefficient for each of the plurality of bins based on the smoothing parameter values and a number of neighboring bins,

compute normalized arrays of occupant behavior feature values based on the histogram;
generate one or more attributes of occupant behavior for a simulated occupant of the target building structure based on the normalized arrays of occupant behavior feature values,
store

Assignees

• Goldstein Rhys
• Khan Azam
• Tessier Alexander
• Autodesk Inc

Inventors

• Goldstein Rhys
• Khan Azam
• Tessier Alexander

Classifications

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G06Q50/16

  Real estate · CPC title

• G06F30/13

  Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads · CPC title

• G06Q50/06

  Energy or water supply · CPC title

• G06Q10/04 Primary

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title