Building control system with break even temperature uncertainty determination and performance analytics

1. A building control system comprising:

a communications interface configured to receive an energy use model for a building site, the energy use model having a break even temperature parameter representing a heating balance point or a cooling balance point, wherein the energy use model is used to predict an energy consumption of the building site in response to the break even temperature parameter and one or more predictor variables; and

a processing circuit configured to:

calculate a numerical uncertainty in the break even temperature parameter; and

use the uncertainty in the break even temperature parameter to analyze an energy performance of the building site.

2. The building control system of claim 1 , wherein the processing circuit is configured to:

receive inputs from one or more sensory devices of the building site;

apply the inputs to the energy use model to determine an output for one or more building control devices of the building site; and

use the output to operate the building control devices to affect a variable state or condition of the building site.

3. The building control system of claim 1 , wherein the processing circuit is configured to determine the uncertainty in the break even temperature parameter by:

simultaneously determining the uncertainty of the break even temperature parameter and an uncertainty of one or more additional parameters of the energy use model; and

using the simultaneously determined uncertainties to improve an accuracy of analyzing the energy performance.

4. The building control system of claim 1 , wherein the processing circuit is configured to determine the uncertainty in the break even temperature parameter by:

calculating a gradient of an output of the energy use model with respect to the break even temperature parameter;

determining a covariance matrix using the calculated gradient; and

using the covariance matrix to identify the uncertainty in the break even temperature parameter.

5. The building control system of claim 1 , wherein the processing circuit is configured to determine the uncertainty in the break even temperature parameter by:

obtaining a set of data points, each of the data points comprising a value for the one or more predictor variables of the energy use model and an associated energy consumption value for the building site;

generating multiple samples from the set of data points, each of the multiple samples including a plurality of data points selected from the set of data points;

for each of the multiple samples, estimating the break even temperature parameter using the plurality of data points included in the sample; and

determining the uncertainty in the break even temperature parameter using multiple estimates of the break even temperature parameter.

6. The building control system of claim 1 , wherein the processing circuit is configured to analyze the energy performance of the building site by performing a peer analysis of one or more energy use model parameters for a class of buildings including the building site, the peer analysis comprising:

calculating a difference between an energy use model parameter for the building site and a mean of the energy use model parameters for the class of buildings;

using the uncertainty in the break even temperature parameter to improve an accuracy of the calculation; and

detecting an outlier model parameter based on a result of the calculation.

7. The building control system of claim 1 , wherein the processing circuit is configured to analyze the energy performance of the building site by performing a temporal analysis of one or more energy use model parameters for the building site, the temporal analysis comprising:

calculating a difference between a value for an energy use model parameter at a particular time and a mean of a set of values for the energy use model parameter, the set of values including a plurality of values for the energy use model parameter at various times;

using the uncertainty in the break even temperature parameter to improve an accuracy of the calculation; and

detecting an outlier model parameter based on a result of the calculation.

8. The building control system of claim 1 , wherein the processing circuit is configured to analyze the energy performance of the building site by:

monitoring changes to one or more energy use model parameters for the building site;

detecting existence of a fault condition using a monitored change to the energy use model parameters; and

using the uncertainty in the break even temperature parameter to improve an accuracy of the detection.

9. The building control system of claim 1 , wherein the processing circuit is configured to analyze the energy performance of the building site by:

calculating an energy savings opportunity for the building site; and

using the uncertainty in the break even temperature parameter to improve an accuracy of the calculation.

10. The building control system of claim 1 , wherein the processing circuit is configured to:

update the uncertainty in the break even temperature parameter;

apply inputs to the energy use model;

conduct a performance analysis using the energy use model, wherein a result of the performance analysis is a function of the break even temperature parameter;

provide an output using the result of the performance analysis; and

determine an uncertainty of the output using the updated uncertainty of the uncertainty in the break even temperature parameter.

11. A method for analyzing an energy performance of a building site, the method comprising:

receiving an energy use model for the building site, the energy use model having a break even temperature parameter representing a heating balance point or a cooling balance point, wherein the energy use model is used to predict an energy consumption of the building site as a function of the break even temperature parameter and one or more predictor variables;

calculating a numerical uncertainty in the break even temperature parameter; and

using the uncertainty in the break even temperature parameter to analyze the energy performance of the building site.

12. The method of claim 11 , further comprising:

receiving inputs from one or more sensory devices of the building site;

applying the inputs to the energy use model to determine an output for one or more building control devices of the building site; and

using the output to operate the building control devices to affect a variable state or condition of the building site.

13. The method of claim 11 , wherein determining the uncertainty in the break even temperature parameter comprises:

simultaneously determining the uncertainty of the break even temperature parameter and an uncertainty of one or more additional parameters of the energy use model; and

using the simultaneously determined uncertainties to improve an accuracy of analyzing the energy performance.

14. The method of claim 11 , wherein determining the uncertainty in the break even temperature parameter comprises:

calculating a gradient of an output of the energy use model with respect to the break even temperature parameter;

determining a covariance matrix using the calculated gradient; and

using the covariance matrix to identify the uncertainty in the break even temperature parameter.

15. The method of claim 11 , wherein determining the uncertainty in the break even temperature parameter comprises:

obtaining a set of data points, each of the data points comprising a value for the one or more predictor variables of the energy use model and an associated energy consumption value for the building site;

generating multiple samples from the set of data points, each of the multiple samples including a plurality of data points selected from the set of data points;

for each of the multiple samples, estimating the break even temperature parameter using the plurality of data points included in the sample; and

determining the uncertainty in the break even temperature parameter using multiple estimates of the break even temperature parameter.

16. The method of claim 11 , wherein analyzing the energy performance of the building site comprises performing a peer analysis of one or more energy use model parameters for a class of buildings including the building site, the peer analysis comprising:

calculating a difference between an energy use model parameter for the building site and a mean of the energy use model parameters for the class of buildings;

using the uncertainty in the break even temperature parameter to improve an accuracy of the calculation; and

detecting an outlier model parameter based on a result of the calculation.

17. The method of claim 11 , wherein analyzing the energy performance of the building site comprises performing a temporal analysis of one or more energy use model parameters for the building site, the temporal analysis comprising:

calculating a difference between a value for an energy use model parameter at a particular time and a mean of a set of values for the energy use model parameter, the set of values including a plurality of values for the energy use model parameter at various times;

using the uncertainty in the break even temperature parameter to improve an accuracy of the calculation; and

detecting an outlier model parameter based on a result of the calculation.

18. The method of claim 11 , wherein analyzing the energy performance of the building site comprises:

monitoring changes to one or more energy use model parameters for the building site;

detecting existence of a fault condition using a monitored change to the energy use model parameters; and

using the uncertainty in the break even temperature parameter to improve an accuracy of the detection.

19. The method of claim 11 , wherein analyzing the energy performance of the building site comprises:

calculating an energy savings opportunity for the building site; and

using the uncertainty in the break even temperature parameter to improve an accuracy of the calculation.

20. The method of claim 11 , further comprising:

updating the uncertainty of the model parameters;

applying inputs to the energy use model;

conducting a performance analysis using the energy use model, wherein a result of the performance analysis is a function of one or more of the model parameters;

providing an output using the result of the performance analysis; and

determining an uncertainty of the output using the updated uncertainty of the model parameters.