BALANCE POINT DETERMINATION

• US 20110276527A1
• Filed: 07/18/2011
• Published: 11/10/2011
• Est. Priority Date: 12/15/2010
• Status: Active Grant

• Current Assignee: SCIenergy, Inc.
• Original Assignee: Scientific Conservation, Inc.
• Inventors: Pitcher, John, Hortman, Matthew
• Granted Patent: US 8,370,283 B2
• Time in Patent Office: Days
• US Class Current: 706/21
• CPC Class Codes: G06F 13/24 using interrupt G06F13/32 takes precedence
• CPC Class Codes: G06F 2111/08 Probabilistic or stochastic CAD
• CPC Class Codes: G06F 2113/14 Pipes
• CPC Class Codes: G06F 2119/08 Thermal analysis or thermal optimisation
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30

Abstract

Systems and methods for predicting energy usage of an asset are provided. Among several implementations of methods implemented by a computer, one embodiment of a computer-implemented method includes selecting one of a plurality of base temperatures that allows a linear equation to estimate energy consumption by an asset as a function of an average daily demand on the asset to attain a desired temperature. The computer-implemented method also includes inserting the selected base temperature in a non-linear equation for modeling the asset'"'"'s energy consumption.

Claims

1. A computer-implemented method comprising:

selecting one of a plurality of base temperatures that allows a linear equation to estimate energy consumption by an asset as a function of an average daily demand on the asset to attain a desired temperature; and

inserting the selected base temperature in a non-linear equation for modeling the asset'"'"'s energy consumption.

2. The computer-implemented method of claim 1, further comprising:

receiving a plurality of weather measurements indicating weather conditions of a region in which the asset is located, wherein the plurality of weather measurements are obtained during a baseline time period; and

receiving a plurality of energy consumption measurements indicating amounts of energy consumed by the asset, wherein the energy consumption measurements are obtained during the baseline time period;

wherein the average daily demand is calculated for each of a plurality of billing periods in the baseline time period; and

wherein the plurality of base temperatures represent outdoor temperatures at which the asset is not needed to attain the desired temperature.

3. The computer-implemented method of claim 1, wherein each of the plurality of base temperatures includes a heating base temperature and a cooling base temperature, wherein the heating base temperature represents an outdoor temperature at or above which heating by the asset is not needed to attain a first desired indoor temperature, and wherein the cooling base temperature represents an outdoor temperature at or below which cooling by the asset is not needed to attain a second desired indoor temperature;

and

wherein, for each pair of values of the heating base temperature and cooling base temperature, the computer-implemented method further comprises;

calculating an average daily heating demand and an average daily cooling demand for each of the plurality of billing periods in the baseline time period; and

creating the linear equations representing the estimations of energy consumption as a function of the average daily heating demand and average daily cooling demand for each respective billing period.

4. The computer-implemented method of claim 1, further comprising training an artificial neural network (ANN) by providing the ANN with an input related to the average daily demand using the selected base temperature and an output related to an average daily amount of energy consumption.

5. The computer-implemented method of claim 1, further comprising:

receiving a plurality of weather measurements indicating weather conditions of a region in which the asset is located, wherein the plurality of weather measurements are obtained during a baseline time period;

receiving a plurality of energy consumption measurements indicating amounts of energy consumed by the asset, wherein the energy consumption measurements are obtained during the baseline time period;

calculating the average daily demand to attain a predetermined range of temperatures, wherein the average daily demand represents an energy demand on the asset, wherein the average daily demand is calculated for each of a plurality of billing periods in the baseline time period, and wherein the desired temperature is within the predetermined range of temperatures;

utilizing a plurality of linear equations representing estimations of energy consumption as a function of the average daily demand for each respective billing period, wherein each linear equation corresponds to a respective one of the plurality of base temperatures, the base temperatures representing outdoor temperatures at which the asset is not needed to attain the predetermined range of temperatures; and

evaluating each of the linear equations based in part on how well the linear equation estimates actual energy consumption,

wherein the linear equation to estimate energy consumption by the asset is one of the plurality of linear equations, and

wherein the selected base temperature corresponds to the linear equation that best estimates the actual energy consumption.

6. The computer-implemented method of claim 5, wherein the base temperatures include heating base temperatures and cooling base temperatures, each heating base temperature representing an outdoor temperature at or above which heating by an HVAC system of the asset is not needed to attain a first desired indoor temperature, and each cooling base temperature representing an outdoor temperature at or below which cooling by the HVAC system is not needed to attain a second desired indoor temperature, and wherein, for each pair of values of the heating base temperature and cooling base temperature, the method further comprises:

calculating an average daily heating demand and an average daily cooling demand for each of the plurality of billing periods in the baseline time period; and

creating the linear equations representing the estimations of energy consumption as a function of the average daily heating demand and average daily cooling demand for each respective billing period.

7. The computer-implemented method of claim 5, further comprising:

training an artificial neural network (ANN) by providing the ANN with one or more inputs and an output for each billing period, each input related to the average daily demand using the selected base temperature for a respective billing period, and each output related to an average daily amount of energy consumption;

wherein the ANN comprises at least one non-linear function.

8. The computer-implemented method of claim 7, further comprising:

predicting energy consumption of the asset based on outdoor temperatures during a prediction period following the baseline time period;

calculating an offset between the predicted energy consumption and actual energy consumption for a billing period of the prediction period; and

communicating with a manager of the asset when the offset between the predicted energy consumption and the actual energy consumption exceeds a predetermined threshold.

9. The computer-implemented method of claim 5, wherein the baseline time period is approximately one year and each billing period is approximately one month;

wherein receiving the plurality of weather measurements further comprises receiving the weather measurements from a weather service about once every hour during the baseline time period;

wherein receiving energy consumption measurements further comprises receiving energy consumption data from an energy bill provided by an energy company; and

wherein the asset is a building.

10. The computer-implemented method of claim 5, wherein creating the plurality of linear equations uses the following formula:

KWHLIN_k(H_i,C_i)=A1_k+(A2_k*H_i)+(A3_k*C_i)

and uses a least-squares analysis to determine A1, A2, and A3, where A1 is a coefficient representing a factor of energy usage that is not associated with heating and cooling, A2 is a coefficient representing a factor of energy usage associated with the heating demand, and A3 is a coefficient representing a factor of energy usage associated with the cooling demand;

wherein A2 is also a factor of a volume of space to be heated and the efficiency of the heating system, and wherein A3 is a factor of the volume of space to be cooled and the efficiency of the cooling system.

11. The computer-implemented method of claim 5, wherein evaluating the linear equation involves calculating a coefficient of determination R² using the following equation:

12. A system comprising:

a processing device configured to control the operations of the system;

an interface device configured to receive a plurality of outdoor temperature measurements of a region in which an asset is located and a plurality of energy consumption measurements of the asset, wherein the plurality of outdoor temperature measurements and energy consumption measurements are taken during a baseline time period;

an energy use prediction program in communication with the processing device, the energy use prediction program configured to enable the processing device to process a pair of values of a heating base temperature and a cooling base temperature, the energy use prediction program comprising an average daily heating demand calculating module, an average daily cooling demand calculating module, a linear equation fitting module, and a linear equation evaluation module.

13. The system of claim 12, wherein the energy use prediction program is further configured to enable the processing device to process each pair of values of a heating base temperature and a cooling base temperature from a plurality of values of heating base temperatures and cooling base temperatures.

14. The system of claim 13, wherein, for each pair of values, the energy use prediction program is configured to enable the processing device to:

calculate an average daily heating demand using the average daily heating demand calculating module and an average daily cooling demand using the average daily cooling demand calculating module for each of a plurality of billing periods in the baseline time period;

create a linear equation using the linear equation fitting module, the linear equation representing an estimation of energy consumption as a function of the average daily heating demand and average daily cooling demand for each respective billing period;

evaluate the linear equation using the linear equation evaluation module based in part on how well the linear equation estimates actual energy consumption; and

select the pair of values of the heating base temperature and cooling base temperature corresponding to the linear equation that provides a desirable evaluation for estimating actual energy consumption.

15. The system of claim 14, wherein the energy use prediction program further comprises an artificial neural network (ANN) interface module configured to train an ANN by providing the ANN with first and second inputs and an output for each billing period, each first input related to the average daily heating demand using the selected heating base temperature for a respective billing period, each second input related to the average daily cooling demand using the selected cooling base temperature for the respective billing period, and each output related to an average daily amount of energy consumption;

wherein the energy use prediction program is further configured to predict energy consumption of an HVAC system based on outdoor temperatures during a prediction period following the baseline time period, and wherein the asset is a building and the HVAC system is incorporated in the building; and

wherein the energy use prediction program further comprises a graph creating module configured to create a graph showing predicted energy consumption and actual energy consumption to allow an observation of an offset between the predicted energy consumption and actual energy consumption for one or more billing periods of the prediction period.

16. The system of claim 12, wherein:

the average daily heating demand calculating module and the average daily cooling demand calculating module use the following equations;

17. A computer-readable medium configured to store instructions for predicting energy consumption, the instructions comprising:

logic adapted to receive a plurality of weather measurements of outdoor weather conditions of a region in which an asset is located, wherein the plurality of weather measurements are taken during a baseline time period, and to receive energy consumption measurements of energy consumed by the asset, wherein the energy consumption measurements are taken during the baseline time period;

logic adapted to calculate, for a first pair of values of a heating base temperature and a cooling base temperature, an average daily heating demand and an average daily cooling demand for each of a plurality of billing periods in the baseline time period;

logic adapted to create, for the first pair of values, a linear equation representing an estimation of energy consumption as a function of the average daily heating demand and average daily cooling demand for each respective billing period;

logic adapted to evaluate, for the first pair of values, the linear equation based in part on how well the linear equation estimates actual energy consumption.

18. The computer-readable medium of claim 17, further comprising:

logic adapted to process each pair of values of a heating base temperature and a cooling base temperature from a plurality of values of heating base temperatures and cooling base temperatures, wherein the logic adapted to calculate the average daily heating demand and average daily cooling demand is further adapted to calculate average daily heating demand and average daily cooling demand for each pair of values, wherein the logic adapted to create the linear equation is further adapted to create a linear equation for each pair of values, and wherein the logic adapted to evaluate the linear equation is further adapted to evaluate the linear equation for each pair of values; and

logic adapted to select the pair of values of the heating base temperature and cooling base temperature corresponding to the linear equation that optimally estimates actual energy consumption;

wherein the instructions further comprise logic adapted to train an artificial neural network (ANN) by providing the ANN with first and second inputs and an output for each billing period, each first input related to the average daily heating demand using the selected heating base temperature for a respective billing period, each second input related to the average daily cooling demand using the selected cooling base temperature for the respective billing period, and each output related to an average daily amount of energy consumption.

19. The computer-readable medium of claim 17, wherein the instructions further comprise:

logic adapted to predict energy consumption of an HVAC system based on outdoor temperatures during a prediction period following the baseline time period, wherein the asset is a building and the HVAC system is incorporated in the building; and

logic adapted to calculate an offset between the predicted energy consumption and actual energy consumption for one or more billing periods of the prediction period.

20. The computer-readable medium of claim 17, wherein the baseline time period is approximately one year and each billing period is approximately one month, and wherein the logic adapted to receive the plurality of weather measurements further comprises receiving the weather measurements from a weather service about once every hour during the baseline time period;

and

wherein the heating base temperature represents an outdoor temperature at or above which heating by an HVAC system of the asset is not needed to attain a first desired indoor temperature, and wherein the cooling base temperature represents an outdoor temperature at or below which cooling by the HVAC system is not needed to attain a second desired indoor temperature.