Apparatus and method for demand response dispatch employing weather induced facility consumption characterizations

• US 10,409,310 B2
• Filed: 09/10/2018
• Issued: 09/10/2019
• Est. Priority Date: 03/31/2015
• Status: Active Grant

• Current Assignee: Enel X North America, Inc. (ENEL SPA)
• Original Assignee: Enel X North America, Inc. (ENEL SPA)
• Inventors: Al-Mohssen, Husain, Bassa, Angela S., Paradis, Richard R.
• Primary Examiner(s): Diallo, Mamadou L
• Application Number:
  US16/126,161
• Publication Number:
  US 20190018438A1
• Time in Patent Office: 365 Days
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 19/048 Monitoring; Safety
• CPC Class Codes: G05B 2219/2639 Energy management, use maximum of cheap power, keep peak load low
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G05F 1/66 Regulating electric power

Abstract

A method for dispatching buildings, including: generating data sets, each having energy values along with corresponding time and outside temperature values, where the energy values are shifted by one of a plurality of lag values relative to the corresponding time and outside temperature values; performing a machine learning model analysis on the each of the data sets; determining a least valued residual that indicates a corresponding energy lag for each of the buildings, the corresponding energy lag describes a transient energy consumption period preceding a change in outside temperature; using outside temperatures, model parameters, and energy lags for all of the buildings to estimate a cumulative energy consumption for the buildings, and to predict a dispatch order reception time for the demand response program event; and employing the dispatch order reception time to prepare actions required to control the each of the buildings to optimally shed energy specified in a dispatch order.

Claims

1. A demand response dispatch prediction system, comprising:

baseline data stores, configured to store a plurality of baseline energy use data sets for buildings participating in a demand response program;

a building lag optimizer, configured to receive identifiers for said buildings, and configured to retrieve said plurality of baseline energy use data sets from said baseline data stores for said buildings, and configured to generate energy use data sets for each of said buildings, each of said energy use data sets comprising energy consumption values along with corresponding time and outside temperature values, wherein said energy consumption values within said each of said energy use data sets are shifted by one of a plurality of lag values relative to said corresponding time and outside temperature values, and wherein each of said plurality of lag values is different from other ones of said plurality of lag values, and configured to perform a machine learning model analysis on said each of said energy use data sets to yield corresponding machine learning model parameters and a corresponding residual, and configured to determine a least valued residual from all residuals yielded, said least valued residual indicating a corresponding energy lag for said each of said buildings, and machine learning model parameters that correspond to said least valued residual, and wherein said corresponding energy lag describes a transient energy consumption period preceding a change in outside temperature;

a dispatch prediction element, coupled to said building lag optimizer and to weather stores, configured to receive, for each of said buildings, outside temperatures, said corresponding energy lag, and said corresponding machine learning model parameters, and configured to estimate a cumulative energy consumption for said buildings, and configured to predict a dispatch order reception time for a demand response program event; and

a dispatch control element, coupled to said dispatch prediction element, configured to receive said dispatch order reception time, and configured to prepare actions required to control said each of said buildings to optimally shed energy specified in a corresponding dispatch order.

2. The system as recited in claim 1, wherein said plurality of lag values indicates shifts of said energy consumption values to different time and outside temperature values.

3. The system as recited in claim 1, wherein said corresponding time values are less than or equal to said corresponding energy lag for said each of said buildings.

4. The system as recited in claim 1, wherein said corresponding time values comprise hourly values and said plurality of lag values spans a 24-hour period.

5. The system as recited in claim 1, wherein said dispatch order reception time is predicted as a function of demand response contract data and a specified threshold known to trigger said demand response program event.

6. The system as recited in claim 1, wherein said cumulative energy consumption for said buildings comprises a future energy consumption timeline as a function of said outside temperatures.

7. The system as recited in claim 1, wherein said each of said energy use data sets comprises a first portion of a corresponding each of a plurality of baseline energy use data sets, and wherein required energy consumption values resulting from shifts are taken from a second portion of said corresponding each of a plurality of baseline energy use data sets.

8. A system for predicting a dispatch for buildings participating in a demand response program event, the system comprising:

baseline data stores, configured to store a plurality of baseline energy use data sets for the buildings;

a building lag optimizer, configured to determine an energy lag for one of the buildings, said building lag optimizer comprising;

a thermal response processor, configured to generate a plurality of energy use data sets for said one of the buildings, each of said plurality of energy use data sets comprising energy consumption values along with corresponding time and outside temperature values, wherein said energy consumption values within said each of said plurality of energy use data sets are shifted by one of a plurality of lag values relative to said corresponding time and outside temperature values, and wherein each of said plurality of lag values is different from other ones of said plurality of lag values; and

a machine learning model engine, coupled to said thermal response processor, configured to receive said plurality of energy use data sets, and configured to perform a machine learning model analysis on said each of said plurality of energy use data sets to yield corresponding machine learning model parameters and a corresponding residual;

wherein said thermal response processor determines a least valued residual from all residuals yielded by said machine learning model engine, said least valued residual indicating said energy lag for said building, wherein said energy lag describes a transient energy consumption period preceding a change in outside temperature;

a dispatch prediction element, coupled to said building lag optimizer and to weather stores, configured to receive, for each of the buildings, outside temperatures, said corresponding energy lag, and said corresponding machine learning model parameters, and configured to estimate a cumulative energy consumption for the buildings, and configured to predict a dispatch order reception time for the demand response program event; and

a dispatch control element, coupled to said dispatch prediction element, configured to receive said dispatch order reception time, and configured to prepare actions required to control said each of the buildings to optimally shed energy specified in a corresponding dispatch order.

9. The system as recited in claim 8, wherein said plurality of lag values indicates shifts of said energy consumption values to different time and outside temperature values.

10. The system as recited in claim 8, wherein said corresponding time values are less than or equal to said corresponding energy lag for said each of said buildings.

11. The system as recited in claim 8, wherein said corresponding time values comprise hourly values and said plurality of lag values spans a 24-hour period.

12. The system as recited in claim 8, wherein said dispatch order reception time is predicted as a function of demand response contract data and a specified threshold known to trigger said demand response program event.

13. The system as recited in claim 8, wherein said cumulative energy consumption for said buildings comprises a future energy consumption timeline as a function of said outside temperatures.

14. The system as recited in claim 8, wherein said each of said plurality of energy use data sets comprises a first portion of a corresponding each of a plurality of baseline energy use data sets, and wherein required energy consumption values resulting from shifts are taken from a second portion of said corresponding each of a plurality of baseline energy use data sets.

15. A method for dispatching buildings participating in a demand response program event, the method comprising:

retrieving a plurality of baseline energy use data sets for the buildings from a baseline data stores;

generating a plurality of energy use data sets for each of the buildings, each of the plurality of energy use data sets comprising energy consumption values along with corresponding time and outside temperature values, wherein the energy consumption values within the each of the plurality of energy use data sets are shifted by one of a plurality of lag values relative to the corresponding time and outside temperature values, and wherein each of the plurality of lag values is different from other ones of the plurality of lag values;

performing a machine learning model analysis on the each of the plurality of energy use data sets to yield corresponding machine learning model parameters and a corresponding residual;

determining a least valued residual from all residuals yielded by the machine learning model analysis, the least valued residual indicating a corresponding energy lag for the each of the buildings, wherein the corresponding energy lag describes a transient energy consumption period preceding a change in outside temperature;

using outside temperatures, the machine learning model parameters, and energy lags for all of the buildings to estimate a cumulative energy consumption for the buildings, and to predict a dispatch order reception time for the demand response program event; and

employing the dispatch order reception time to prepare actions required to control the each of the buildings to optimally shed energy specified in a corresponding dispatch order.

16. The method as recited in claim 15, wherein the plurality of lag values indicates shifts of the energy consumption values to different time and outside temperature values.

17. The method as recited in claim 15, wherein the corresponding time values are less than or equal to the energy lags.

18. The method as recited in claim 15, wherein the corresponding time values comprise hourly values and the plurality of lag values spans a 24-hour period.

19. The method as recited in claim 15, wherein the dispatch order reception time is predicted as a function of demand response contract data and a specified threshold known to trigger the demand response program event.

20. The method as recited in claim 15, wherein the cumulative energy consumption for the buildings comprises a future energy consumption timeline as a function of the outside temperatures.

21. The method as recited in claim 15, wherein the each of the plurality of energy use data sets comprises a first portion of a corresponding each of a plurality of baseline energy use data sets, and wherein required energy consumption values resulting from shifts are taken from a second portion of the corresponding each of a plurality of baseline energy use data sets.