DEMAND RESPONSE SYSTEM HAVING A PARTICIPATION PREDICTOR

• US 20150170171A1
• Filed: 01/16/2015
• Published: 06/18/2015
• Est. Priority Date: 07/11/2013
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: McCurnin, David J., Dalsin, Nicholas, Rourke, Seth, Koch, Edward
• Granted Patent: US 9,691,076 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 50/06 Energy or water supply
• CPC Class Codes: Y02B 70/3225 Demand response systems, e.g. load shedding, peak shaving
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management
• CPC Class Codes: Y02P 90/82 Energy audits or management systems therefor
• CPC Class Codes: Y04S 20/222 Demand response systems, e.g. load shedding, peak shaving

Abstract

A demand response management system having a participation predictor. There may be a storage device having information collected about past behavior, related to participation in a demand response program, about a customer. The information may incorporate determining a period of time since the customer last participated in a demand response program, a frequency of participation in demand response events by the customer, and a size of energy loads of the customer. A model of the customer may be developed from this and other information. A processor may be used to collect and process the information, develop a model, and to make a prediction of a customer'"'"'s being selected to participate in an event based on the various operator selectable criteria.

Claims

1. A demand response prediction mechanism comprising:

a processor; and

a storage device connected to the processor; and

wherein;

the storage device comprises a demand response (DR) program having opt-in or opt-out participation for one or more customers;

the storage device further comprises inputted information about past behavior of the one or more customers in DR programs;

a model is constructed for each of the one or more customers based on the inputted information about the past behavior about the one or more customers in the DR programs; and

prediction of participation of the one or more customers in an opt-in or opt-out DR program is derived from respective models for the one or more customers.

2. The mechanism of claim 1, wherein a utility of the DR programs has an ability to predict participation of the one or more customers in the opt-in or opt-out DR program for a load shed.

3. The mechanism of claim 2, wherein:

a customer receives credits for each instance of participation in a DR program; and

each instance of participation is an opt-in.

4. The mechanism of claim 3, wherein one or more customers can opt-in automatically or respond to an invitation to opt-in.

5. The mechanism of claim 3, wherein:

each DR program is managed by the utility; and

a number of credits is determined by the utility to create an incentive for one or more customers.

6. The mechanism of claim 5, wherein:

the credits to one or more customers are tracked by a smart phone or web app;

one or more customers can bid for credits; and

the utility can select the one or more customers to opt-in a DR program.

7. The mechanism of claim 2, wherein an opt-in or opt-out of a DR program can be based on a location of the smart phone or web app.

8. The mechanism of claim 6, wherein:

the smart phone or web app can detect a GPS position and notify a DR system that a person of the smart phone is home or away from home;

the person can be asked to opt-in or opt-out to participate in a DR event; and

a decision to opt-in or opt-out can be manual or automatic.

9. A demand response predictor system comprising:

a processor; and

a storage mechanism, connected to the processor, for containing data about a customer in a demand response (DR) program; and

wherein;

a model of the customer is developed from data in the storage mechanism, with the processor; and

a prediction of the customer being selected to participate in the DR program is made from the model with the processor.

10. The system of claim 9, wherein the customer will be selected to participate in a DR event.

11. The system of claim 10, wherein the data in the storage mechanism comprise information about the customer in one or more DR programs.

12. The system of claim 11, wherein:

recency, frequency and load are determined from the past behavior of the customer in the one or more DR programs; and

the recency, frequency and load provide a basis for developing the model of the customer, with the processor.

13. The system of claim 12, wherein:

recency is a period of time since the customer last participated in a DR program;

frequency is a number of DR events that the customer participated in during a specific amount of time; and

load is a size of an energy load of the customer.

14. The system of claim 13, wherein:

recency, frequency and load are categorized into groups according to magnitudes of frequency,

load, and recency; and

predicting a selection of a customer to participate in a DR event for a load shed is based upon membership of the customer in the groups by a utility operator.

15. A method for predicting a customer'"'"'s participation in a demand response program, comprising:

providing a processor;

collecting information about past behavior of a customer in a demand response (DR) program;

developing a model of the customer from the information with the processor; and

predicting selection of a customer for participation in a DR program, with the processor, based on the model.

16. The method of claim 15, further comprising predicting for a utility operator participation of one or more customers based on the model, in a DR event for a load shed.

17. The method of claim 15, further comprising:

determining recency, frequency and load from the information about past behavior of the customer in a DR program; and

developing the model of the customer from recency, frequency and load.

18. The method of claim 17, wherein:

recency is a period of time since the customer last participated in a DR program;

frequency is a number of DR events that the customer participated in during a specific amount of time; and

load is a size of an energy load of the customer.

19. The method of claim 18, further comprising:

categorizing recency, frequency and load of customers into groups according to rankings; and

wherein the rankings indicate predictability of a customer being selected relative to other customers to participate in a DR event.

20. The method of claim 17, further comprising:

determining a number of DR opt outs left for the customer, a number of DR events participated in the past by the customer and a number of DR events that the customer has to participate in; and

developing further the model of the customer with the number of DR opt outs left for the customer, the number of DR events participated in the past by the customer, and the number of DR events in that the customer has to participate.