SYSTEMS AND METHODS FOR MODEL-BASED SOLAR POWER MANAGEMENT

• US 20140136178A1
• Filed: 11/15/2013
• Published: 05/15/2014
• Est. Priority Date: 11/15/2012
• Status: Abandoned Application

• Current Assignee: WaveTech Global Inc.
• Original Assignee: Power Analytics Corporation (PAC Global, Inc.)
• Inventors: Meagher, Kevin, Radibratovic, Brian, Chudgar, Raj, Koopman, Rodger
• Application Number:
  US14/081,487
• Publication Number:
  US 20140136178A1
• Time in Patent Office: Days
• US Class Current: 703/18
• CPC Class Codes: G06F 17/11 for solving equations , e.g. nonlinear equations, general mathematical optimization problems optimization specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/047 Pattern matching networks; Rete networks
• CPC Class Codes: Y02E 10/50 Photovoltaic [PV] energy

Abstract

Systems and methods for model-based real-time solar power management. In an embodiment, real-time data is received from sensor(s) of an electrical system comprising a photo-voltaic power generator. Predicted data is generated based on a virtual model of the electrical system that replicates operation of the sensor(s). The virtual model is continuously and automatically synchronized with the electrical system based on a difference between the real-time data and the predicted data. Solar irradiance forecast data may also be received and used in conjunction with the virtual model to forecast a power output of the photo-voltaic power generator.

Claims

1. A system for predicting power output from a photo-voltaic power generator, the system comprising:

at least one hardware processor; and

one or more software modules that are configured to, when executed by the at least one hardware processor,

receive real-time data from one or more sensors of an electrical system comprising a photo-voltaic power generator,

generate predicted data based on a virtual model of the electrical system that replicates operation of the one or more sensors,

continuously and automatically synchronize the virtual model with the electrical system based on a difference between the real-time data and the predicted data,

receive solar irradiance forecast data, and

forecast a power output of the photo-voltaic power generator based on the virtual model and the solar irradiance forecast data.

2. The system of claim 1, wherein the photo-voltaic power generator comprises an inverter, and wherein the one or more software modules are further configured to provide ramp-up and ramp-down signals to the inverter.

3. The system of claim 2, wherein the one or more software modules are further configured to provide Volt/VAR and frequency targets to the inverter.

4. The system of claim 3, wherein the one or more software modules are further configured to receive feedback from the inverter.

5. The system of claim 4, wherein the one or more software modules are further configured to provide the feedback to an operator.

6. The system of claim 4, wherein the one or more software modules are further configured to provide the feedback to an electronic market.

7. The system of claim 1, wherein the one or more software modules are further configured to calculate an amount of energy storage based on the forecasted power output.

8. The system of claim 1, wherein continuously and automatically synchronizing the virtual model with the electrical system based on a difference between the real-time data and the predicted data comprises:

when the difference exceeds a threshold, updating the virtual model; and

,

when the difference does not exceed the threshold, not updating the virtual model.

9. The system of claim 1, wherein continuously and automatically synchronizing the virtual model with the electrical system based on a difference between the real-time data and the predicted data comprises:

when the difference exceeds a first threshold but does not exceed a second threshold that is higher than the first threshold, updating the virtual model;

when the difference does not exceed the first threshold, not updating the virtual model; and

,

when the difference exceeds the second threshold, generating an alert, and not updating the virtual model.

10. The system of claim 9, wherein updating the virtual model comprises adjusting one or more operating parameters of the virtual model.

11. A method for predicting power output from a photo-voltaic power generator, the method comprising using at least one hardware processor to:

receive real-time data from one or more sensors of an electrical system comprising a photo-voltaic power generator,

generate predicted data based on a virtual model of the electrical system that replicates operation of the one or more sensors,

continuously and automatically synchronize the virtual model with the electrical system based on a difference between the real-time data and the predicted data,

receive solar irradiance forecast data, and

forecast a power output of the photo-voltaic power generator based on the virtual model and the solar irradiance forecast data.

12. The method of claim 11, wherein the photo-voltaic power generator comprises an inverter, and wherein the method further comprises providing one or more of a ramp-up signal and a ramp-down signal to the inverter.

13. The method of claim 12, wherein the method further comprises providing Volt/VAR and frequency targets to the inverter.

14. The method of claim 13, further comprising receiving feedback from the inverter.

15. The method of claim 14, further comprising providing the feedback to an operator.

16. The method of claim 15, further comprising providing the feedback to an electronic market.

17. The method of claim 11, further comprising calculating an amount of energy storage based on the forecasted power output.

18. The method of claim 11, wherein continuously and automatically synchronizing the virtual model with the electrical system based on a difference between the real-time data and the predicted data comprises:

when the difference exceeds a threshold, updating the virtual model; and

,

when the difference does not exceed the threshold, not updating the virtual model.

19. The method of claim 11, wherein continuously and automatically synchronizing the virtual model with the electrical system based on a difference between the real-time data and the predicted data comprises:

when the difference exceeds a first threshold but does not exceed a second threshold that is higher than the first threshold, updating the virtual model;

when the difference does not exceed the first threshold, not updating the virtual model; and

,

when the difference exceeds the second threshold, generating an alert, and not updating the virtual model.

20. The method of claim 19, wherein updating the virtual model comprises adjusting one or more operating parameters of the virtual model.