Systems And Methods For Model-Based Solar Power Management

• US 20160246907A1
• Filed: 04/04/2016
• Published: 08/25/2016
• Est. Priority Date: 11/15/2012
• Status: Abandoned Application

• Current Assignee: WaveTech Global Inc.
• Original Assignee: Power Analytics Corporation (PAC Global, Inc.)
• Inventors: Chudgar, Raj, Meagher, Kevin, Radibratovic, Branislav, Koopman, Rodger
• Application Number:
  US15/089,938
• Publication Number:
  US 20160246907A1
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 predicting power output from photo-voltaic power generation resources are disclosed. An analytics server is communicatively connected to a data acquisition component and a virtual system model database. The analytics server is operable to receive real-time data via the data acquisition component from an electrical system comprising photo-voltaic power generation resources; generate predicted data based on a virtual model of the electrical system provided by the virtual system model database; 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 generation resources based on the virtual model and the solar irradiance forecast data. The photo-voltaic power generation resources include at least one photo-voltaic inverter.

Claims

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

an analytics server communicatively connected to a data acquisition component and a virtual system model database;

wherein the analytics server is operable to;

receive real-time data via the data acquisition component from an electrical system comprising photo-voltaic power generation resources;

generate predicted data based on a virtual model of the electrical system provided by the virtual system model database;

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 generation resources based on the virtual model and the solar irradiance forecast data.

2. The system of claim 1, wherein the photo-voltaic power generation resources includes at least one photo-voltaic inverter.

3. The system of claim 2, wherein the analytics server is operable to send ramp-up and ramp-down signals to the at least one photo-voltaic inverter.

4. The system of claim 2, wherein the analytics server is further operable to send Volt/VAR and frequency targets to the at least one photo-voltaic inverter.

5. The system of claim 2, wherein the analytics server is further operable to receive feedback from the at least one photo-voltaic inverter.

6. The system of claim 5, wherein the analytics server is further operable to provide the feedback to an operator.

7. The system of claim 5, wherein the analytics server is further operable to provide the feedback to an energy market.

8. The system of claim 5, wherein the feedback from the at least one photo-voltaic inverter comprises real-time power output from the photo-voltaic power generation resources.

9. The system of claim 1, wherein the analytics server is operable to update the virtual model when the difference exceeds a Defined Difference Tolerance (DDT) value but below an alarm threshold value.

10. The system of claim 9, wherein the analytics server is operable to generate an alert and not update the virtual model when the difference exceeds the alarm threshold value.

11. A method for predicting power output from photo-voltaic power generation resources, comprising:

receiving real-time data from an electrical system comprising photo-voltaic power generation resources;

generating predicted data based on a virtual model of the electrical system;

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

receiving solar irradiance forecast data; and

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

12. The method of claim 11, wherein the photo-voltaic power generation resources includes at least one photo-voltaic inverter.

13. The method of claim 12, further comprising sending ramp-up and ramp-down signals to the at least one photo-voltaic inverter.

14. The method of claim 12, further comprising sending Volt/VAR and frequency targets to the at least one photo-voltaic inverter.

15. The method of claim 12, further comprising receiving feedback from the at least one photo-voltaic inverter.

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

17. The method of claim 15, further comprising providing the feedback to an energy market.

18. The method of claim 15, wherein the feedback from the at least one photo-voltaic inverter comprises real-time power output from the photo-voltaic power generation resources.

19. The method of claim 11, further comprising updating the virtual model when the difference exceeds a Defined Difference Tolerance (DDT) value but below an alarm threshold value.

20. The method of claim 19, further comprising generating an alert and not updating the virtual model when the difference exceeds the alarm threshold value.