Systems And Methods For Model-Based Solar Power Management

• US 20170228653A1
• Filed: 04/26/2017
• Published: 08/10/2017
• Est. Priority Date: 11/15/2012
• Status: Abandoned Application

• Current Assignee: WaveTech Global Inc.
• Original Assignee: Power Analytics Corporation (PAC Global, Inc.)
• Inventors: Radibratovic, Branislav, Chudgar, Raj, Meagher, Kevin, Koopman, Rodger
• Application Number:
  US15/497,913
• Publication Number:
  US 20170228653A1
• Time in Patent Office: Days
• 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 comprising:

an analytics server constructed and configured for communication with a data acquisition component and a database;

wherein the server is operable to;

receive real-time data from an electrical system having at least one photo-voltaic (PV) power generation resource, the real-time data communicated by the data acquisition component;

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

synchronize the virtual model with the electrical system real-time data based upon 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 synchronized virtual model and the solar irradiance forecast data.

2. The system of claim 1, wherein the PV power generation resource includes at least one PV inverter.

3. The system of claim 1, wherein the analytics server is further operable to communicate ramp-up and ramp-down control messages to the at least one PV inverter.

4. The system of claim 1, wherein the analytics server is further operable to communicate Volt/VAR targets to the at least one PV inverter.

5. The system of claim 1, wherein the analytics server is further operable to communicate frequency targets to the at least one PV inverter

6. The system of claim 1, wherein the analytics server and at least one PV generation resource are operable for two-way network-based communication with each other.

7. The system of claim 1, wherein the analytics server is further operable to receive information from the at least one PV power generation resource.

8. The system of claim 1, wherein the analytics server is further operable to communicate information about the at least one PV power generation resource to an energy market.

9. The system of claim 1, wherein the analytics server receives real-time power generation information from the at least one PV power generation resource.

10. The system of claim 1, wherein the analytics server is operable to update the virtual model when the difference between the real-time data and the predicted data exceeds a threshold.

11. The system of claim 1, wherein the synchronizing of the virtual model with the real-time data of the electrical system is continuous and automatic.

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

an analytics server receiving real-time data from an electrical system including at least one PV power generation resource;

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

synchronizing the virtual model with the real-time data of the electrical system based upon a difference between the real-time data and the predicted data;

receiving solar irradiance forecast data; and

forecasting a power output of the at least one PV power generation resource based on the virtual model and the solar irradiance forecast data.

13. The method of claim 12, further including sending ramp-up and ramp-down control messages to the at least one PV power generation resource.

14. The method of claim 12, further including sending Volt/VAR target messages to the at least one PV power generation resource.

15. The method of claim 12, further including sending frequency target messages to the at least one PV power generation resource,

16. The method of claim 12, further including receiving messages from the at least one PV generation resource.

17. The method of claim 16, wherein the messages include real-time power output data from the at least one PV power generation resource.

18. The method of claim 12, further comprising updating the virtual model when the difference exceeds a threshold value.