Very short term load prediction

• US 7,058,522 B2
• Filed: 05/07/2004
• Issued: 06/06/2006
• Est. Priority Date: 05/13/2003
• Status: Expired due to Fees

• Current Assignee: Siemens AG
• Original Assignee: Siemens Power Transmission & Distribution Incorporated (Siemens AG)
• Inventors: Chen, Dingguo
• Primary Examiner(s): Raymond, Edward
• Application Number:
  US10/841,058
• Publication Number:
  US 20040246643A1
• Time in Patent Office: 760 Days
• Field of Search: 702/60, 702182-185, 702/188, 706 15- 23
• US Class Current: 702/60
• CPC Class Codes: H02J 2203/20 Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
• CPC Class Codes: H02J 3/00 Circuit arrangements for ac mains or ac distribution networks
• CPC Class Codes: H02J 3/003 Load forecast, e.g. methods or systems for forecasting future load demand
• CPC Class Codes: Y02E 60/00 Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
• CPC Class Codes: Y04S 10/50 Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
• CPC Class Codes: Y04S 40/20 Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Abstract

Certain exemplary embodiments provide a method comprising: providing system electrical load information for an electric power system to one or more neural networks; and via the one or more neural networks, predicting a system electrical load for a predetermined immediate future period.

Claims

1. A method, comprising:

receiving system electrical load information for an electric power system at one or more neural networks;

via the one or more neural networks, predicting a system electrical load for a predetermined immediate future period in predetermined intervals; and

providing the predicted system electrical load to a Dynamic Economic Dispatch module adapted to use a Lagrange Multiplier approach to determine a response to the predicted system electrical load.

2. The method of claim 1, further comprising:

receiving an identification of a source of the system electrical load information.

3. The method of claim 1, further comprising:

obtaining system electrical load information.

4. The method of claim 1, further comprising:

obtaining historical system electrical load information.

5. The method of claim 1, further comprising:

obtaining actual system electrical load information for a predetermined immediate past period.

6. The method of claim 1, further comprising:

obtaining actual system electrical load information for a predetermined immediate past period in predetermined intervals.

7. The method of claim 1, further comprising:

filtering the system electrical load information.

8. The method of claim 1, further comprising:

normalizing the system electrical load information.

9. The method of claim 1, further comprising:

smoothing the system electrical load information.

10. The method of claim 1, further comprising:

determining patterns in the system electrical load information.

11. The method of claim 1, further comprising:

classifying the system electrical load information.

12. The method of claim 1, further comprising:

calculating parameters of the system electrical load information.

13. The method of claim 1, further comprising:

training the one or more neural networks.

14. The method of claim 1, wherein the one or more neural networks utilize a nonlinear dynamic model.

15. The method of claim 1, wherein each of the one or more neural networks is responsible for a non-overlapping time period of a day.

16. The method of claim 1, wherein the system electrical load information is provided to the one or more neural networks automatically at a predetermined frequency.

17. The method of claim 1, wherein the system electrical load information is provided to the one or more neural networks manually.

18. The method of claim 1, wherein the system electrical load information comprises incremental system load information.

19. The method of claim 1, wherein the system electrical load information comprises absolute system load information.

20. A machine-readable medium containing instructions for activities comprising:

receiving system electrical load information for an electric power system at one or more neural networks;

via the one or more neural networks, predicting a system electrical load for a predetermined immediate future period in predetermined intervals; and

providing the predicted system electrical load to a Dynamic Economic Dispatch module adapted to use a Lagrange Multiplier approach to determine a response to the predicted system electrical load.

21. A system comprising:

one or more neural networks adapted to predict a system electrical load for an electric power system, the system electrical load predicted for a predetermined immediate future period in predetermined intervals;

a Dynamic Economic Dispatch module adapted to use a Lagrange Multiplier approach to determine a response to the predicted system electrical load, the predicted system electrical load received from said one or more neural networks; and

a user interface for specifying operations of said one or more neural networks.