Direct neural dynamic programming method for power system stability enhancement

Chao Lu, Jennie Si, Xiaorong Xie, Lei Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A neural network-based approximate dynamic programming (ADP) method, the direct neural dynamic programming (direct NDP), is introduced in this paper. The paper covers the basic principle of this learning scheme and an illustrative example of how direct NDP can be implemented. The paper focuses on how direct NDP can be applied to power system stability control. In this case direct NDP is based on real-time system measurements provided by wide area measurement system (WAMS) to compensate for nonlinearities and uncertainties in the system. The learning objective used in controller design makes use of a reward function that reflects system global characteristics if available. This learning control mechanism is adopted in the implementation of a static var compensator (SVC) supplementary damping control and two DC power modulation control systems. The design and evaluation of the learning controller and the system performance are evaluated based on simulations of a standard 2-area system. Results demonstrate the adaptive and learning features of the neural controller which is advantageous over traditional control designs.

Original languageEnglish (US)
Title of host publicationProceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05
Pages128-135
Number of pages8
Volume2005
DOIs
StatePublished - 2005
Event13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05 - Arlington, VA, United States
Duration: Nov 6 2005Nov 10 2005

Other

Other13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05
CountryUnited States
CityArlington, VA
Period11/6/0511/10/05

Fingerprint

System stability
Dynamic programming
Controllers
Control system stability
Electric power system measurement
Real time systems
Damping
Modulation
Neural networks
Control systems

Keywords

  • Direct neuro dynamic programming
  • Power system stability control
  • Wide area measurement system

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Lu, C., Si, J., Xie, X., & Yang, L. (2005). Direct neural dynamic programming method for power system stability enhancement. In Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05 (Vol. 2005, pp. 128-135). [1599252] https://doi.org/10.1109/ISAP.2005.1599252

Direct neural dynamic programming method for power system stability enhancement. / Lu, Chao; Si, Jennie; Xie, Xiaorong; Yang, Lei.

Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05. Vol. 2005 2005. p. 128-135 1599252.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lu, C, Si, J, Xie, X & Yang, L 2005, Direct neural dynamic programming method for power system stability enhancement. in Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05. vol. 2005, 1599252, pp. 128-135, 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05, Arlington, VA, United States, 11/6/05. https://doi.org/10.1109/ISAP.2005.1599252
Lu C, Si J, Xie X, Yang L. Direct neural dynamic programming method for power system stability enhancement. In Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05. Vol. 2005. 2005. p. 128-135. 1599252 https://doi.org/10.1109/ISAP.2005.1599252
Lu, Chao ; Si, Jennie ; Xie, Xiaorong ; Yang, Lei. / Direct neural dynamic programming method for power system stability enhancement. Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05. Vol. 2005 2005. pp. 128-135
@inproceedings{fd23b5e099514eceacbfe45397443ecf,
title = "Direct neural dynamic programming method for power system stability enhancement",
abstract = "A neural network-based approximate dynamic programming (ADP) method, the direct neural dynamic programming (direct NDP), is introduced in this paper. The paper covers the basic principle of this learning scheme and an illustrative example of how direct NDP can be implemented. The paper focuses on how direct NDP can be applied to power system stability control. In this case direct NDP is based on real-time system measurements provided by wide area measurement system (WAMS) to compensate for nonlinearities and uncertainties in the system. The learning objective used in controller design makes use of a reward function that reflects system global characteristics if available. This learning control mechanism is adopted in the implementation of a static var compensator (SVC) supplementary damping control and two DC power modulation control systems. The design and evaluation of the learning controller and the system performance are evaluated based on simulations of a standard 2-area system. Results demonstrate the adaptive and learning features of the neural controller which is advantageous over traditional control designs.",
keywords = "Direct neuro dynamic programming, Power system stability control, Wide area measurement system",
author = "Chao Lu and Jennie Si and Xiaorong Xie and Lei Yang",
year = "2005",
doi = "10.1109/ISAP.2005.1599252",
language = "English (US)",
isbn = "1599750287",
volume = "2005",
pages = "128--135",
booktitle = "Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05",

}

TY - GEN

T1 - Direct neural dynamic programming method for power system stability enhancement

AU - Lu, Chao

AU - Si, Jennie

AU - Xie, Xiaorong

AU - Yang, Lei

PY - 2005

Y1 - 2005

N2 - A neural network-based approximate dynamic programming (ADP) method, the direct neural dynamic programming (direct NDP), is introduced in this paper. The paper covers the basic principle of this learning scheme and an illustrative example of how direct NDP can be implemented. The paper focuses on how direct NDP can be applied to power system stability control. In this case direct NDP is based on real-time system measurements provided by wide area measurement system (WAMS) to compensate for nonlinearities and uncertainties in the system. The learning objective used in controller design makes use of a reward function that reflects system global characteristics if available. This learning control mechanism is adopted in the implementation of a static var compensator (SVC) supplementary damping control and two DC power modulation control systems. The design and evaluation of the learning controller and the system performance are evaluated based on simulations of a standard 2-area system. Results demonstrate the adaptive and learning features of the neural controller which is advantageous over traditional control designs.

AB - A neural network-based approximate dynamic programming (ADP) method, the direct neural dynamic programming (direct NDP), is introduced in this paper. The paper covers the basic principle of this learning scheme and an illustrative example of how direct NDP can be implemented. The paper focuses on how direct NDP can be applied to power system stability control. In this case direct NDP is based on real-time system measurements provided by wide area measurement system (WAMS) to compensate for nonlinearities and uncertainties in the system. The learning objective used in controller design makes use of a reward function that reflects system global characteristics if available. This learning control mechanism is adopted in the implementation of a static var compensator (SVC) supplementary damping control and two DC power modulation control systems. The design and evaluation of the learning controller and the system performance are evaluated based on simulations of a standard 2-area system. Results demonstrate the adaptive and learning features of the neural controller which is advantageous over traditional control designs.

KW - Direct neuro dynamic programming

KW - Power system stability control

KW - Wide area measurement system

UR - http://www.scopus.com/inward/record.url?scp=33847365758&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847365758&partnerID=8YFLogxK

U2 - 10.1109/ISAP.2005.1599252

DO - 10.1109/ISAP.2005.1599252

M3 - Conference contribution

AN - SCOPUS:33847365758

SN - 1599750287

SN - 9781599750286

VL - 2005

SP - 128

EP - 135

BT - Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems, ISAP'05

ER -