Advertisement

Survey of Projects Involving Evolutionary Algorithms Sponsored by the Electric Power Research Institute

  • A. Martin Wildberger
Chapter
  • 330 Downloads
Part of the The IMA Volumes in Mathematics and its Applications book series (IMA, volume 111)

Abstract

Over the last five years, the Electric Power Research Institute (EPRI) has been engaged in a number of research and development projects using evolutionary algorithms for applications in the electric power industry. (EPRI 1994b) Most of these projects also involve theory, since advances in theoretical understanding is often necessary in order to address critical barriers faced in practical applications. Projects reviewed briefly in this paper include:

This chapter briefly describes:
  • successful use of global optimization by genetic algorithms combined with parallel local solutions by coupled gradient neural networks to solve the unit commitment problem (a highly constrained, mixed-integer programming problem usually attacked by Lagrangian relaxation methods).

  • projects co-sponsored with the National Science Foundation that are using evolutionary methods in combination with other techniques in the context of “intelligent control systems.”

  • successful use of a genetic algorithm to test an expert system for improving the performance of fossil-fueled power plants.

  • successful use of genetic algorithms to optimize a neural network for heat-rate improvement of nuclear plant operation; now being extended to construct a generic tool for the automated design and optimization of neural networks in any context.

  • exploration of ways to use autonomous evolving agents as a modeling technique for the electric power market and ultimately for the industry itself as it moves toward increased deregulation and competition.

  • plans for the use of multiple adaptive agents as a modeling method to allow real-time, distributed control of the electric power grid.

Keywords

Genetic Algorithm Expert System Electric Power Research Institute Electric Power Industry Adaptive Control System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Anderson, P.W., Arrow, K.J. and D. Pines. eds.The Economy as an Evolving Complex System, Reading, MA: Addison Wesley, 1988.zbMATHGoogle Scholar
  2. [2]
    Axelrod, R. TheEvolution of Cooperation, New York: Basic Books, 1994.Google Scholar
  3. [3]
    Brams, S.T. and Mattli, W. Theory of Moves: Overview and Examples.Conflict Management and Peace Science 12(2):1–29, 1993.Google Scholar
  4. [4]
    Electric Power Research Institute,Optimization of theUnit Commitment Problem by aCoupled Gradient Network and by aGenetic Algorithm, EPRI Technical Report TR-103697, Pleasant Hill, CA: EPRI Dist. Ctr. (May), 1994a.Google Scholar
  5. [5]
    Electric Power Research Institute, Evolutionary Computing, EPRI Technical Brief, TB-104097. EPRI Dist. Ctr. Pleasant Hill, CA (Jun.), 1994b.Google Scholar
  6. [6]
    Electric Power Research Institute,Genetic Optimization of Neural Network Architecture TR-104074, EPRI Dist. Ctr. Pleasant Hill, CA, 1994c.Google Scholar
  7. [7]
    Electric Power Research Institute,Genetic Algorithm Testbed for Expert System Testing EPRI Report, TR-106004. EPRI Dist. Ctr. Pleasant Hill, CA (Jan.) 1996a.Google Scholar
  8. [8]
    Electric Power Research Institute,Integrated Knowledge Framework (IKF) for Coal-Fired Power Plants, EPRI Technical Report TR-106211-V1/2/3, Pleasant Hill, CA: EPRI Dist. Ctr. (Mar), 1996b.Google Scholar
  9. [9]
    Electric Power Research Institute,High-Power Electronics Advanced Technology Program, EPRI Brochure BR-1006800, Pleasant Hill, CA: EPRI Dist. Ctr, 1996c.Google Scholar
  10. [10]
    Friedman, D. and J. Rust. ed.,The Double Auction Market, Reading, MA: Addison Wesley, 1993.Google Scholar
  11. [11]
    Goldberg, D.,Genetic Algorithms in Search Optimization and Machine Learning, Reading, MA: Addison Wesley, 1988.Google Scholar
  12. [12]
    Grefenstette, J.J. ed.,Proceedings of theFirst International Conference on Genetic Algorithms and Their Applications (Pittsburgh, July 1985), Lawrence Erlbaum, Hillsdale, NJ, 1988.Google Scholar
  13. [13]
    Harp, S.A. and T. Samad,Genetic algorithms and neural networksfor optimized modeling and control InMission Earth: Modeling and Simulation for aSustainable Future,Proceedings of the 1995 WesternMulticonference (Las Vegas, Nevada, Jan. 15–18) A.M. Wildberger, ed., 14–20, San Diego, CA: Society for Computer Simulation, 1988.Google Scholar
  14. [14]
    Holland, J.H., The Effect of Labels (Tags) on Social Interactions, Technical Report, 93–10–064, Santa Fe Institute, 1993.Google Scholar
  15. [15]
    Koza, J.R., Genetic Programming: On the Programming of Computers by Means of Natural Selection, Cambridge. MA: MIT Press, 1992.Google Scholar
  16. [16]
    Koza, J.R., Genetic Programming II: Scalable Automatic Programming by Means of Automatically Defined Functions, Cambridge. MA: MIT Press, 1994.Google Scholar
  17. [17]
    Roache, E.A., K.A. Hickok, K.F. Loje, M.W. Hunt and J.J. Grefenstette, Genetic Algorithms for Expert System Validation In Mission Earth: Modeling and Simulation for a Sustainable Future, Proceedings of the 1995 Western Multi-conference (Las Vegas, Nevada, Jan. 15–18) A.M. Wildberger, ed., 45–51, San Diego, CA: Society for Computer Simulation, 1995.Google Scholar
  18. [18]
    Santa Fe Institute (sfi@santafe.edu),ftp://ftp.santafe.edu/pub/swarm/ or from WEB site:http://www.santafe.edu/projects/swarm/ 1996.Google Scholar
  19. [19]
    Wildberger A.M., Genetic Algorithms as a Modeling Tool In Proceedings of the 1994 European Simulation Symposium, 24–28, Ghent, Belgium: Society for Computer Simulation International, 1994a.Google Scholar
  20. [20]
    Wildberger, A.M., Automated Management for Future Power Networks: A Long-Term Vision, Public Utilities Fortnightly, 132, 20 (Nov.): 38–41, 1994b.Google Scholar
  21. [21]
    Wildberger, A.M., Some Implications of Soft Computing for Simulation, In Proceedings of the 1995 Summer Computer Simulation Conference, 237–241, San Diego, CA: Society for Computer Simulation, 1995.Google Scholar

Copyright information

© Springer Science+Business Media New York 1999

Authors and Affiliations

  • A. Martin Wildberger
    • 1
  1. 1.Mgr., Mathematics & Information Science Strategic Research & DevelopmentElectric Power Research InstitutePalo AltoUSA

Personalised recommendations