Estimation of Distributed Generation Using Complex-Valued Network Inversion with Regularization

Chapter
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 110)

Abstract

Network inversion has been studied as a neural network based solution of inverse problems. Complex-valued network inversion has been proposed as the extension of this inversion to the complex domain. Further, regularization is considered for solving ill-posed inverse problems. On the other hand, the estimation of the parameters of a distributed generation from observed data is a complex-valued inverse problem with ill-posedness. In this chapter, we propose the application of a complex-valued network inversion with regularization to the inverse estimation of a distributed generation.

Keywords

Complex-valued neural networks Distributed generation Ill-posed inverse problems Regularization 

Notes

Acknowledgement

This work was supported in part by a Grant-in-Aid for Scientific Research #21700260 from the Japan Society for the Promotion of Science.

References

  1. 1.
    Grötsch CW (1993) Inverse problems in the mathematical sciences. Informatica InternationalGoogle Scholar
  2. 2.
    Linden A, Kindermann J (1989) Inversion of multilayer nets. Proceedings of the International Joint Conference on Neural Networks II, pp. 425–430Google Scholar
  3. 3.
    Ogawa T, Kanada H (2005) Network inversion for complex-valued neural networks. Proceedings of the IEEE International Symposium on Signal Processing and Information Technology, pp. 850–855Google Scholar
  4. 4.
    Tikhonov AN, Arsenin VY (1977) Solutions of ill-posed problems. WinstonGoogle Scholar
  5. 5.
    Fukami S, Ogawa T, Kanada H (2008) Regularization for complex-valued network inversion. Proceedings of the SICE Annual Conference, 1237–1242Google Scholar
  6. 6.
    Korovkin NV, Chechurin VL, Hayakawa M (2007) Inverse problems in electric circuits and electromagnetics. SpringerGoogle Scholar
  7. 7.
    Craig IJD, Brown JC (1986) Inverse problems in astronomy. Adam HilgerGoogle Scholar
  8. 8.
    Craig JJ (1989) Introduction to robotics mechanics and control. Addison-WesleyGoogle Scholar
  9. 9.
    Valova I, Kameyama K, Kosugi Y (1995) Image decomposition by answer-in-weights neural network. IEICE Trans Inform Syst E78-D-9:1221–1224Google Scholar
  10. 10.
    Lu B-L, Ito K (1999) Regularization of inverse kinematics for redundant manipulators using neural network inversion. Proceedings of the IEEE international conference on neural networks, pp.2726–2731Google Scholar
  11. 11.
    Nitta T (1997) An extension of the backpropagation algorithm to complex numbers. Neural Networks 10(8):1392–1415CrossRefGoogle Scholar
  12. 12.
    Hirose A, Hara T (2003) Complex-valued self-organizing map dealing with multi-frequency interferometeric data for radar imaging systems. Proceedings of WSOM 2003, pp. 255–260Google Scholar
  13. 13.
    Nemoto I, Kubono M (1996) Complex associative memory. Neural Networks 9:253–261CrossRefGoogle Scholar
  14. 14.
    Ogawa T, Nakamura K, Kanada H (2011) Solution of ill-posed inverse problem of distributed generation using complex-valued network inversion. Lecture notes in engineering and computer science: proceedings of the international multiconference of engineers and computer scientists 2011, IMECS 2011, Hong Kong, 16–18 March 2011Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Takehiko Ogawa
    • 1
  • Kyosuke Nakamura
    • 2
  • Hajime Kanada
    • 1
  1. 1.Department of Electronics and Computer SystemsTakushoku UniversityHachioji-shiJapan
  2. 2.Electronics and Information Science Course, Graduate School of EngineeringTakushoku UniversityHachioji-shiJapan

Personalised recommendations