Advertisement

Neural-Based P-Q Decoupled Control for Doubly Fed Induction Generator in Wind Generation System

  • Moulay Rachid DouiriEmail author
Chapter
Part of the Power Systems book series (POWSYS)

Abstract

This chapter describes an Artificial Neural Network (ANN) approach for active and reactive decoupled control based Direct Power Control (DPC) in Doubly Fed Induction Generator (DFIG) for Wind Generation System (WGS) by using the suitable voltage vectors on the rotor side. To avoid the computational complexity of DPC, we develop a neuronal approach using an individual training technique with fixed weight and supervised networks. For this, the neural system is split into 5 sub-networks namely: reactive and real power measurement sub-networks with dynamic neurons and fixed-weight; reactive calculation and reference real sub-networks with square neurons and fixed-weight; reference stator current computation sub-network with logarithm of sigmoid, tangent sigmoid neurons and supervised weight; reference rotor current computation sub-network with recurrent neurons and fixed-weight; and reference rotor voltage calculation sub-networks with dynamic neurons and fixed-weight. Under transient conditions, and for step changes of the real and the reactive power references, the DFIG is capable of tracking the references with a response time of less than 1 s. This is fast enough for changes made by the power system operator, and for tracking wind speed variations. Thus, the sensorless measurement of the position is effective in controlling P and Q.

References

  1. 1.
    Schmehl R (2017) Airborne wind energy: advances in technology development and research. SpringerGoogle Scholar
  2. 2.
    Ruiz-Cruz R, Sanchez EN, Loukianov A, Ruz-Hernandez JA (2018) Real-time neural inverse optimal control for a wind generator. IEEE Trans Sustain Energy 1(1), Article in Press (2018).  https://doi.org/10.1109/tste.2018.2862628
  3. 3.
    Vieto I, Sun J (2018) Sequence impedance modeling and analysis of Type-III wind turbines. IEEE Trans Energy Convers 33(2):537–545.  https://doi.org/10.1109/tec.2017.2763585CrossRefGoogle Scholar
  4. 4.
    Suppioni VP, Grilo AP, Teixeira JC (2018) Improving network voltage unbalance levels by controlling DFIG wind turbine using a dynamic voltage restorer. Int J Electr Power Energy Syst 96:537–545.  https://doi.org/10.1016/j.ijepes.2017.10.002CrossRefGoogle Scholar
  5. 5.
    Lodhe PC, Munje RK, Date TN (2015) Sliding mode control for direct power regulation of doubly fed induction generator. In: Paper presented at the 11th IEEE India conference: emerging trends and innovation in technology, INDICON.  https://doi.org/10.1109/indicon.2014.7030494
  6. 6.
    Elkington K, Ghandhari M (2013) Non-linear power oscillation damping controllers for doubly fed induction generators in wind farms. IET Renew Power Gener 7(2):172–179.  https://doi.org/10.1049/iet-rpg.2011.0145CrossRefGoogle Scholar
  7. 7.
    Sguarezi Filho AJ, Filho ER (2012) Model-based predictive control applied to the doubly-fed induction generator direct power control. IEEE Trans Sustain Energy 3(3):398–406.  https://doi.org/10.1109/tste.2012.2186834CrossRefGoogle Scholar
  8. 8.
    Guo Y, Gao H, Wu Q, stergaard J, Yu D, Shahidehpour M (2019) Distributed coordinated active and reactive power control of wind farms based on model predictive control. Int J Electr Power Energy Syst 104:78–88.  https://doi.org/10.1016/j.ijepes.2018.06.043CrossRefGoogle Scholar
  9. 9.
    Das S, Subudhi B (2018) \(H^{\infty }\) robust active and reactive power control scheme for a PMSG-based wind energy conversion system. IEEE Trans Energy Convers 33(3):980–990.  https://doi.org/10.1109/TEC.2018.28030673CrossRefGoogle Scholar
  10. 10.
    Darvish Falehi A (2014) Optimal design and analysis of NIOFPID-based direct power control to strengthen DFIG power control. J Dyn Syst Measurement Control 140(9):091001.  https://doi.org/10.1115/1.4039485CrossRefGoogle Scholar
  11. 11.
    Alba E, Mart R (2006) Metaheuristic procedures for training neural networks. SpringerGoogle Scholar
  12. 12.
    Castillo O, Melin P, Kacprzyk J (2018) Fuzzy logic augmentation of neural and optimization algorithms: theoretical aspects and real applications. In: Studies in computational intelligence, vol 749. SpringerGoogle Scholar
  13. 13.
    Ghoudelbourk S, Dib D, Omeiri A (2015) Decoupled control of active and reactive power of a wind turbine based on DFIG and matrix converter. Energy Syst 7(3):483–497.  https://doi.org/10.1007/s12667-015-0177-1CrossRefGoogle Scholar
  14. 14.
    Jerbi L, Krichen L, Ouali A (2009) A fuzzy logic supervisor for active and reactive power control of a variable speed wind energy conversion system associated to a flywheel storage system. Elect Power Syst Res 79(6):919–925.  https://doi.org/10.1016/j.epsr.2008.12.006CrossRefGoogle Scholar
  15. 15.
    Rajendran S, Parvathi Sankar DS, Govindarajan U (2014) Active and reactive power regulation in grid connected wind energy systems with permanent magnet synchronous generator and matrix converter. IET Power Electron 7(3):591–603.  https://doi.org/10.1049/iet-pel.2013.0058CrossRefGoogle Scholar
  16. 16.
    Hore D, Sarma R (2018) Neural network-based improved active and reactive power control of wind-driven double fed induction generator under varying operating conditions. Wind Eng: 0309524X1878040.  https://doi.org/10.1177/0309524x18780402CrossRefGoogle Scholar
  17. 17.
    Gupta N (2018) Tochastic optimal reactive power planning and active power dispatch with large penetration of wind generation. J Renew Sustaina Energy 10(2):025902.  https://doi.org/10.1063/1.5010301CrossRefGoogle Scholar
  18. 18.
    Ackermann T (2012) Wind power in power systems. Wiley.  https://doi.org/10.1002/9781119941842Google Scholar
  19. 19.
    Monroy A, Alvarez-Icaza L (2006) Real-time identification of wind turbine rotor power coefficient. In: 45th IEEE conference on decision and control, pp 3690–3695.  https://doi.org/10.1109/cdc.2006.376895
  20. 20.
    Shamshirband S, Petkovic D, Saboohi H, Anuar NB, Inayat I, Akib S, Cojbaic Z, Nikolic V, Mat Kiah ML, Gani A (2014) Wind turbine power coefficient estimation by soft computing methodologies: comparative study. Energy Convers Manag 81:520–526.  https://doi.org/10.1016/j.enconman.2014.02.055CrossRefGoogle Scholar
  21. 21.
    Abad G, López J, Rodríguez MA, Marroyo L, Iwanski G (2011) Doubly fed induction machine. Wiley.  https://doi.org/10.1002/9781118104965CrossRefGoogle Scholar
  22. 22.
    Peresada S, Tilli A, Tonielli A (2004) Power control of a doubly fed induction machine via output feedback. Control Eng Pract 12(1):41–57.  https://doi.org/10.1016/S0967-0661(02)00285-XCrossRefGoogle Scholar
  23. 23.
    Douiri MR, Belghazi O, Cherkaoui M (2015) Recurrent self-tuning neuro-fuzzy for speed induction motor drive. J Circuits Syst Comput 24(09):1550131.  https://doi.org/10.1142/s0218126615501315CrossRefGoogle Scholar
  24. 24.
    Douiri MR, Belghazi O, Cherkaoui M (2015) Neuro-fuzzy-based auto-tuning proportional integral controller for induction motor drive. Int J Comput Intell Appl 14(03):1550016.  https://doi.org/10.1142/s1469026815500169CrossRefGoogle Scholar
  25. 25.
    Xiong L, Wang J, Mi X, Khan MW (2018) Fractional order sliding mode based direct power control of grid-connected DFIG. IEEE Trans Power Syst 33(3):3087–3096.  https://doi.org/10.1109/tpwrs.2017.2761815CrossRefGoogle Scholar
  26. 26.
    Soares O, Gonalves H, Martins A, Carvalho A (2010) Nonlinear control of the doubly-fed induction generator in wind power systems. Renew Energy 35(8):1662–1670.  https://doi.org/10.1016/j.renene.2009.12.008CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Electrical Engineering, Higher School of TechnologyCadi Ayyad UniversityEssaouiraMorocco

Personalised recommendations