Reinforcement Learning Based PID Control of Wind Energy Conversion Systems

Authors

Abstract

In this paper an adaptive PID controller for Wind Energy Conversion Systems (WECS) has been developed. The
adaptation technique applied to this controller is based on Reinforcement Learning (RL) theory. Nonlinear
characteristics of wind variations as plant input, wind turbine structure and generator operational behavior
demand for high quality adaptive controller to ensure both robust stability and safe performance. Thus, a
reinforcement learning algorithm is used for online tuning of PID coefficients in order to enhance closed loop
system performance. In this study, at start the proposed controller is applied to two pure mathematical plants,
and then the closed loop WECS behavior is discussed in the presence of a major disturbance.

Keywords


[1] K. Ogawa, N.Ymammura, M.Ishda, Study for Small
Size Wind Power Generating System Using
Switched Reluctance Generator, IEEE International
Conference on Industrial Technology, 2006, pp.
1510-1515,
[2] S. Manesis, Fuzzy Logic Control Development in
SCADA Software Frameworks, International
Review of Automatic Control,
[3] F. D. Bianchi, H. De Battista and R. J. Mantz,
“Wind Turbine Control Systems Principles,
Modeling and Gain Scheduling Design” Springer-
Verlag London Limited 2007.
[4] Miguel Angel Mayosky, Gustavo I.E.Cancelo
“Direct Adaptive Control of Wind Energy
Conversion Systems Using Gaussian Networks”
IEEE Trans on Neural Networks,Vol.10, pp.898-
906, July 1999
[5] M.Sedighizade, A.Rezazadeh “Adaptive PID
Control of Wind Energy Conversion Systems Using
RASP1 Mother Wavelet Basis Function Networks”
Proceedings of Academy of Science, Engineering
and Technology Vol.27, pp.269-273. February 2008
[6] M.Sedighizade “Nonlinear Model Identification and
Control of Wind Turbine Using Wavelets"
Proceedings of the 2005 IEEE Conference on
Control Applications Toronto, pp.1057-1062
Canada, 2005
[7] M. Kalantari, M. Sedighizadeh “Adaptive Self
Tuning Control of Wind Energy Conversion
Systems Using Morlet Mother Wavelet Basis
Functions Networks”12th Mediterranean IEEE
Conference on Control and Automation MED’04,
Kusadasi, Turkey, 2004.
[8] X. Zhang, D. XU and Y. LIU, “Predictive
Functional Control of a Doubly Fed Induction
Generator for Variable Speed Wind Turbines,” 5th
World Congress on Intelligent Control and
Automation, June 15- 19, Hangzhou. P.R. China,
2004.
[9] Damien Ernst,et al ”Power System Stability Control:
Reinforcement Learning Framework”IEEE
Transaction on Power System,Vol.19,No.1,February
2004
[10] R. Bellman, ”Dynamic Programming”.
Princeton, NJ: Princeton Univ. Press, 1957.
[11] P.Puleston”Control strategies for wind energy
conversion systems”Ph.D.dissertation,Univ.La Plata.
Argentina 1997