Optimal design of power system stabilizer based on multilayer perceptron neural networks using bee’s algorithm

Y. Akamine *

Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, Tokyo, Japan

Abstract

The modern power networks are very big and have nonlinear characteristics. In these big and complicated networks, many problems and abnormal conditions may be occurring. Power system stabilizers or PSS tools are applied to produce additional control efforts for the excitation system to remove or enfeeble the inferior frequency power system fluctuation. There are many techniques for PSS control that have some shortcomings and deficiencies. To overcome the shortcoming and defect of the conventional techniques, in this paper we proposed an optimal neural network based technique using bee’s algorithm. The suggested technique is applied in a power network to produce additional control effort signals to the excitation section. The proposed method has two main parts: The controller part and the optimization part. In the controller part, we proposed MLP neural network as a controller. The MLP neural network has good capability in control tasks. In the MLP neural networks, the number of hidden layers and relative neuron numbers have a high effect on its performance. For this purpose in the optimization part, we used the bee’s algorithm for finding the optimal number of these parameters. To evaluate the performance of the suggested technique, some computer simulations are done and the obtained results show that the suggested method has good performance.

Keywords

MLP, PSS, Optimization, Control, Excitation

Digital Object Identifier (DOI)

https://doi.org/10.21833/AEEE.2019.09.002

Article history

Received 2 April 2019, Received in revised form 20 July 2019, Accepted 21 July 2019

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Akamine Y (2019). Optimal design of power system stabilizer based on multilayer perceptron neural networks using bee’s algorithm. Annals of Electrical and Electronic Engineering, 2(9): 6-11

References (13)

  1. Baykasoglu A, Ozbakir L, and Tapkan P (2009). The bees algorithm for workload balancing in examination job assignment. European Journal of Industrial Engineering, 3(4): 424-435. https://doi.org/10.1504/EJIE.2009.027035   [Google Scholar]
  2. Haykin S (1994). Neural networks: A comprehensive foundation. Prentice Hall PTR, USA.   [Google Scholar]
  3. Kalteh AA, Zarbakhsh P, Jirabadi M, and Addeh J (2013). A research about breast cancer detection using different neural networks and K-MICA algorithm. Journal of Cancer Research and Therapeutics, 9(3): 456. https://doi.org/10.4103/0973-1482.119350   [Google Scholar]
  4. Liu Y, Niu B, and Luo Y (2015). Hybrid learning particle swarm optimizer with genetic disturbance. Neurocomputing, 151: 1237-1247. https://doi.org/10.1016/j.neucom.2014.03.081   [Google Scholar]
  5. Mernik M, Liu SH, Karaboga D, and Črepinšek M (2015). On clarifying misconceptions when comparing variants of the artificial bee colony algorithm by offering a new implementation. Information Sciences, 291: 115-127. https://doi.org/10.1016/j.ins.2014.08.040   [Google Scholar]
  6. Nechadi E, Harmas MN, Hamzaoui A, and Essounbouli N (2012). Type-2 fuzzy based adaptive synergetic power system control. Electric Power Systems Research, 88: 9-15. https://doi.org/10.1016/j.epsr.2012.01.009   [Google Scholar]
  7. Park YM, Choi MS, and Lee KY (1996). A neural network-based power system stabilizer using power flow characteristics. IEEE Transactions on Energy Conversion, 11(2): 435-441. https://doi.org/10.1109/60.507657   [Google Scholar]
  8. Pham DT, Ghanbarzadeh A, Koç E, Otri S, Rahim S, and Zaidi M (2006). The bees algorithm—A novel tool for complex optimisation problems. In the IPROMS 2006 Proceeding 2nd International Virtual Conference on Intelligent Production Machines and Systems: 454-459. https://doi.org/10.1016/B978-008045157-2/50081-X   [Google Scholar]
  9. Sun Z, Wang N, Srinivasan D, and Bi Y (2014). Optimal tunning of type-2 fuzzy logic power system stabilizer based on differential evolution algorithm. International Journal of Electrical Power & Energy Systems, 62: 19-28. https://doi.org/10.1016/j.ijepes.2014.04.022   [Google Scholar]
  10. Supriyadi AC, Takano H, Murata J, and Goda T (2014). Adaptive robust PSS to enhance stabilization of interconnected power systems with high renewable energy penetration. Renewable energy, 63: 767-774. https://doi.org/10.1016/j.renene.2013.09.044   [Google Scholar]
  11. Wen S, Huang T, Zeng Z, Chen, Y, and Li P (2015). Circuit design and exponential stabilization of memristive neural networks. Neural Networks, 63: 48-56. https://doi.org/10.1016/j.neunet.2014.10.011   [Google Scholar]
  12. Zhang Y, Li Y, Sun J, and Ji J (2015). Estimates on compressed neural networks regression. Neural Networks, 63: 10-17. https://doi.org/10.1016/j.neunet.2014.10.008   [Google Scholar]
  13. Zhao ZS, Feng X, Lin YY, Wei F, Wang SK, Xiao TL, Cao MY, and Hou ZG (2015). Evolved neural network ensemble by multiple heterogeneous swarm intelligence. Neurocomputing, 149: 29-38. https://doi.org/10.1016/j.neucom.2013.12.062   [Google Scholar]