Application of a simple Estimation of Distribution Algorithm to power system controller design

Estimation of Distribution Algorithms (EDAs) are a class of Evolutionary Algorithms in which the explicit representation of the population is replaced with a probability distribution where new candidate solutions are obtained by sampling this distribution. In lieu of crossover, the probability distribution vector is updated using candidate solutions that have the highest fitness. New sample solutions are generated from the updated probability distribution vector and another generation begins. This process is repeated until some convergence criteria are met. In this paper, one of the simplest version of EDAs known as Population-Based incremental Learning (PBIL) is considered. The standard PBIL is modified by adapting its learning rate according to the generation. The proposed Adaptive PBIL (APBIL) is used to optimally tune the parameters of a power system stabilizer (PSS). The effectiveness of the Adaptive PBIL is demonstrated by comparing the APBIL-PSS with the PBIL-PSS and the conventional PSS (CPSS). Simulation results show that both the PBIL-PSS and the APBIL-PSS provide more damping to the system than the CPSS. However, the APBIL-PSS gives a better performance than the standard PBIL-PSS.

[1]  P. Kundur,et al.  Application of Power System Stabilizers for Enhancement of Overall System Stability , 1989, IEEE Power Engineering Review.

[2]  Shumeet Baluja,et al.  A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning , 1994 .

[3]  Reza Rastegar,et al.  The Population-Based Incremental Learning Algorithm converges to local optima , 2006, Neurocomputing.

[4]  Rich Caruana,et al.  Removing the Genetics from the Standard Genetic Algorithm , 1995, ICML.

[5]  Chi-Jui Wu,et al.  Damping of power system oscillations with output feedback and strip eigenvalue assignment , 1995 .

[6]  A.A. Abido,et al.  Particle swarm optimization for multimachine power system stabilizer design , 2001, 2001 Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.01CH37262).

[7]  O. P. Malik,et al.  An adaptive power system stabilizer based on recurrent neural networks , 1997 .

[8]  M. A. Abido,et al.  Simultaneous stabilization of multimachine power systems via genetic algorithms , 1999 .

[9]  Hiroshi Sasaki,et al.  SYNTHESIS OF TWO-INPUT PSS BASED ON THE H∞ CONTROL THEORY , 1998 .

[10]  Jie Yao,et al.  Bi-Objective Multipopulation Genetic Algorithm for Multimodal Function Optimization , 2010, IEEE Transactions on Evolutionary Computation.

[11]  P. Kundur,et al.  Power system stability and control , 1994 .

[12]  Ganesh K. Venayagamoorthy,et al.  Comparative Study of Population Based Techniques for Power System Stabilizer Design , 2009, 2009 15th International Conference on Intelligent System Applications to Power Systems.

[13]  Lawrence. Davis,et al.  Handbook Of Genetic Algorithms , 1990 .

[14]  D. E. Goldberg,et al.  Genetic Algorithms in Search, Optimization & Machine Learning , 1989 .

[15]  K.A. Folly.  Design of power system stabilizer: a comparison between genetic algorithms (GAs) and population-based incremental learning (PBIL) , 2006, 2006 IEEE Power Engineering Society General Meeting.

[16]  Alberto Suárez,et al.  Hybrid Approaches and Dimensionality Reduction for Portfolio Selection with Cardinality Constraints , 2010, IEEE Computational Intelligence Magazine.