Design static VAR compensator controller using artificial neural network optimized by modify Grey Wolf Optimization

This paper introduce a novel design of the static VAR compensator (SVC) controller for damping power system oscillations. A multi layer neural network model tuned by Grey Wolf Optimization algorithm (GWO) is investigated and presented. GWO search algorithm is used to optimized all the connection of weights and biases for the artificial neural network. The proposed approach depends up on the expected wide range of the effective operating conditions of the SVC. Modification is introduced in the proposed optimizer exploration-exploitation balance to enhance its rate of convergence over the original algorithm. The robustness of the proposed controller successfully testing for damping oscillations of two-axis nonlinear single machine infinite bus system. A comparative study for the controller based the classical PI controller have been presented.

[1]  Al-Attar Ali Mohamed,et al.  Grey Wolf Optimization for Multi Input Multi Output System , 2015 .

[2]  G. Panda,et al.  Design and analysis of SSSC-based supplementary damping controller , 2010, Simul. Model. Pract. Theory.

[3]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[4]  H. H. Happ,et al.  Power System Control and Stability , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[6]  Onur Seref,et al.  Modeling and Solving Real-Life Global Optimization Problems with Meta-heuristic Methods , 2009 .

[7]  K. Sabitha,et al.  Enhancement of ATC With Facts Devices using Real-Code Genetic Algorithm , 2014 .

[8]  Ieee Standards Board.  IEEE recommended practice for excitation system models for power system stability studies , 1992 .

[9]  Swagatam Das,et al.  An improved particle swarm optimizer with difference mean based perturbation , 2014, Neurocomputing.

[10]  Biplab Bhattacharyya,et al.  Fuzzy based evolutionary algorithm for reactive power optimization with FACTS devices , 2014 .

[11]  Manuel López-Ibáñez,et al.  Ant colony optimization , 2010, GECCO '10.

[12]  Wu Husheng,et al.  A uncultivated wolf pack algorithm for high-dimensional functions and its application in parameters optimization of PID controller , 2014, 2014 IEEE Congress on Evolutionary Computation (CEC).

[13]  Barbara Webb,et al.  Swarm Intelligence: From Natural to Artificial Systems , 2002, Connect. Sci..

[14]  L. Coelho.  A quantum particle swarm optimizer with chaotic mutation operator , 2008 .

[15]  Yixiong Feng,et al.  Exploratory study of sorting particle swarm optimizer for multiobjective design optimization , 2010, Math. Comput. Model..

[16]  S. Panda.  Multi-objective PID controller tuning for a FACTS-based damping stabilizer using Non-dominated Sorting Genetic Algorithm-II , 2011 .

[17]  Ajith Abraham,et al.  Erratum to "On convergence of the multi-objective particle swarm optimizers" [Inform. Sci 181 (2011) 1411-1425] , 2011, Inf. Sci..

[18]  Peter W. Sauer,et al.  Power System Dynamics and Stability , 1997 .

[19]  Kwok-Wo Wong,et al.  A novel particle swarm optimizer with time-delay , 2007, Appl. Math. Comput..

[20]  Jiangye Yuan,et al.  A modified particle swarm optimizer with dynamic adaptation , 2007, Appl. Math. Comput..

[21]  K. Ellithy,et al.  A hybrid neuro-fuzzy static var compensator stabilizer for power system damping improvement in the presence of load parameters uncertainty , 2000 .

[22]  S. P. Singh,et al.  Fuzzy neural network based voltage stability evaluation of power systems with SVC , 2008, Appl. Soft Comput..

[23]  G. El-Saady,et al.  Damping power systems oscillations using FACTS combinations , 2004, 39th International Universities Power Engineering Conference, 2004. UPEC 2004..

[24]  Husheng Wu,et al.  A uncultivated wolf pack algorithm for high-dimensional functions and its application in parameters optimization of PID controller , 2014, IEEE Congress on Evolutionary Computation.

[25]  A. Rezaee Jordehi,et al.  Brainstorm optimisation algorithm (BSOA): An efficient algorithm for finding optimal location and setting of FACTS devices in electric power systems , 2015 .