Hybrid Neuro-fuzzy Legendre-based Adaptive Control Algorithm for Static Synchronous Series Compensator

Abstract This article presents a novel adaptive non-linear control scheme for a static synchronous series compensator to improve power system stability. The proposed control system synergistically integrates the Legendre polynomial functional neural network, a member of the orthogonal polynomials family, with adaptive neuro-fuzzy Takagi–Sugeno control. The control scheme exploits the online, model-free direct control structure, which reduces the computational complexity, latency, and memory requirements, to make the proposed control strategy highly suitable for real-time implementation. The performance of the proposed control system is validated against different contingencies and operating conditions using non-linear time-domain simulations and different performance indices. The performance of the proposed control system is compared with the adaptive neuro-fuzzy Takagi–Sugeno. The results reveal that the proposed control scheme effectively damps the local and inter-area mode of oscillations.

[1]  Xiaoxin Zhou,et al.  Nonlinear adaptive controller design of SSSC for damping inter-area oscillation , 2010 .

[2]  Nan Zhao,et al.  Adaptive PI Algorithm of SSSC Controller for Power Flow of Power Systems Based on Neural Networks , 2009, 2009 Asia-Pacific Power and Energy Engineering Conference.

[3]  Hongwei Wang,et al.  Tracking Control of Robot Manipulators via Orthogonal Polynomials Neural Network , 2009, ISNN.

[4]  Narayana Prasad Padhy,et al.  Power-system Stability Improvement by PSO Optimized SSSC-based Damping Controller , 2008 .

[5]  En-Bing Lin,et al.  Legendre wavelet method for numerical solutions of partial differential equations , 2010 .

[6]  Goutam Chakraborty,et al.  Nonlinear channel equalization for wireless communication systems using Legendre neural networks , 2009, Signal Process..

[7]  Jun Wang,et al.  Fluctuation prediction of stock market index by Legendre neural network with random time strength function , 2012, Neurocomputing.

[8]  H. F. Wang,et al.  Static synchronous series compensator to damp power system oscillations , 2000 .

[9]  Hong Gu,et al.  Prediction of Chaotic Time Series Based on Neural Network with Legendre Polynomials , 2009, ISNN.

[10]  Santosh Kumar Nanda,et al.  Application of Functional Link Artificial Neural Network for Prediction of Machinery Noise in Opencast Mines , 2011, Adv. Fuzzy Syst..

[11]  R.G. Harley,et al.  Secondary control for a series reactive compensator based on a voltage-source PWM inverter , 2004, IEEE Power Electronics Letters.

[12]  H. F. Wang,et al.  Power system oscillation stability and control by FACTS and ESS — A survey , 2009, 2009 International Conference on Sustainable Power Generation and Supply.

[13]  Ziqian Liu,et al.  Self‐tuning control of electrical machines using gradient descent optimization , 2007 .

[14]  M. Rajaram,et al.  INTELLIGENT CONTROL SCHEMES FOR SSSC BASED DAMPING CONTROLLERS IN MULTI-MACHINE POWER SYSTEMS , 2010 .

[15]  Santosh Kumar Nanda,et al.  Application of Legendre Neural Network for Air Quality Prediction , 2011 .

[16]  Babu Narayanan,et al.  POWER SYSTEM STABILITY AND CONTROL , 2015 .

[17]  Vyacheslav N. Chesnokov.  Fast training analog approximator on the basis of Legendre polynomials , 1997, Defense, Security, and Sensing.