Total views : 236

Voltage Stability Assessment using Artificial Neural Networks

Affiliations

  • Department of EEE, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, India

Abstract


Objectives: To calculate the load flow analysis by using Artificial Neural Networks (ANN) and the Cascade Architecture (CC) with Levenberg-Marquardt (LM) algorithm is used for this proposed system. Methods/Statistical Analysis: Many conventional methods such as Newton-Raphson method, Gauss-Seidel method, AC load flow analysis etc., are used to estimate the load flow analysis of a power system. The major backdrops in using these methods are, using complex non-linear equations, iterative methods and time consuming. To overcome these problems, this paper discusses using Artificial Neural Networks (ANN) which reduces the time consumption in calculating load flow analysis. Findings: In the real-time planning and operation of a power system the major consideration is voltage stability assessment. The voltage instability in a power system will lead to a blackout condition. The continuous increase in load demand, changes in system conditions causes voltage collapse. So the on-line monitoring of voltage stability is a necessary condition. Application/Improvements: The output of the load flow analysis is used to calculate the Index that is used to maintain the system in stable limits.

Keywords

Artificial Neural Networks (ANN), Cascade Architecture (CC), Levenberg-Marquardt (LM), Stability Index, Voltage Stability.

Full Text:

 |  (PDF views: 224)

References


  • Stevenson WD. Elements of power system analysis. 4th ed. McGraw-Hill; 1982.
  • Wood AJ, Wollenberg BF. Power generation operation and control. Newyork: Wiley; 1984.
  • Kumari MS, Maheswarapu S. Enhanced genetic algorithm based computation technique for multi-objective optimal power flow solution. International Journal of Electrical Power and Energy Systems. 2010 Jul; 32(6):736–42.
  • Pandya KS, Joshi SK. A survey of optimal power flow methods. Journal of Theoretical and Applied Information Technology. 2008 Jan; 450–8.
  • Boopathi CS, Venkadesan A, Subhransu SD. Comparison of various learning algorithms for artificial neural network based on-load flow analysis. International Review on Modelling and Simulation. 2014 Apr; 7(2):323–30.
  • Boopathi CS, Dash SS, Selvakumar K, Venkadesan A, Subramani C, Vamsikrishna D. Unit commitment problem with POZ constraint using dynamic programming method. International Review of Electrical Engineering. 2014 Jan; 9(1):218–25.
  • Selvakumar K, Vijayakumar K, Palanisamy R, Karthikeyan D, Santhoshkumar G. SFLA to solve short term thermal unit commitment problem with startup and shutdown ramp limits. IREMOS. 2015 Dec; 8(6):670–8.
  • A brief description of the levenberg-marquardt algorithm implemented. Available from: http://users.ics.forth.gr/~lourakis/levmar/levmar.pdf
  • Fahlman SE, Lebiere C. The Cascade-Correlation Learning Architecture. Advances in Neural Information Processing Systems.1990; 524–32.
  • Jahromi MZ, Bioki MMH, Rashidinejad M, Fadaeinedjad R. Solution to the unit commitment problem using an artificial neural network. Turkish Journal of Electrical Engineering and Computer Sciences. 2013 Jan; 21:198–212.
  • Hsu YY, Yang CC. Fast voltage estimation using an artificial neural network. Electric Power system Research. 1993 May; 27(1):1–9.
  • Paucar VL, Rider MJ. Artificial neural networks for solving the power flow problem in electric power system. Electric Power Systems Research. 2002 Jun; 62(2):139–44.
  • Krishna J, Srivastava L. Counter propagation neural network for solving power flow problem. World Academy of Science, Engineering and Technology International Journal of Electrical, Computer, Energetic, Electronic and Communication Engineering. 2008; 2(3):521–6.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.