A pareto archive evolutionary strategy based radial basis function neural network training algorithm for failure rate prediction in overhead feeders

ABSTRACT

This paper outlines a radial basis function neural network approach to predict the failures in overhead distribution lines of power delivery systems. The RBF networks are trained using historical data. The network sizes and errors are simultaneously minimized using the Pareto Archive Evolutionary Strategy algorithm. Mutation of the network is carried out by invoking an orthogonal least square procedure. The performance of the proposed method was compared to a fuzzy inference approach and with multilayered perceptrons. The results suggest that this approach outperforms the other techniques for the prediction of failure rates.

REFERENCES

• 1: Gupta, S., Pahwa, A., Brown, R. E., Das, S.: A Fuzzy Model for Overhead Distribution Feeders Failure Rates, Proceedings of the 34th North American Power Symposium, Arizona State University, (2002), pp. 248--253.
• 2: Gupta, S., Pahwa, A., Zhou, Y., Brown, R. E., Das, S.: Data Selection To Train A Fuzzy Model For Overhead Distribution Feeders Failure Rates, Proceedings of the ISAP 2003 Conference, Lemnos, Greece, (2003).
• 3: Gupta, S., Pahwa, A., Zhou, Y., Brown, R. E., Das, S.: An Adaptive Fuzzy Model For Overhead Distribution Feeders Failure Rates, Electric Power Components and Systems, in press.
• 4: Broomhead, D. S., Lowe, D.: Multivariate functional interpolation and adaptive networks, Complex Systems, Vol. 2, (1988), pp. 321--355.
• 5: Chen, S., Cowan, C.F.N., Grant, P..M.: Orthogonal least squares learning for radial basis function networks, IEEE Transactions on Neural Networks, Vol. 2, no. 2, (1991), 302--309.
• 6: Jang, J. -S. R., Sun, C.-T.: "Functional equivalence between radial basis function networks and fuzzy inference systems", IEEE Transactions on Neural Networks, Vol. 4, no. 1 (1993) 156--159.
• 7: David E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989
• 8: Whitehead, B. A.: Genetic Evolution of Radial Basis Function Coverage Using Orthogonal Niches, IEEE Transactions on Neural Networks, Vol. 7, no. 6, (Nov 1996), 1525--1528.
• 9: Whitehead, B. A., Choate, T. D.: Cooperative-Competitive Genetic Evolution of Radial Basis Function Centers and Widths for Time Series Prediction, IEEE Transactions on Neural Networks, Vol. 7, no. 4, (July 1996), 869--880.
• 10: Steve A. Billings , Guang L. Zheng, Radial basis function network configuration using genetic algorithms, Neural Networks, v.8 n.6, p.877-890, 1995 [doi>10.1016/0893-6080(95)00029-Y ]
• 11: Alex Alexandridis , Haralambos Sarimveis , George Bafas, A new algorithm for online structure and parameter adaptation of RBF networks, Neural Networks, v.16 n.7, p.1003-1017, September 2003 [doi>10.1016/S0893-6080(03)00052-2]
• 12: Chen, S., Wu, Y., Luk, B. L.: Combined Genetic Algorithm Optimization and Regularized Orthogonal Least Square Learning for Radial Basis Function Networks, IEEE Transactions on Neural Networks, Vol. 10, no. 5, (Sept 1999), 1239--1243.
• 13: González J., Rojas, I., Ortega, J., Pomares, H., Díaz, A.: Multiobjective Evolutionary Optimization of the Size, Shape and Position Parameters of Radial Basin Function Networks for Function Approximation, IEEE Transactions on Neural Networks, Vol. 14, no. 6, (Nov 2003), 1478--1498.
• 14: Fonseca, C.M., Fleming, P.J.: An overview of evolutionary algorithms in multiobjective optimization, Evolutionary Computation, Vol. 3, no. 1 (Spring 1995) 1--16.
• 15: Coello Coello, C.A.: A comprehensive survey of evolutionary-based multiobjective optimization techniques, Knowledge and Information Systems, Vol. 1, no. 3 (Aug 1999) 269--308.
• 16: David A. Van Veldhuizen , Gary B. Lamont, Multiobjective Evolutionary Algorithms: Analyzing the State-of-the-Art, Evolutionary Computation, v.8 n.2, p.125-147, June 2000 [doi>10.1162/106365600568158]
• 17: Zitzler, E., Thiele, L.: Multiobjective evolutionary algorithms: A comparative case study and the strength Pareto approach. IEEE Transactions on Evolutionary Computation 3(4): 257--271 (1999).
• 18: Zitzler, E., Thiele, L., Laumanns, M., Fonseca, C.M., da Fonseca, V.G.: Performance assessment of multiobjective optimizers: An analysis and review, IEEE Transactions on Evolutionary Computation, Vol. 7, no. 2 (Apr. 2003) 117--132.
• 19: Deb, K., Agrawal,S., Pratap, A. and Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6(2): 182--197 (2002).
• 20: Joshua D. Knowles , David W. Corne, Approximating the Nondominated Front Using the Pareto Archived Evolution Strategy, Evolutionary Computation, v.8 n.2, p.149-172, June 2000 [doi>10.1162/106365600568167]
• 21: Knowles, J., Corne, D.: Properties of an adaptive archiving algorithm for storing nondominated vectors, IEEE Transactions on Evolutionary Computation, Vol. 7, no. 2 (Apr. 2003) 100--116.
• 22: Knowles, J., Corne, D.: The Pareto Archived Evolution Strategy: A New Baseline Algorithm for Pareto Multiobjective Optimisation, Proceedings of the 1999 Congress on Evolutionary Computation (1999), 98--105.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Connectionism and neural nets

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Parameter learning

General Terms:
Algorithms

Keywords:
multi-objective optimization, neural networks, pareto archive evolutionary strategy, power system reliability, radial basis function