Designing an intelligent decision support system for human-centered utility management automation part 2: design procedure, experimental results, and case study

  • Authors:

  • Alireza Fereidunian;Caro Lucas;Hamid Lesani;Mansooreh Zangiabadi

  • Affiliations:

  • Islamic Azad University, Tehran, Iran and Electrical and Computer Engineering Department, Faculty of Engineering, University of Tehran, Tehran, Iran;Electrical and Computer Engineering Department, Faculty of Engineering, University of Tehran, Tehran, Iran and Intelligent Systems Group, Essential Sciences Research Center, IPM, Tehran, Iran;Electrical and Computer Engineering Department, Faculty of Engineering, University of Tehran, Tehran, Iran;Electrical and Computer Engineering Department, Faculty of Engineering, University of Tehran, Tehran, Iran

  • Venue:
  • ACMOS'05 Proceedings of the 7th WSEAS international conference on Automatic control, modeling and simulation
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a DSS design procedure is presented. The mentioned DSS is a neural network, which is used to estimate the state of a power distribution system loading condition. The effects of different sorts of data distributions, pre-processing, complex conformal mapping, input noise, and error function on the learning and recalling performance of the DSS neural networks are studied. A practical example illustrates how the finally designed DSS can aid decision and control operations in a real standard distribution system, in both normal and abnormal conditions. A mathematical discussion, on a contradiction concerning to the effect of space equalization on DSS learning is brought in an appendix.. The paper includes discussions, practical numerical examples, and results.