Soft Computing Based Data Mining Applied for Fault Diagnosis and Reliability Problems Evaluation in Power System

Abstract

The objective of this research is to introduce an artificial neural network based solution for the problem of measuring the actual amount of harmonics injected into a power network by an individual nonlinear load. newlineIn this modern era, the demand for electrical and electronics system has increased so much that it has become very hard to do without it. Now a day, a smooth life cannot be expected without electrical energy. Today, electrical and electronic devices are used in every area may it be homes, offices, markets, traffic, education, health, service, defense, communication, sports, industries etc. newlineSoft computing methodologies (involving fuzzy sets, neural networks, genetic algorithms, and rough sets) are most widely applied in the data mining step of the overall KDD process. Fuzzy sets provide a natural framework for the process in dealing with uncertainty. Neural networks and rough sets are widely used for classification and rule generation. Genetic algorithms (GAs) are involved in various optimization and search processes. Other approaches like case based reasoning and decision trees are also widely used to solve data mining problems. KDD Process is interactive and iterative involving, more or less, the following steps: Understanding the application domain, Extracting the target data set, Data cleaning and preprocessing, Data integration, Data reduction and projection, Choosing the function of data mining, Choosing the data mining algorithm(s), Data mining, Interpretation, Using discovered knowledge: includes incorporating this knowledge into the performance system, taking actions based on knowledge. newline