ABSTRACT

The basic idea deals with detecting the voltage collapse ahead of time to provide the operators a lead time for remedial actions and for possible prevention of blackouts. To detect cases of voltage collapse, pattern recognition in conjunction with power system simulator for engineering (PSSE) program was created and then deployed in Nigeria 330KV integrated power system to develop Regularized Least Squares Classification (RLSC) as well as Classification and Regression Trees (CART) heuristic methods for separating voltage stability cases from unstable voltage cases that would result in response to system contingencies and fault conditions. Dynamic simulation software (PSS/E) is used to simulate voltage stable and unstable cases, these cases are used to train and test the pattern recognition algorithms, simulate several contingencies on the Nigerian 330KV Integrated 52 Bus power System and compile the results in two categories of stable and unstable voltage cases. The results are shown as channel plot of voltage in per unit against time in seconds in figure 4.1 and figure 4.2 for stable and unstable cases. The appendix shows the result after simulation for a particular contingency.