Comparison of shuffled frog leaping algorithm and PSO in data clustering with constraint for grouping voltage control areas in power systems

摘要

Voltage Control Areas (VCAs) play an important role in voltage stability assessment and control. Since it isnimpossible to detect VCAs in real time during appearance of emergency cases for large-scale power systems,nit is a reasonable solution to train and employ an artificial intelligent system (AIS), for on-line predicting ofnVCAs. However, at different emergency and alert cases, there are various VCAs for power system.nClustering the data of Participation Factors (PFs) of all studied cases into a finite number of groups wouldnlead to a more accurate ANN-based online VCA identifier. Each cluster has a representative center that is thencritical VCA corresponding to all contingencies and load stresses which would lead to the same cases as thenmembers of that cluster. In this paper a novel data clusteringmethod based on shuffled frog leaping algorithmn(SFLA) is presented for this purpose. In the first part of present study the general application of SFLA in datanclustering is compared with PSO as the most popular Memetic Algorithm (MA), to demonstrate the validitynof proposed clustering method. Consequently, as the clustering of VCAs is a problem with linear equalitynconstraint, the compatibility of SFLA for solving under constraint clustering problems and its priority tonPSO from this point of view, are shown in this study. Numerical results are presented at the first part for threenstandard test data sets and at the second part for IEEE 118-bus test system. Copyright#2010 JohnWiley &nSons, Ltd.