Dynamic voltage stability prediction of power systems by a new feature selection technique and probabilistic neural network

摘要: With continued increase in the electrical energy demand and tendency towards maximizing economic benefits power transmission system, especially liberalized electricity markets, real-time voltage security analysis has become a growing concern electric utilities. However, static methods, such as flow based have difficulty evaluating stability some feasible region boundaries may not be correctly analyzed by these methods due to use of simple models for system components. On other hand, dynamic modeling evaluation are complex, expensive, time consuming. In this paper, new feature selection technique combined with probabilistic neural network (PNN) is proposed purpose. A major difference our paper previous research works area that proposes prediction, while usually focus on evaluation. The prediction method examined IEEE 14-bus New England 39-bus test systems effectiveness demonstrated. Also, effect different load models, branch contingencies, generator contingencies evaluated. Another advantage it can used varied topologies configurations system. Copyright © 2010 John Wiley & Sons, Ltd.