Electric Power Research Institute Incorporated

A B Kumar

Ali Ipakchi

Gerald W Cauley

Vladimir Brandwajn

Dynamic security analysis of a power system is divided into several diverse sub-problems, including sub-problems that may be analyzed using artificial intelligence ('AI') technology. A rule-based topological analysis procedure distinguishes between outage contingencies that are definitely safe or harmless to the integrity of the power system, and potentially severe outage contingencies that are harmful to the power system. Initial outage selection correctly relates the state of the power system before the analysis. By methodically and automatically identifying potentially severe outages, the need for extensive off-line studies based on time domain simulations is avoided, thus promoting computational efficiency. This methodology further provides automatic detection of critical interfaces, e.g., flows through which may significantly impact the post-contingency state of the power system.

Rule-based procedure for automatic selection of contingencies in

Analysis and evaluation of outage effects on the dynamic security of power systems is made with a neural network using composite contingency severity indices. A preferably small number of indices describes the power system characteristics immediately post-contingency. These indices are then used as classifiers of the safety of the power system. Using the values of the severity indices, an artificial neural network distinguishes between safe, stable contingencies and potentially unstable contingencies. The severity of the contingency is evaluated based upon a relatively small fixed set of severity indices that are calculated based on a partial time domain simulation. Because a fixed set of severity indices is used, the size and architecture of the neural network is problem independent, thus permitting its use with large scale power systems. Further, the amount of required time domain simulation for the selection of the potentially harmful unstable contingencies is reduced by screening out benign, stable appearing contingencies. The network is trained off-line using training cases that concentrate around the security boundary to reduce the number of cases required to train the neural network.

Growing community of inventors

Cupertino, CA, United States of America

A B Kumar