Summary
In a power network, timely and accurate security assessment has been noted as the major concern of operators in secure operation of the power system. In this paper, power system security region has been constructed by using the retrieval of power system's hidden information. In fact, variables of a power system contain information regarding the status of power system security. Therefore, in order to overcome the complexity and experience‐based selection problems, descriptor variables of the power system security have been extracted by using feature extraction techniques. Also, taking the correlation between the load busses of power system into account, a realistic load modeling has been considered based on the copula modeling technique. These methods have been analyzed to opt the most effective approach, based on the mutual information index, average correlation coefficient index, and generalization error rate. The simulation results for the IEEE 9‐bus, IEEE 118‐bus, and IEEE 300‐bus test systems have demonstrated the effectiveness of the proposed method in the security region reconstruction with high information content (HIC). Rigorous analyses have also shown the interdependency of load correlation towards the complexity of implementation, which as a result, achieving a lower‐dimensional dataset with a lower classification error and a more obvious separation among the security classes is attainable.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.