Density-based clustering and probabilistic classification for integrated transmission-distribution network security state prediction

•Grid security state clustering and classification using density-based clustering and probabilistic classification algorithms.•A novel method for comprehensive dataset development that considers the penetration levels of different DG types and grid contingencies.•An ANFIS-based technique for estimating the critical clearing time of the grid under varying grid parameters.•Performance comparisons of proposed density-based clusterer with non-density based clusterers as well as proposed probabilistic classifier and deterministic classifiers. The proliferation of renewable energy sources (RESs) into the distribution network necessitates the need for the capability to predict the security state of the grid. This paper proposes a density-based clustering and probabilistic classification approach to predict the security state of the modern grid. Firstly, an approach to predict the critical clearing time using the changes in inertia constant and system load is proposed. Secondly, an algorithm for training dataset development from the transient stability responses of the grid considering different operation scenarios is proposed. An expectation-maximization (EM) algorithm using the density-based clustering technique was applied to the dataset to obtain clusters representing the network's security states. Finally, a predictive model was obtained from the labeled dataset using a Naïve-Bayes (NB) probabilistic classifier. The feasibility of this approach is demonstrated using the IEEE 14 bus system. Respectively, an APA and RMSE of 98% and 3.6% were obtained. Also, an MAE of less than 1% was obtained when the proposed model was tested with seven different datasets having a different number of instances. The results show that the proposed technique can predict the security of the integrated transmission-distribution networks considering different DG types, penetration levels, and network disturbances with a high degree of accuracy.