Development of an Ensemble Decision Tree-Based Power System Dynamic Security State Predictor

Abstract

Real-time assessment and prediction of dynamic security plays an important role in power systems operation and control. Analysis of the current operating state and prediction of plausible future insecurity is crucial for real-time decision-making and implementation of necessary control strategies to ensure secure operation of bulk power systems. On-line security assessment demands low complexity and computational time. The traditional methods of assessment of dynamic security of electric power systems often prove to be inadequate for online and real-time conditions due to their high complexity and long computation time. This article proposes a pattern recognition approach to dynamic security analysis for large and complex power systems using ensemble decision tree to form reliable decision rules for fast and accurate prediction of power system's operating states in a real-time and on-line environment. An ensemble security predictor (ENSP) was developed and trained to act as “dynamic security state predictor” to predict and classify power system's dynamic operating states into secure, insecure, and intermediate transitional classes. Two different case studies were performed on IEEE 118-bus and IEEE 300-bus systems to evaluate and compare the performance of the proposed method on systems of varying size and complexity. While prediction accuracy of some of the single-learner classifiers decreased considerably when implemented on a large sized system, the performance of ENSP declined marginally, and the results were acceptable for very large sized systems.