Machine Learning Techniques Applied to On-Line Voltage Stability Assessment: A Review

Electric power systems have become larger, more complex and found to be operating close to their stability limits with small security margin. In such situation, fast and accurate assessment of voltage stability is necessary in order to prevent large-scale blackouts. Due to its ability to learn off-line and produce accurate results on-line, machine learning (ML) techniques i.e., artificial neural networks, decision trees, support vector machines, fuzzy logic and adaptive neuro-fuzzy inference system are widely applied for on-line voltage stability assessment. This paper focuses on providing a clear review of the latest ML techniques employed in on-line voltage stability assessment. For each technique, a brief description is first presented and then a detailed review of the finding published research papers discussed the application of this technique in on-line voltage stability assessment is presented. Based on the conducted review, some discussions and limitations of ML techniques are finally presented.