A Survey on Dynamic Security Assessment of Power Systems Using Machine Learning Techniques

摘要

The efforts to modernize current electric grids has led to the emergence of Smart Grid paradigm throughout the world. Large-scale penetration of renewable generation has given rise to additional technical challenges arising from increased variability and uncertainty. Amidst such new challenges and new technological advancements, the current electric grids can be no longer allowed to operate as they did in the past. There is an urgent need to improve grid security more than ever before. Traditional implementations of security assessment rely only on steady-state methods and hence, do not capture the system's dynamic status. On the other hand, an implementation of dynamic security assessment (DSA) would strive to assess both, the static and dynamic system states. This paper presents a discussion on various aspects of DSA and the role of machine learning (ML) techniques in enabling real-time DSA implementations.