energies Review Artificial Intelligence Techniques for Power System Transient Stability Assessment Petar Sarajcev * , Antonijo Kunac , Goran Petrovic and Marin Despalatovic   Citation: Sarajcev,P.; Kunac, A.; Petrovic, G.; Despalatovic, M. Artificial Intelligence Techniques for Power System Transient Stability Assessment. Energies 2022, 15, 507. https://doi.org/10.3390/en15020507 Academic Editors: Tomonobu Senjyu, Alon Kuperman and José Gabriel Oliveira Pinto Received: 9 December 2021 Accepted: 7 January 2022 Published: 11 January 2022 Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affil- iations. Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). Department of Power Engineering, University of Split, FESB, HR21000 Split, Croatia; akunac00@fesb.hr (A.K.); petrovic@fesb.hr (G.P.); despi@fesb.hr (M.D.) * Correspondence: petar.sarajcev@fesb.hr; Tel.: +385-2130-5806 Abstract: The high penetration of renewable energy sources, coupled with decommissioning of con- ventional power plants, leads to the reduction of power system inertia. This has negative repercussions on the transient stability of power systems. The purpose of this paper is to review the state-of-the-art regarding the application of artificial intelligence to the power system transient stability assessment, with a focus on different machine, deep, and reinforcement learning techniques. The review covers data generation processes (from measurements and simulations), data processing pipelines (features engineering, splitting strategy, dimensionality reduction), model building and training (including ensembles and hyperparameter optimization techniques), deployment, and management (with mon- itoring for detecting bias and drift). The review focuses, in particular, on different deep learning models that show promising results on standard benchmark test cases. The final aim of the review is to point out the advantages and disadvantages of different approaches, present current challenges with existing models, and offer a view of the possible future research opportunities. Keywords: power system stability; transient stability assessment; transient stability index; artificial intelligence; machine learning; deep learning 1. Introduction Modern power systems are experiencing fundamental changes that are driven by global warming policies, market forces, and the advancement of technology. They are, at the same time, facing multiple challenges on different fronts. This paper examines one of these important challenges, associated with a transient stability assessment (TSA) of power systems. Namely, power systems of today face a two-pronged challenge, emanating from an increased penetration of renewable energy sources (i.e., wind and photovoltaic power plants, RESs), coupled with a simultaneous decommissioning of the conventional carbon-fired power plants. This shift of balance between RESs and conventional power plants exposes a major downside of the renewables today, which is a reduced system inertia (when less generators with rotating mass are in operation). This reduction of the available rotating mass will have important ramifications on the future security and stability of power system operation [1–3]. With the increased proportion of RESs in the generation mix, the problem of reduced system inertia will only increase. Transient stability disruptions can be the leading causes behind major outages, which are often accompanied by severe economic losses. Hence, these concerns are increasingly drawing the attention of the various stakeholders partaking in the power system operation [4,5]. The dynamic performance of the power system depends on its ability to maintain a desired level of stability and security under various disturbances (e.g., short-circuits, sudden loss of large generation units, etc.). The focus of this paper is on the transient (or large signal rotor angle) stability, which can be considered one of the most important types of power stability phenomena [6]. Figure 1 graphically presents a taxonomy of power system transient stability methods [7]. This taxonomy includes both traditional methods and machine-learning-based methods. However, this review will deal only with different Energies 2022, 15, 507. https://doi.org/10.3390/en15020507 https://www.mdpi.com/journal/energies