A Review of Machine Learning Approaches to Power System Security and Stability

Abstract

Increasing use of renewable energy sources, liberalized energy markets and most importantly, the integrations of various monitoring, measuring and communication infrastructures into modern power system network offer the opportunity to build a resilient and efficient grid. However, it also brings about various threats of instabilities and security concerns in form of cyberattack, voltage instability, power quality (PQ) disturbance among others to the complex network. The need for efficient methodologies for quicker identification and detection of these problems have always been a priority to energy stakeholders over the years. In recent times, machine learning techniques (MLTs) have proven to be effective in numerous applications including power system studies. In the literature, various MLTs such as artificial neural networks (ANN), Decision Tree (DT), support vector machines (SVM) have been proposed, resulting in effective decision making and control actions in the secured and stable operations of the power system. Given this growing trend, this paper presents a comprehensive review on the most recent studies whereby MLTs were developed for power system security and stability especially in cyberattack detections, PQ disturbance studies and dynamic security assessment studies. The aim is to highlight the methodologies, achievements and more importantly the limitations in the classifier(s) design, dataset and test systems employed in the reviewed publications. A brief review of reinforcement learning (RL) and deep reinforcement learning (DRL) approaches to transient stability assessment is also presented. Finally, we highlighted some challenges and directions for future studies.

Power system events classification using genetic algorithm based feature weighting technique for support vector machine

“…Alimi et al. [ 3 ] presented a review of ML approaches to power systems security solutions. Among the foremost deployed ML tools, SVM has continued to be a dominant model as it gives excellent classification performances [ 7 ].…”

“…However, as conventional ML algorithms are highly susceptible to errors and misclassifications owing to ineffective parameter selections, feature weighting techniques and complicated design procedures, the proposed models have shown various forms of shortcomings. To this end, various feature selection, feature weighting and optimization techniques have been deployed for ML performance optimization, feature selection and weighting procedures [ 3 ]. Ullah et al.…”

“…These tools offer varying contributions in terms of performance and reliability enhancement as some of them are designed and equipped with a variety of outstanding features for efficiency and effectiveness. However, the increasing use of these devices and other cyber presence increases the vulnerabilities and channels through which sabotage, terrorism and intrusion can be perpetuated into the network [ 1 , 2 , 3 ]. The consequences of various high-profile incidences such as the Yemen blackout, Ukrainian power grid blackout, Iran nuclear program attack, etc.…”

“…The consequences of various high-profile incidences such as the Yemen blackout, Ukrainian power grid blackout, Iran nuclear program attack, etc. have shown the devastating effects of intrusion and unwanted events on power infrastructures [ 1 , 3 ]. Also, as modern power system networks spread across wide geographical landscapes, substations and transmission lines that travel over thousands of miles can be physically assaulted by adversaries.…”

Comprehensive Review on Detection and Classification of Power Quality Disturbances in Utility Grid With Renewable Energy Penetration

“…Shashank et al [14] present an account of major computational intelligence-based techniques for addressing the problem of islanding in power grids with renewable energy penetration. Also, a comprehensive review of machine learning-based algorithms has been discussed in [15] for addressing effective decision making and control actions capabilities. Emerging PQ challenges due to renewable energy penetration with control algorithms have been addressed in [16].…”