Real-time stability assessment in smart cyber-physical grids: a deep learning approach

• Published in: IET Smart Grid Vol. 3; no. 4; pp. 454 - 461
• Main Authors: Darbandi, Farzad, Jafari, Amirreza, Karimipour, Hadis, Dehghantanha, Ali, Derakhshan, Farnaz, Raymond Choo, Kim-Kwang
• Format: Journal Article
• Language: English
• Published: Durham The Institution of Engineering and Technology 01.08.2020; John Wiley & Sons, Inc; Wiley
• Subjects: Accuracy; Algorithms; Artificial neural networks; B0290F Interpolation and function approximation (numerical analysis); B8110C Power system control; Back propagation networks; backpropagation; C4130 Interpolation and function approximation (numerical analysis); C5290 Neural computing techniques; C7410B Power engineering computing; Case studies; conjugate gradient backpropagation algorithm; conjugate gradient methods; Control stability; Control systems; CPS; cyber-attacks; cyber-physical system; cyber-physical systems; Deep learning; deep learning approach; effective TSA; Feature selection; feedforward neural nets; feedforward neural network; Fletcher–Reeves updates; IEEE 39‐bus test system; information and communication technologies; Kohonen learning algorithm; Machine learning; Methods; minimum redundancy maximum relevancy algorithm; Monitoring; Neural networks; Pattern recognition; Performance evaluation; physical communication layers; power engineering computing; power system security; power system transient stability; real-time stability assessment; real-time stability condition predictor; Redundancy; self-organising feature maps; smart cyber-physical grids; Smart grid; smart power grids; Special Issue: Machine Learning in Power Systems; system monitoring; system operators; Transient stability; transient stability assessment; Wavelet transforms; conjugate gradient methods; cyber-attacks; real-time stability assessment; CPS; power system transient stability; smart power grids; effective TSA; Fletcher–Reeves updates; Kohonen learning algorithm; self-organising feature maps; IEEE 39-bus test system; real-time stability condition predictor; smart cyber-physical grids; minimum redundancy maximum relevancy algorithm; physical communication layers; system operators; cyber-physical system; power engineering computing; power system security; transient stability assessment; cyber-physical systems; conjugate gradient backpropagation algorithm; feedforward neural network; backpropagation; deep learning approach; system monitoring; information and communication technologies; feedforward neural nets
• ISSN: 2515-2947; 2515-2947
• DOI: 10.1049/iet-stg.2019.0191

The increasing coupling between the physical and communication layers in the cyber-physical system (CPS) brings up new challenges in system monitoring and control. Smart power grids with the integration of information and communication technologies are one of the most important types of CPS. Proper monitoring and control of the smart grid are highly dependent on the transient stability assessment (TSA). Effective TSA can provide system operators with insightful information on stability statuses and causes under various contingencies and cyber-attacks. In this study, a real-time stability condition predictor based on a feedforward neural network is proposed. The conjugate gradient backpropagation algorithm and Fletcher–Reeves updates are used for training, and the Kohonen learning algorithm is utilised to improve the learning process. By real-time assessment of the network features based on the minimum redundancy maximum relevancy algorithm, the proposed method can successfully predict transient stability and out of step conditions for the network and generators, respectively. Simulation results on the IEEE 39-bus test system indicate the superiority of the proposed method in terms of accuracy, precision, false positive rate, and true positive rate.