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

IET Smart Grid

Ali Dehghantanha¹  Hadis Karimipour²  Farnaz Derakhshan³  Amirreza Jafari³  Farzad Darbandi³  Kim-Kwang Raymond Choo⁴ 

[1] School of Computer Science, University of Guelph;

[2] School of Engineering, University of Guelph;

[3] University of Tabriz;

[4] the University of Texas at San Antonio;

关键词: backpropagation;    self-organising feature maps;    power system transient stability;    smart power grids;    power system security;    feedforward neural nets;    conjugate gradient methods;    power engineering computing;    cyber-physical systems;    smart cyber-physical grids;    deep learning approach;    physical communication layers;    cyber-physical system;    cps;    system monitoring;    smart power grids;    information and communication technologies;    transient stability assessment;    effective tsa;    system operators;    cyber-attacks;    real-time stability condition predictor;    feedforward neural network;    conjugate gradient backpropagation algorithm;    fletcher–reeves updates;    kohonen learning algorithm;    minimum redundancy maximum relevancy algorithm;    ieee 39-bus test system;    real-time stability assessment;   

DOI  :  10.1049/iet-stg.2019.0191

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown