IEEE Access · 2018 · 43 citations · 19 references
ComputingComputer ScienceElectrical EngineeringMachine LearningStochastic ModelingUncertainty QuantificationFailure AnalysisPower System ReliabilityPower SystemsProbabilistic Machine LearningReliability ModelingCascading Failure ModelingElectrical Power SystemsFailure PredictionOperating ConditionsPower System Reliability AnalysisPower System Reliability ModelingReliability PredictionSystem Reliability
Considering the engineering characteristics of power systems and the concept of machine learning, a model named ``ITEPV”was proposed in this paper to investigate the mechanism of cascading failures in power systems. This model tries to simulate a large number of possible cascading failure chains as ``experience”, and then to predict the cascading failure propagation with the highest possibility obtained from the ``experience”. In order to get the prediction result, the uncertainty of loads and generations is considered to generate numerous random operating conditions, and then implementing ``N - 1”for each operating condition to obtain the ``experience”. Based on the ``experience”, a Bayes network can be established to predict the cascading failure propagation. The ``ITEPV”model was tested on the IEEE Reliability Test System-1996 (RTS-96), and the results were validated by employing different sample sizes of random operating conditions. From this paper, it can be concluded that employing machine learning into electrical engineering not only simplifies the complicated issue but also makes the results more accurate.
19
Pattern Recognition and Machine Learning
Journal of Electronic Imaging · 2007 · 22.1K citations
Pattern Recognition and Machine Learning
Kybernetes · 2007 · 8.4K citations
C. Grigg, P. Wong, P. F. Albrecht et al. · IEEE Transactions on Power Systems · 1999 · 3.1K citations
Engineering, Electrical Engineering, Systems Engineering +15
Ross Baldick, Badrul Chowdhury, Ian Dobson et al. · 2008 · 323 citations