Neural Network Based Early Warning System for an Emerging Blackout in Smart Grid Power Networks

Gupta, Sandeep K.; Kazi, Faruk; Wagh, Sushama; Kambli, Ruta

doi:10.1007/978-3-319-11227-5_16

Cited by 33 publications

(26 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figure 1 at prediction centre, a scaled conjugate gradient (SCG) feedforward supervised ANN is used to train prediction model using historical blackout data (Gupta et al, 2015). Once ANN trained, it classify whether power flow in the grid is normal or blackout may happen by simply giving online input data to ANN model (Gupta et al, 2015).…”

Section: Probabilistic Data From Gaussian Distributionmentioning

confidence: 99%

“…In this situation, higher order moments are required to analyse dynamical changes in load flow. The higher order moments have been used in Gupta et al (2015) to extract the dynamics of cascading link failure. Approximately 45 complete blackout scenario has analysed with probabilistic model and used as historical database.…”

Section: Probabilistic Data From Gaussian Distributionmentioning

confidence: 99%

“…Once ANN trained, it classify whether power flow in the grid is normal or blackout may happen by simply giving online input data to ANN model (Gupta et al, 2015).…”

Section: Probabilistic Data From Gaussian Distributionmentioning

confidence: 99%

“…Prediction was based on offline analysis of past blackout events and online data which is assumed to be available from WAMS. The present paper uses early warning, generated from Gupta et al (2015), as a precursor of blackout prediction. Based on early warning, a mitigation plan is proposed to protect the grid against blackout.…”

Section: Introductionmentioning

confidence: 99%

“…A neural network (NN)-based early warning system for blackout prediction has been proposed in our earlier attempt (Gupta et al, 2015) where, a machine learning (ML) technique along with probabilistic model (Gupta et al, 2014) was used for prediction of emerging blackout. Prediction was based on offline analysis of past blackout events and online data which is assumed to be available from WAMS.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Augmenting WAMPAC with machine learning tools for early warning and mitigation of blackout events

Gupta

Kazi²,

Wagh³

et al. 2018

IJHT

Self Cite

View full text Add to dashboard Cite

Abstract:The development of phasor measurement unit (PMU) in the power network and availability of real-time communication in wide area monitoring system has enabled the proactive blackout prediction and possibility of mitigation against blackout events. The objective of this paper is to provide a wide area monitoring protection and control (WAMPAC) model which can predict cascade failure and minimise the risk of massive blackout. The proposed model is a combination of simulation and a measurement-based approach. The key contribution of this paper is a topological analysis of grid using graph theoretic approach, blackout prediction using machine learning technique and the mitigation plan against blackout by combining graph theoretic approach and change in voltage phase angle at different buses. The proposed methodology is validated using IEEE 30 bus system.

show abstract

Section: Probabilistic Data From Gaussian Distributionmentioning

confidence: 99%

Section: Probabilistic Data From Gaussian Distributionmentioning

confidence: 99%

“…Once ANN trained, it classify whether power flow in the grid is normal or blackout may happen by simply giving online input data to ANN model (Gupta et al, 2015).…”

Section: Probabilistic Data From Gaussian Distributionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations