Detecting cyberattacks on electrical storage systems through neural network based anomaly detection algorithm

HIGHLIGHTS

SUMMARY

The main contribution of this work is the development of an anomaly detection algorithm based on a neural_network autoencoder. Ref shows a contextual anomaly detection method based on an artificial neural_network and explains the use of this method to discover voltage control manipulation in the low voltage distribution grid. A deep learning scheme composed of Long Short Term Memory-Stacked Autoencoders and Convolutional Neural_Network (CNN-SAE) followed by a softmax activation layer has been used for fault detection in a wind turbine in Ref. Three different autoencoding schemes (multilayer perceptron, convolutional, and long-short . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or E-mail:

If you don't have an account, you can create one here.