DEEP LEARNING DETECTION OF ELECTRICITY THEFT CYBER-ATTACKS IN RENEWABLE DISTRIBUTED GENERATION

The focuses on detecting electricity theft cyber-attacks in the consumption domain, this paper investigates electricity thefts at the distributed generation (DG) domain. In this attack, malicious customers hack into the smart meters monitoring their renewable-based DG units and manipulate their readings to claim higher supplied energy to the grid and hence falsely overcharge the utility company. Deep machine learning is investigated to detect such a malicious behaviour. A set of cyber-attack functions were introduced to manipulate the integrity of the readings of the injected power from the DG units in order to falsely overcharge the electric utility company. It integrating various data from the DG smart meters, meteorological reports, and SCADA metering points in the training of a deep convolutional-Artificial Neural Network is performed and analyse the cyber-theft on electrical data. The machine learning and feed neural network algorithm of Artificial Neural Network is applied and find the cyber-attack in benign and malicious Electrical data and predict the data. The prediction result is based on in the form of accuracy.