Anomaly Detection in Smart Grid using Wavelet Transform and Artificial Neural Network

This paper presents a scheme for detecting anomalous power consumption patterns attack using wavelet transform and artificial neural network for smart grid. The main procedure of the proposed algorithm consists of following steps: I) Creating normal and anomaly patterns of power consumption to train the proposed method. II) Wavelet transform is applied on power consumption patterns to extract features. III) Training artificial neural network with extracted features as an input. IV) Launching the trained artificial neural network to detect anomalous power consumption attack based on a threshold. In the simulations, the proposed method can detect anomalous power consumption attack with 74.25% accuracy in the worst case scenario. Also, four levels of wavelet transform make different features, so the proposed method has different performance. Keywords—Artificial neural network; wavelet transform; anomalous power consumption attack; smart grid; computer network security.