Abnormal Detection to Big Data Using Deep Neural Networks

Abstract

It is difficult to detect the anomalies in big data using traditional methods due to big data has the characteristics of mass and disorder. For the common methods, they divide big data into several small samples, then analyze these divided small samples. However, this manner increases the complexity of segmentation algorithms, moreover, it is difficult to control the risk of data segmentation. To address this, here proposes a neural network approch based on Vapnik risk model. Firstly, the sample data is randomly divided into small data blocks. Then, a neural network learns these divided small sample data blocks. To reduce the risks in the process of data segmentation, the Vapnik risk model is used to supervise data segmentation. Finally, the proposed method is verify on the historical electricity price data of Mountain View, California. The results show that our method is effectiveness.

Anomaly detection of electric energy meter data based on deep network

“…In recent years, with the increasing demand and quality of power consumption by consumers, the power grid infrastructure is gradually replaced by a series of digital systems, and smart grid (SG) emerges as the times require [1]. SG has greatly improved the ability of consumers and energy suppliers (ES) to detect, control and predict electric energy.…”