Abstract:

In order to locate the leakage fault location of low-voltage electrical lines, cut off the power supply of electrical lines, and ensure the safety and reliability of the power supply network. This paper proposes an electrical line leakage fault detection system and to detect the electric city theft in a particular area. In which the customer and government is facing the quality, increasing generation load, affecting the overall economy of the government etc. For lack of technology and data, insecurity, the complexity associated with traditional methods, untimeliness, and general human cost, electricity assets monitoring, and management have remained a big problem in many developing countries. By using proposed system, it can significantly reduce this loss by analysing the electric reduce this loss by analysing the electricity consumption. In this paper by using machine learning technique employing DBSCAN, K-MEANS Algorithm for detection. The electricity theft approach in a particular area by using the graphs and Traditional Grid (Pie table) for the prediction. The data collected is analysed and pre-processed before it is used for model training and testing. This study also provides the guide to various considerations when adopting this technology in terms of the choice of machine learning architecture, adequate training samples over multiple fault characteristics, effects of data augmentation, and balancing of intra-class heterogeneity.

Description:

DBSCAN, Electricity Theft, Fault detection, K-Means, Machine Learning