Using LSTM Networks to Identify False Data of Smart Terminals in the Smart Grid

Abstract

Smart grid is the next generation of power system which contains a large number of smart terminals. One of the most import issues in smart grid is to provide reliable communication between smart terminals and master station to ensure system security and stability. When implementing security protection method for smart grid master station, there are several challenges such as heterogeneity within the system that need to be addressed. In this paper, we propose a novel approach, which utilizing machine learning algorithms in the gateways of master station to help secure the the smart grid. We use Long Short-Term (LSTM) network in the master station gateways to detect abnormal data sent from smart terminals. We evaluate this approach and the results demonstrate that the method can effectively identify the illegal data and improve the security of smart grid.