Machine Learning to Ensure Data Integrity in Power System Topological Network Database

Abstract

Operational and planning modules of energy systems heavily depend on the information of the underlying topological and electric parameters, which are often kept in database within the operation centre. Therefore, these operational and planning modules are vulnerable to cyber anomalies due to accidental or deliberate changes in the power system database model. To validate, we have demonstrated the impact of cyber-anomalies on the database model used for operation of energy systems. To counter these cyber-anomalies, we have proposed a defence mechanism based on widely accepted classification techniques to identify the abnormal class of anomalies. In this study, we find that our proposed method based on multilayer perceptron (MLP), which is a special class of feedforward artificial neural network (ANN), outperforms other exiting techniques. The proposed method is validated using IEEE 33-bus and 24-bus reliability test system and analysed using ten different datasets to show the effectiveness of the proposed method in securing the Optimal Power Flow (OPF) module against data integrity anomalies. This paper highlights that the proposed machine learning-based anomaly detection technique successfully identifies the energy database manipulation at a high detection rate allowing only few false alarms.