ANOMALY DETECTION IN ELECTRICITY CYBER INFRASTRUCTURES

This paper presents a novel anomaly detection methodology for the p otection of electricity critical infrastructures that learns the no rmal behaviour of the system, builds up a profile and detects anomalous operations which deviate from t he profile. This can be used to identify attacks, failures and accidents and it can als o be used to improve state estimation, correct topology errors and inform the operators about pot ential discrepancies between their view of the network and its actual state. This paper will cover two of the anomaly-detecting techniques that we have been developing for electricity ne tworks invariant induction and simulated ants – and a Bayesian methodology for integrat in the output of these detectors. The results presented in this paper demonstrate that this techn ique could make a significant contribution to the security of electricity critical infra structures.