Bad Data Detection and Identification Using Neural Network-Based Reduced Model State Estimator

This paper explores the capability of the reduced model artificial neural network-based power system state estimator to accurately identify single and multiple bad data. This state estimator uses fewer measurements than conventional state estimators and does not require network observability analysis. A comparison of the single bad data detection and identification between the proposed state estimator and the Weighted Least Squares state estimator on GE 6-bus and IEEE 14-bus power systems is provided. The results show that the proposed state estimator is more accurate and faster than the WLS state estimator. Furthermore, the proposed methodology is a great alternative to the conventional techniques and is therefore well suited for smart grid applications.