Bad data detection in state estimation using Decision Tree technique

State estimation is a useful study in every control and dispatching center that its outcome is used for other programs like optimal power flow and load frequency control. State estimation uses network model and a group of measurements to calculate the best estimation of state variables of system. Measurements may get amounts of error in data reading or transmitting. One of important issue of state estimator is bad data detection. A famous method for bad data detection is Chi-square method but it has some defections. In this paper Probabilistic Neural Network (PNN) and Decision Tree (DT) are used to detect bad data detection in state estimation. The proposed method was simulated on IEEE30 buses network and Chi-square, PNN and DT methods are applied to scenarios and results is compared.