Support Vector Machine Based Approach for State Estimation of Iraqi Super Grid Network

The correct assessment of network topology and system operating state in the presence of corrupted data is one of the most challenging problems during real-time power system monitoring, particularly when both topological and analogical errors are considered. This paper deals with Support Vector Machine method for state estimation problem in power systems including estimation and detection, which can help to improve Iraqi super grid electrical power network state estimation. The results of state estimation using the Support Vector Machine (SVM) and the conventional weighted Least Squares (WLS) State Estimator on basis of time, accuracy and robustness, particularly when both bad data and topological errors are to be considered. It has been established that the SVM based models provide results much faster, and work well even including single and multiple bad measurements, topology branches errors.