Adaptive Load Shedding Method Based on Power Imbalance Estimated by ANN

摘要

A new adaptive load shedding method based on the artificial neural network (ANN) and power flow tracing is proposed in this paper. The ANN is used to estimate the total active power imbalance according to the time interval of frequency drop of the equivalent inertial center from the rated value to the threshold. Load frequency regulation factor and the load priority are incorporated into the power flow tracing method to choose locations of load shedding and determine the amount of load shedding of each load. The new method is tested in the 8-machine 36-bus system. The test results demonstrate that the active power imbalance estimated by the ANN is more accurate. Besides, the new load shedding algorithm can give priority to shedding the load with smaller load frequency regulation factor and protect important loads from being shed.