Tuning of SVC damping controllers over a wide range of load models using an artificial neural network

This paper presents an artificial neural network (ANN)-based technique for tuning a damping controller for a static var compensator (SVC) to improve the damping of power systems over a wide range of typical load models. A proportional-integral (PI) controller is considered for the damping controller and its parameters are determined using the poleplacement technique. The types and characteristics of loads vary seasonally, and in some cases change over a day; consequently, a damping controller designed with fixed parameters can be adequate for some loads but, contrarily, can contribute to system instability with loads having other extreme characteristics. The developed ANN-based technique uses predetermined system load characteristics combined with other measured system conditions as continuous inputs. Based on such information, the ANN technique adjusts the SVC damping controller parameters to assure good damping and system stability for the prevailing conditions. The proposed ANN technique has been applied to tune the parameters of the SVC damping controller for two power systems. The results show that the load model parameters have a considerable effect on the tuned parameters of the damping controller. Computer simulations performed on the two power systems show that the tuned parameters of the SVC damping controller using the ANN technique can provide better damping than the fixed parameters damping controller.