A combined artificial neural network-fuzzy dynamic programmingapproach to reactive power/voltage control in a distribution substation

摘要

Reactive power/voltage control in a distribution substation isninvestigated in this work. The purpose is to determine proper capacitornon/off status and suitable load tap changer (LTC) positions for the 24nhours in the next day. To reach this goal, an artificial neural networkn(ANN) is designed to reach a preliminary dispatch schedule for thencapacitor and LTC. The inputs to the ANN are main transformer real powernand reactive power and primary and secondary bus voltages and thenoutputs are the desired capacitor on/off status and LTC tap positions.nThe preliminary dispatch schedule is further refined by fuzzy dynamicnprogramming in order to reach the final schedule. To demonstrate theneffectiveness of the proposed method, reactive power/voltage control isnperformed on a distribution substation in Taipei, Taiwan. Results fromnthe example show that a proper dispatch schedule for capacitor and LTCncan be reached by the proposed method in a very short period