Increasing penetration of renewable energy sources in form of distributed generators has brought many technical challenges to distribution networks. Among those, voltage and reactive power control should be revised and improved. Existing and new control resources should be coordinated based on real-time information and in closed loop. To achieve this, machine learning (ML) can be used to map the relationship between the selected network information and the desired control output. In this paper, setting of the shunt compensator operating in capacitive or inductive modes is coordinated with the tap position of substation transformer by the developed ML. Dataset emulating network behaviour during a year operation is constructed for training ML. A multi-class classification problem is formulated. Simulation results show satisfactory accuracy for some classes.
Machine learning based CDMA power control