Softly Collaborated Voltage Control in PV Rich Distribution Systems With Heterogeneous Devices
Licheng Wang, Tao Wang, Gang Huang, Kai Wang, Ruifeng Yan, Youbing Zhang
Abstract
With the continuous increase of photovoltaic (PV) penetration, the voltage control interactions between newly installed PV inverters and previously deployed on-load tap-changer (OLTC) transformers become ever more significant. To achieve coordinated voltage regulation, current methods often rely on a decision-making algorithm to fully take over the control of both inverters and OLTC. Consequently, OLTC has to give up its autonomous tap switching logic and executes corresponding upgrades in order to be controlled by the new algorithm. Aiming at bridging this gap, a soft coordination framework is proposed in this paper. Specifically, the decision-making algorithm will only directly control inverters' Var output, and OLTC is allowed to maintain its autonomous control state for tap switching. To realize such soft coordination, the voltage control problem should first be modelled as a memory-based Markov decision process (MDP), and on this basis, the recurrent soft actor-critic algorithm (RSAC) is proposed for proxy model training. The well-trained proxy model can properly adjust inverters' Var output to “softly” collaborate with OLTC's tap operations, which finally attains overvoltage elimination and line loss minimization. Simulation results verify the superiority of our proposed method over traditional ones in coordinating heterogeneous devices for voltage control.