Dual Timescales Voltages Regulation in Distribution Systems Using Data-Driven and Physics-Based Optimization

A large number of electric vehicles, distributed solar, and/or wind turbine generators connected to distribution systems lead to frequent and sharp voltages fluctuations. The action rates of conventional adjustable devices and smart inverters are very different. In this context, a novel dual-timescale voltage control scheme is proposed by organically combining data-driven with physics-based optimization. On fast timescale, a quadratic programming for balanced and unbalanced distribution systems is developed based on branch flow equations. The optimal reactive power of renewable distributed generators and static VAR compensators is configured on several minutes or seconds. Whereas, on slow timescale, a data-driven Markovian decision process is developed, in which the charge/discharge power of energy storage systems, statuses/ratios of switchable capacitors reactors, and voltage regulators are configured hourly to minimize long-term discounted squared voltages magnitudes deviations using an adapted deep deterministic policy gradient deep reinforcement learning algorithm. The capabilities of the proposed method are validated with IEEE 33-bus balanced and 123-bus unbalanced distribution systems.