Smart Online Charging Algorithm for Electric Vehicles via Customized Actor-Critic Learning

With the advances in the Internet-of-Things technology, electric vehicles (EVs) have become easier to schedule in daily life, which is reshaping the electric load curve. It is important to design efficient charging algorithms to mitigate the negative impact of EV charging on the power grid. This article investigates an EV charging scheduling problem to reduce the charging cost while shaving the peak charging load, under unknown future information about EVs, such as arrival time, departure time, and charging demand. First, we formulate an EV charging problem to minimize the electricity bill of the EV fleet and study the EV charging problem in an online setting without knowing future information. We develop an actor-critic learning-based smart charging algorithm (SCA) to schedule the EV charging against the uncertainties in EV charging behaviors. The SCA learns an optimal EV charging strategy with continuous charging actions instead of discrete approximation of charging. We further develop a more computationally efficient customized actor-critic learning charging (CALC) algorithm by reducing the state dimension and thus improving the computational efficiency. Finally, simulation results show that our proposed SCA can reduce EVs' expected cost by 24.03%, 21.49%, 13.80%, compared with the eagerly charging algorithm, online charging algorithm, reinforcement learning (RL)-based adaptive energy management algorithm, respectively. CALC is more computationally efficient, and its performance is close to that of SCA with only a gap of 5.56% in the cost.

Automated summary

With the advancement of IoT technology, scheduling electric vehicles has become easier, but the negative impact on the power grid due to charging needs to be addressed. This article investigates the problem of scheduling EV charging to minimize cost and balance electricity load without knowing future information. The proposed smart charging algorithms effectively reduce charging costs and peak load while considering uncertainties in EV charging behaviors.