Autonomous Charging of Electric Vehicle Fleets to Enhance Renewable Generation Dispatchability.

摘要: A total 19% of generation capacity in California is offered by PV units and over some months, more than 10% this energy curtailed. In research, a novel approach to reduce renewable curtailments increasing system flexibility means electric vehicles' charging coordination represented. The presented problem sequential decision making process, solved fitted Q-iteration algorithm which unlike other reinforcement learning methods, needs fewer episodes learning. Three case studies are validate the effectiveness proposed approach. These cases include aggregator load following, ramp service utilization non-deterministic generation. results suggest that through framework, EVs successfully learn how adjust their schedule stochastic scenarios where trip times, as well solar power unknown beforehand.