Electric Vehicle Charging via Machine-Learning Pattern Recognition

Abstract

This paper presents machine learning valley-filling (MLVF) to enhance plug-in electric vehicle (PEV) charging at the local power level while minimizing the effects of uncontrolled PEV charging. This study investigated whether a neural network algorithm could learn to identify when to begin charging a PEV by distinguishing low and high demand sections in the forecasted baseload. The results indicate that a neural network algorithm can indeed identify low and high demand sections in the forecasted baseload and learn when to begin charging electric vehicles to decrease demand loads. MLVF achieved a microaveraged F1 score, an indicator of a classifier’s overall accuracy, of 92.84% of selecting the correct timeslot to initiate charging.