Fig. 4From: Learning capacity: predicting user decisions for vehicle-to-grid servicesArchitecture of the prediction engine. Probabilities from an individual’s user preferences (yellow) and vehicle locations (blue) at the time of the potential market opportunity are input to a layer of nodes for each of the N users (U1 to UN). The capacity node predicts overall capacity (Ccum) given predicted outputs for each user weighted by the user’s reliabilityBack to article page