Abstract: Self-balancing groups are introduced as a feature of managed charging of electric vehicles in order to avoid overloading of elements of the transmission grid, such as transformers, by use of a load forecast signal. In a self-balancing managed charge system, each vehicle is assigned to a vehicle group, which abstractly represents a cluster of vehicles supported by shared utility resources, such as a transformer or set of transformers. As each vehicle in a group plugs in for charging, the self-balancing managed charge system forecasts an expected load curve for the power that the groups of vehicles will draw. This forecast is then summed for all the vehicles in the group, and becomes a signal for the next vehicle to determine the charging as subsequent members of the group plug in.

Abstract: Techniques are presented for the detection of whether an EV is using a household or other user location for charging. A machine learning model is trained on a training population of user locations using historical usage data and a label for a some of the user locations, typically a small proportion, indicating that an EV charges there, where the labels can, for example, be provided by a utility or derived from the EVs' telematics. The trained model can then be applied to un-labeled user locations' electricity usage data to detect EV charging, both assigning a label and a confidence value to the label. If telematics are available, for user locations at which EV charging is detected, the EV charging can be disaggregated from other electricity usage of the user location.