Uncertainty in controllable devices and their power in distribution grids is a considerable problem for grid operators. The corresponding "blind" control of electric vehicles (EV), heat pumps, heating, ventilation, and air conditioning systems can harm the grid. On the one hand, if not enough controllable devices are available to balance the load, congestion, potentially damaging the operating equipment, can occur. On the other hand, the incentive of prosumer involvement to provide flexibility can decrease due to overcontrol of their devices. To analyze how many devices and their respective power are currently in use, the measurement data, for instance, smart meters data, need to be disentangled and split into the household load, the load caused by EVs, etc. In this contribution, we develop an LSTM-based auto-encoder model to detect electric vehicles charging in household profiles. We test the model by increasing the number of households with respect to the EV. Furthermore, we use the minimum controllable power defined in the German Energy Industry Act to increase the classification of EVs. The LSTM autoencoder can reliably identify electric vehicles in grouped smart meter data. It provides near-optimal results for three households with a precision of 97% for four households.