Electric Vehicles (EVs) and Plug-in Hybrid Vehicles (PHVs) are expected to work not only as transportation devices, but also as power storages in an Energy Management System (EMS) because of their batteries of high capacity. In order to utilize the in-vehicle battery in the EMS with considering acceptance of the users, the EMS needs to know when the vehicle is driven and when is parked, which is represented a Profile of Departure and Travel Time (PDTT). This paper presents an prediction method of the PDTT of one day ahead based on Statistics of Departure/Travel Time (SDTT) and Statistics of Arrival/Parked Time (SPAT). The prediction problem of PDTT is formulated as a maximum-likelihood estimation problem under the condition that the SDTT and SPAT are available. In order to find a global optimal solution within a reasonable computational cost, first of all, a Markov model representing time-passage of moving or parked is derived from the SDTT and SPAT. Then, the dynamic programming is applied to find the most likely PDTT of the car. The usefulness of the proposed method is evaluated by numerical experiments, wherein the SDTT and SPAT are created by real driving data of 30 vehicles.
