Electric Vehicles Plug-In Duration Forecasting Using Machine Learning for Battery Optimization

The aging of rechargeable batteries, with its associated replacement costs, is one of the main issues limiting the diffusion of electric vehicles (EVs) as the future transportation infrastructure. An effective way to mitigate battery aging is to act on its charge cycles, more controllable than discharge ones, implementing so-called battery-aware charging protocols. Since one of the main factors affecting battery aging is its average state of charge (SOC), these protocols try to minimize the standby time, i.e., the time interval between the end of the actual charge and the moment when the EV is unplugged from the charging station. Doing so while still ensuring that the EV is fully charged when needed (in order to achieve a satisfying user experience) requires a “just-in-time” charging protocol, which completes exactly at the plug-out time. This type of protocol can only be achieved if an estimate of the expected plug-in duration is available. While many previous works have stressed the importance of having this estimate, they have either used straightforward forecasting methods, or assumed that the plug-in duration was directly indicated by the user, which could lead to sub-optimal results. In this paper, we evaluate the effectiveness of a more advanced forecasting based on machine learning (ML). With experiments on a public dataset containing data from domestic EV charge points, we show that a simple tree-based ML model, trained on each charge station based on its users’ behaviour, can reduce the forecasting error by up to 4× compared to the simple predictors used in previous works. This, in turn, leads to an improvement of up to 50% in a combined aging-quality of service metric.

Development and Verification of a Simulation Model for 120 kW Class Electric AWD (All-Wheel-Drive) Tractor during Driving Operation

This study was conducted to develop a simulation model of a 120 kW class electric all-wheel-drive (AWD) tractor and verify the model by comparing the measurement and simulation results. The platform was developed based on the power transmission system, including batteries, electric motors, reducers, wheels, and a charging system composed of a generator, an AC/DC converter, and chargers on each axle. The data measurement system was installed on the platform, consisting of an analog (current) and a digital part (rotational speed of electric motors and voltage and SOC (state of charge) level of batteries) by a CAN (controller area network) bus. The axle torque was calculated using the current and torque curves of the electric motor. The simulation model was developed by 1D simulation software and used axle torque and vehicle velocity data to create the simulation conditions. To compare the results of the simulation, a driving test using the platform was performed at a ground speed of 10 km/h in off- and on-road conditions. The similarities between the results were analyzed using statistical software and we found no significant difference in axle torque data. The simulation model was considered to be highly reliable given the change rate and average value of the SOC level. Using the simulation model, the workable time of driving operation was estimated to be about six hours and the workable time of plow tillage was estimated to be about 2.4 h. The results showed that the capacity of the battery is slightly low for plow tillage. However, in future studies, the electric AWD tractor performance could be improved through battery optimization through simulation under various conditions.