Real-time systems require up-to-date information. Measurement signals in the power train of Electric Vehicles (EVs) are however often received with individual time delays due to the distributed architecture of the power train. Our idea is to compensate the time delays by predicting each signal from the last received value until the present time step. In this work, we evaluate 5 state-of-the-art algorithms and 2 naive methods for time series prediction. We execute all algorithms on real power train data of EVs and compare the results. Our evaluation focuses on run-time and accuracy. All methods achieve a prediction error rate of less than 5 %. As expected, the benchmark naive method is the fastest. Surprisingly, it retrieves comparable results to Exponential Smoothing. BATS and TBATS are the slowest methods. Nevertheless, they achieve the best accuracy, but suffer from outliers. Auto-Regressive Integrated Moving Average (ARIMA) achieves the smallest Mean Absolute Percentage Error (MAPE) and thus the best compromise between outliers and accuracy of all algorithms. Additionally, to further improve the accuracy, we investigate Additionally, to further improve the accuracy, we investigate the benefits of combining predictions of different algorithms.

In present study we focus on a special case problem for an island where the transportation is mainly based on barouches pulled by horses due to the limitation on the use of internal combustion engine vehicles. Both the daily travels of islanders and touristic tours of visitors are provided by barouches that are operated as private travel mode, where they serve to meet individual travelers demands. Our motivation has therefore been to alternate barouches with electric vehicles in conjunction with determining the locations of recharging stations in order to respect the animal rights and pollution concerns. Considering the rugged topology of the case area, we notice the limitations and benefits of EVs. On one hand, noticing the slope climbing restrictions and limited driving range of EVs may be accepted as the most significant challenges of alternating the vehicle types of the fleet. On the other hand, the potential of regenerative energy, together with the reduced emission effects, is a promising feature of EVs. In this context, we formulate an Electrified Location Routing Problem using mixed integer linear programming by realistically calculating the battery load considering explicitly the driving resistances and the potential regenerative braking.

This paper proposes a model for charge scheduling of electric vehicles in last-mile distribution that takes into account battery degradation. A mixed integer linear programming formulation is proposed that minimizes labor, battery degradation and time-dependent energy costs. The benefit of implementing charge schedule optimization is assessed for a real-life case study at e-grocer Picnic. It is shown that charging optimization yields an overall reduction of charging costs by 25.2% when compared to the current operational charging performance. Furthermore, the impacts of three different shift schedule types, the increase in vehicle battery size and the coordinated charging are investigated. It turns out that more energy demanding shift schedules result in higher average charging cost per charged amount of energy. The introduction of a larger battery size as well as coordinated charging show potential for decreasing overall costs.