Olaf Czogalla

This paper presents a new methodology for calculating the total cost of ownership (TCO) for the deployment of battery-electric buses in public transportation. The model considers multiple parameters and their dynamics, complementing the existing body of knowledge on TCO models. The model integrates internal and external cost categories, accounting for cost dynamics over time and the allocation of these costs among different stakeholders, including public transport operators and local authorities. Unlike static models, our dynamic framework captures the evolution of costs throughout the project lifecycle by incorporating forecasted values for variables such as operational expenditures, energy prices, maintenance, and environmental costs. Furthermore, the model includes externalities such as emissions and noise pollution costs, which are often overlooked in traditional TCO assessments. Based on data obtained from public transport operators, we applied the TCO model to a real-life long-term conversion scenario in southern Poland. The main research findings emphasize the importance of operating and external costs in the overall TCO structure, with the latter accounting for up to 30% of the total TCO. Their inclusion in the model is crucial because they are typically not considered in TCO models.

Traffic signal forecasting plays a significant role in intelligent traffic systems since it can predict upcoming traffic signal without using traditional radio-based direct communication with infrastructures, which causes high risk in the communication security. Previously, mathematical and statistical approach has been adopted to predict fixed time traffic signals, but it is no longer suitable for modern traffic-actuated control systems, where signals are dependent on the dynamic requests from traffic flows. And as a large amount of data is available, machine learning methods attract more and more attention. This paper views signal forecasting as a time-series problem. Firstly, a large amount of real data is collected by detectors implemented at an intersection in Hanover via IoT communication among infrastructures. Then, Baseline Model, Dense Model, Linear Model, Convolutional Neural Network, and Long Short-Term Memory (LSTM) machine learning models are trained by one-day data and the results are compared. At last, LSTM is selected for a further training with one-month data producing a test accuracy over 95%, and the median of deviation is only 2 s. Moreover, LSTM is further evaluated as a binary classifier, generating a classification accuracy over 92% and AUC close to 1.