Keynote Lectures

Abstract
A vital requirement of the power system is always to maintain a balance between generation and the demand. To meet the increasing demand and simultaneously decrease the carbon footprint of the power grid, fossil fuel-based energy sources are being phased out and distributed renewable energy sources are being integrated into the power grid. These renewable energy sources increase the unpredictability of power generation, as they are dependent on factors such as the sun and the wind. This unpredictability can threaten the system's resilience in extreme cases where the generation and demand deviate excessively. A solution to tackling this unpredictability is using Information and Communication Technology (ICT) systems, in both a proactive and reactive sense, for power grid services. Proactively, forecasts of generation and demand can be used to schedule system operations to maintain the balance between generation and demand, thus making the system plannable. Reactively, in case of deviations from the planned schedule, certain generation flexibilities can be activated to ensure the generation meets the demand. However, imprecise generation prediction could lead to insufficient flexibility to restore a balance between generation and demand, leading to cascading impacts on the power system. This reliance of the power system on the ICT system introduces a mutual dependency, where the power system relies on ICT for monitoring, control and decision making and ICT relies on the power system for power supply. Consequently, issues such as incorrect and unavailable data and increased communication latency can lead to erroneous decisions being taken in the power system. These issues impact the resilience of the system since the erroneous decision taken may not remedy the existing challenge and, in fact, may exacerbate its impact. Some relevant power and energy services are, for example, related to protection, blackstart or flexibility.

Abstract
Nowadays urban mobility systems are facing challenges ranging from environmental pollution to social injustice. The advent of cyber-physical technologies such as automated driving, connectivity and powertrain electrification (ACE), along with well-established innovations (+), might provide us with promising opportunities to face these challenges. However, there is a risk of falling into the “engineer trap”, where technology-driven solutions may backfire on society.

In this context, this talk will show how we have devised optimization models and methods to address research questions encompassing the individual-vehicle and the transportation-system level. In particular, I will first present models and optimization algorithms to design and control fully-electric vehicles. Second, I will give an overview on our work on mobility systems, including concepts and models to study the societal benefits stemming from new mobility paradigms in terms of sustainability, well-being, accessibility and justice.

Abstract
With the introduction of highly automated train operation (Grade of Automation (GoA) 4 operation) a significant performance increase of railway systems can be achieved. This includes the enhancement of the transport capacity in existing tracks, energy savings by means of an optimized driving strategy, reduced mechanical wear and tear as well as increased passenger comfort by means of homogeneous driving, and increased flexibility for demand-oriented train services. However, traditional automation technologies alone are not sufficient to enable the fully automated operation of trains on non-restricted infrastructure. However, Artificial Intelligence (AI) and Machine Learning (ML) offers great potential to realize the mandatory novel functions to replace the tasks of a human train driver, such as obstacle detection on the tracks. The problem, which still remains unresolved, is to find a practical way to link AI/ML methodologies with the requirements and approval processes that are applied in the railway domain. The safe.trAIn project (2022 - 2024) aims to lay the foundation for safe use of AI/ML for the driverless operation of rail vehicles and to thus addresses this key technological challenge hindering the adoption of unmanned rail transport. The project goals are to perform integrated development of guidelines and methods for the safety assurance of AI in highly automated train operation. Based on the requirements for the certification process in the railway domain, safe.trAIn creates a safety argumentation for an AI-based obstacle detection function of a driverless regional train. Therefore, the project investigates methods to prove trustworthiness of AI-based functions taking robustness, performance, uncertainty, transparency, and out-of-distribution aspects of the AI/ML model into account. These methods are integrated into a comprehensive and continues testing and verification process for trains. The feasibility of the guidelines and methods developed in safe.trAIn is evaluated with a real case study in which an exemplary safety case for a driverless regional train is created and assessed.