Eric MSP Veith

OFFIS | OFFIS · Division of Energy

Multi-agent systems have firmly established themselves as a methodology as a distributed heuristics that sees not only scientific, but real-world application in many domains, such as the power grid. These systems can provide guarantees on convergence or other aspects of their operation and are well suited to calculate optimal or close-to-optimal so...

Power grids are a critical infrastructure that get more and more complex. To be better able to deal with the increasingly complex structure, Deep Reinforcement Learning (DRL) has been used to identify stability problems , determine load forecasting, and figure out new attack vectors. Most of the current research is focused on showcasing the perform...

The power grid, a critical national infrastructure, integrates ICT-based control systems to enhance grid operation , involving prosumers and volatile generation and becoming the smart grid. This integration, while improving efficiency, increases the risk of cyberattacks and operational failures, necessitating expert knowledge from grid operators an...

This paper addresses the challenge of neural state estimation in power distribution systems. We identified a research gap in the current state of the art, which lies in the inability of models to adapt to changes in the power grid, such as loss of sensors and branch switching. Our experiments demonstrate that graph neural networks are the most prom...

Learning agents that employ algorithms from the domain of Machine Learning (ML) or Deep Reinforcment Learning (DRL) have gained popularity among scientists, including in Cyber-Physical Systems (CPSs) research. However, simulating complex CPSs encompasses multiple domains and requires careful orchestration, often employing a co-simulation approach....

The analysis of cyber-physical energy systems is often limited to the individual sub-domains. On the one side, this is caused by the system’s complexity. On the other side, there are many specialized tools but only a few open-source solutions, and bringing those tools together is a complex task. For this reason, we built the open-source framework m...

Agent systems have become almost ubiquitous in smart grid research. Research can be roughly divided into carefully designed (multi-) agent systems that can perform known tasks with guarantees, and learning agents based on technologies such as Deep Reinforcement Learning (DRL) that promise real resilience by learning to counter the unknown unknowns....

As automation increases qualitatively and quantitatively in safety-critical human cyber-physical systems, it is becoming more and more challenging to increase the probability or ensure that human operators still perceive key artefacts and comprehend their roles in the system. In the companion paper, we proposed an abstract reference architecture ca...

The design and analysis of multi-agent human cyber-physical systems in safety-critical or industry-critical domains calls for an adequate semantic foundation capable of exhaustively and rigorously describing all emergent effects in the joint dynamic behavior of the agents that are relevant to their safety and well-behavior. We present such a semant...

We propose a reference architecture of safety-critical or industry-critical human cyber-physical systems (CPSs) capable of expressing essential classes of system-level interactions between CPS and humans relevant for the societal acceptance of such systems. To reach this quality gate, the expressivity of the model must go beyond classical viewpoint...

The ongoing penetration of energy systems with information and communications technology (ICT) and the introduction of new markets increase the potential for malicious or profit-driven attacks that endanger system stability. To ensure security-of-supply, it is necessary to analyze such attacks and their underlying vulnerabilities, to develop counte...

Learning systems have achieved remarkable success. Agents trained using Deep Reinforcement Learning (RL) (DRL) methods, e.g., promise real resilience. However, no guarantees can yet be provided for the learned black-box models. For operators of Critical National Infrastructures (CNIs), this is a necessity as no responsibility can be assumed for an...

The ongoing penetration of energy systems with information and communications technology (ICT) and the introduction of new markets increase the potential for malicious or profit-driven attacks that endanger system stability. To ensure security-of-supply, it is necessary to analyze such attacks and their underlying vulnerabilities, to develop counte...

The Thirteenth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies (ENERGY 2023), held between March 13 – 17, 2023, continued the event considering Green approaches for Smart Grids and IT-aware technologies. It addressed fundamentals, technologies, hardware and software needed support, and applications and...

Modern smart grids already consist of various components that interleave classical Operational Technology (OT) with Information and Communication Technology (ICT), which, in turn, have opened the power grid to advanced approaches using distributed software systems and even Artificial Intelligence (AI) applications. This IT/OT integration increases...

Neural State Estimation (NSE) is a novel application of deep learning which is concerned with interpolating the state of a distribution power grid from a limited amount of sensor data and can be represented as a non-linear graph time-series nowcasting problem. Although several authors have proposed their solutions for NSE, there is neither a compar...

Im Auftrag des Bundesministeriums für Wirtschaft und Klimaschutz haben DIN und DKE im Januar 2022 die Arbeiten an der zweiten Ausgabe der Deutschen Normungsroadmap Künstliche Intelligenz gestartet. In einem breiten Beteiligungsprozess und unter Mitwirkung von mehr als 570 Fachleuten aus Wirtschaft, Wissenschaft, öffentlicher Hand und Zivilgesellsch...

This book contributes results of research in the Boolean domain related to important real life applications that will support readers in solving their scientific and practical tasks. Ongoing digitalization leads to ever more applications with growing complexities. The digits of such applications are usually encoded by Boolean variables due to thei...

In the past years, power grids have become a valuable target for cyber-attacks. Especially the attacks on the Ukrainian power grid has sparked numerous research into possible attack vectors, their extent, and possible mitigations. However, many fail to consider realistic scenarios in which time series are incorporated into simulations to reflect th...

Machine learning and computational intelligence technologies gain more and more popularity as possible solution for issues related to the power grid. One of these issues, the power flow calculation, is an iterative method to compute the voltage magnitudes of the power grid's buses from power values. Machine learning and, especially, artificial neur...

Future smart grids can and will be subject of systematic attacks that can result in monetary costs and reduced system stability. These attacks are not necessarily malicious, but can be economically motivated as well. Emerging flexibility markets are of interest here, because they can incite attacks if market design is flawed. The dimension and dang...

In order to prevent conflicting or counteracting use of flexibility options, the coordination between distribution system operator and transmission system operator has to be strengthened. For this purpose, methods for the standardized description and identification of the aggregated flexibility potential of distribution grids are developed. Approac...

The increase of generation capacity in the area of responsibility of the distribution system operator (DSO) requires strengthening of coordination between transmission system operator (TSO) and DSO in order to prevent conflicting or counteracting use of flexibility options. For this purpose, methods for the standardized description and identificati...

Unlocking and managing flexibility is an important contribution to the integration of renewable energy and an efficient and resilient operation of the power system. In this paper, we discuss how the potential of a fleet of battery-electric transportation vehicles can be used to provide frequency containment reserve. To this end, we first examine th...

Power grids are transitioning from an infrastructure model based on reactive electronics towards a smart grid that features complex software stacks with intelligent, pro-active and decentralized control. As the power grid infrastructure becomes a platform for software, the need for a reliable roll-out of software updates on a large scale becomes ev...

Multi-microgrids address the need for a resilient, sustainable, and cost-effective electricity supply by providing a coordinated operation of individual networks. Due to local generation, dynamic network topologies, and islanding capabilities of hosted microgrids or groups thereof, various new fault mitigation and optimization options emerge. Howev...

Explainable Artificial Intelligence (XAI), i.e., the development of more transparent and interpretable AI models, has gained increased traction over the last few years. This is due to the fact that, in conjunction with their growth into powerful and ubiquitous tools, AI models exhibit one detrimental characteristic: a performance-transparency trade...

Modern cyber-physical systems (CPS), such as our energy infrastructure, are becoming increasingly complex: An ever-higher share of Artificial Intelligence (AI)-based technologies use the Information and Communication Technology (ICT) facet of energy systems for operation optimization, cost efficiency, and to reach CO2 goals worldwide. At the same t...

Modern algorithms in the domain of Deep Reinforcement Learning (DRL) demonstrated remarkable successes; most widely known are those in game-based scenarios, from ATARI video games to Go and the StarCraft~\textsc{II} real-time strategy game. However, applications in the domain of modern Cyber-Physical Systems (CPS) that take advantage a vast variety...

Power grids are transitioning from an infrastructure model based on reactive electronics towards a smart grid that features complex software stacks with intelligent, pro-active and decentralized control. As the power grid infrastructure becomes a platform for software, so does the need for a reliable roll-out of software updates on a large scale. I...

Explainable Artificial Intelligence (XAI), i.e., the development of more transparent and interpretable AI models, has gained increased traction over the last few years. This is due to the fact that, in conjunction with their growth into powerful and ubiquitous tools, AI models exhibit one detrimential characteristic: a performance-transparency trad...

Modern power grids need to cope with increasingly decentralized, volatile energy sources as well as new business models such as virtual power plants constituted from battery swarms. This warrants both, day-ahead planning of larger schedules for power plants, as well as short-term contracting to counter forecast deviations or to accommodate dynamics...

Principles of modern cyber-physical system (CPS) analysis are based on analytical methods that depend on whether safety or liveness requirements are considered. Complexity is abstracted through different techniques, ranging from stochastic modelling to contracts. However, both distributed heuristics and Artificial Intelligence (AI)-based approaches...

This paper introduces Adversarial Resilience Learning (ARL), a concept to model, train, and analyze artificial neural networks as representations of competitive agents in highly complex systems. In our examples, the agents normally take the roles of attackers or defenders that aim at worsening or improving-or keeping, respectively-defined performan...

This paper introduces Adversarial Resilience Learning (ARL), a concept to model, train, and analyze artificial neural networks as representations of competitive agents in highly complex systems. In our examples, the agents normally take the roles of attackers or defenders that aim at worsening or improving-or keeping, respectively-defined performan...

In the domain of energy automation, where a massive number of software-based IoT services interact with a complex dynamic system, processes for software installation and software update become more important and more complex. These processes have to ensure that the dependencies on all layers are fulfilled, including dependencies arising due to the...

The future power grid will rely strongly on renewable energy sources. Since wind power and solar energy are the most widely available sources of renewable energy, they will contribute the greatest share in most countries. The site considerations of wind farms and solar power plants lead to a vastly distributed generation. Additionally, local foreca...

Evolutionary training methods for Artificial Neural Networks can escape local minima. Thus, they are useful to train recurrent neural networks for short-term weather forecasting. However, these algorithms are not guaranteed to converge fast or even converge at all due to their stochastic nature. In this paper, we present an algorithm that uses impl...

Including more renewable energy sources in the energy mix will increase the necessity for a finer grained, automatic control of changes in the energy level. Any such software needs extensive testing before it can be released for general availability. Simulation environments will be a part in these testing stacks, but need realistic input data in or...

The smart grid concept introduces more software control at both endpoints of the energy consumption chain: The consumer is integrated into the grid management using smart metering, whereas the producer will be host to a distributed agent-based software approach. Including more renewable energy sources in the energy mix will increase the necessity f...

For selecting and composing communication ser-vices to create a networking stack in a flexible future network architecture, service descriptions are required. In this paper, we propose a language for describing communication services. The language has been implemented by using the Resource Description Framework (RDF) and evaluated by describing a s...

The current Internet architecture was designed decades ago. Back then the main goals of the architecture were stability, performance and of course its functionality. Current trends, e.g. mobile devices, cloud computing, energy efficiency pose new requirements that the current Internet architecture cannot fulfill. Rather than building new functional...

In the current rather rigid communication model on the Internet, the functional composition of available algorithms is dictated by the ISO/OSI stack model. A flexible architecture, as often discussed in the Future Internet research area, will be able to support the desire to dynamically choose certain mechanisms based on the requirements of a parti...