AI Assisted Domain Modeling

The transition to the digital age results in an increased need for domain models that are machine understandable. Providing explicit knowledge representation of domains of interest, domain models are increasingly expected to be created, understood, and owned by domain experts who are non-experts in modeling. This situation causes a modeling bottleneck in that it is not reasonable to expect all non-experts to become modeling experts.

We turn to Artificial Intelligence (AI) techniques such as Large Language Models (LLMs) and Natural Language Processing (NLP) to empower non-experts to carry out domain modeling related tasks. In particular, a symbiotic collaboration between human intelligence, symbolic AI and subsymbolic AI is advocated, aiming at a triple-helix of human, symbolic, and subsymbolic intelligence for assisting domain modeling.

Leveraging the Power of Formal Methods in the Realm of Enterprise Modeling

Enterprise modeling (EM) supports the description, reflection upon, and (re-)design of various aspects of enterprises (e.g., organizational goals, business processes, or IT infrastructure). Therefore, EM approaches usually cover multiple perspectives on an organization, modeled using different modeling languages in tandem and relate these perspectives to each other. The main role of enterprise models includes the provision of knowledge on selected aspects within, or related to, an enterprise, and consequently to enable a variety of analyses.

A pre-requisite for such model-based analyses is to ensure firstly that the specification of modeling languages is consistent, and secondly, that enterprise models contain the necessary and correct information, in line with domain-specific rules. We capitalize on the verification capabilities of formal methods for achieving this goal in the context of EM. Taking one example meta modeling platform (ADOxx) and one example of lightweight formal method (Alloy) as a starting point, we investigate how the two platforms can be chained together, to take advantage of complementary platform strengths, namely, ADOxx for language specification and use, and Alloy for verification capabilities. We are interested in the verification, both, on the meta model level, in terms of checking the consistency of language specifications, and on the model level, in terms of checking models against well-formedness constraints.

Application of a Model-Based Valuation Method to a Blockchain-based Smart Grid Project

The electricity sector is increasingly characterized by the use of Information Technology (IT) for the electricity grid, leading to its transformation into a smart grid. Various pilot smart grid initiatives exist, which have already showcased their technical feasibility. Nevertheless, for the needs of informed decision-making, a subsequent valuation support of those initiatives for all involved stakeholders is also essential. Considering the importance and complexity of such a valuation, we propose a MOdel-based, multi-perspectiVe method for the valuation of INitiatives in the smart Grid (MOVING). MOVING complements well-established smart grid valuation methods with conceptual modeling, to cater for a systematic analysis of actor goals, value exchanges, and IT. We apply the MOVING method to assess the costs and benefits of a blockchain-based smart grid initiative to encourage local production and consumption of renewable electricity.

Using Conceptual Modeling to Assess the Economic and Regulatory Viability of Renewable Energy Communities

Energy communities constitute an important part of the clean energy transition. With the proliferation of regulations that define, enable and rule energy communities, setting up an energy community that is both economically profitable for stakeholders and viable from the regulatory perspective becomes a demanding task. We demonstrate how conceptual modeling can be used as a viable instrument to conjointly analyse the economic and regulatory viability of energy communities.