Skip to content

Dissemination

Vladimir Alexiev edited this page May 18, 2026 · 9 revisions

Current status: Apr 2026

Introduction

This document describes the Dissemination, Communication, Exploitation and Sustainability aspects of the project. They are important to ensure the impact and sustainability of the development efforts.

  • Dissemination: write joint research papers, attend scientific conferences
  • Communication: write blog posts, attend trade events
  • Exploitation: work with Statnett application owners and end-users to make the project results more usable and reusable in day-to-day work
  • Sustainability and Proliferation: work with other electrical enterprises to attract them for joint exploitation and development
  • Research Proposals: research appropriate funding calls, build appropriate consortia, write research proposals.
    • Also work towards securing GPU funding for joint training/fine-tuning of an electrical-CIM specific LLM.

This is a living document that will evolve with the project. It tracks ideas and actions, organized around a Timeline of monthly activities:

  • Actual: We provide as much information as possible (links to call for papers, presentation, recording, etc)
  • Planned: Clearly marked TODO; the timing of future activities can change multiple times

Exploitation and Sustainability are covered in a separate confidential document.

Dissemination

Scientific contributions:

  • Vladimir Alexiev, Aleksis Datseris, Neli Hateva, Andreas Kimsas, Svein Harald Olsen, Andrey Tagarev, Nikola Tulechki. CIMon (Talk2PowerSystem): Democratizing Power System Analytics via Generative AI. Draft (work in progress), Apr 2026.
  • Arkadiusz Chadzynski, Svein Harald Olsen. CIM-sala-BIM: Aligning High-Voltage Electrical CIM with bSDD for Interoperable BIM Workflows., Draft (work in progress), Apr 2026.

Communication

Participation in events, and blog posts about the project (we planned quarterly posts, but the frequency is significantly greater).

  • TODO: Post more blogs from the series on GraphDB TTYG by Graphwise partners
  • TODO: Present at Siemens Energy "Data over Data" webinar

Mar 2025

Apr 2025

  • Statnett-LLM project: Talk2PowerSystem. Vladimir Alexiev and Neli Hateva. Graphwise LastFriday meeting, 25 Apr 2025
    • Abstract: Electricity is one of the early domains to use semantic technologies (starting in the 1990s). The IEC electrical CIM and ENTSO-E CGMES are comprehensive UML models of the electrical enterprise, from which RDFS/OWL ontologies and SHACL shapes are derived. They are the foundation of managing the electrical grid (Transmission System Operators), distribution (Distribution System Operators) and markets. Statnett is the Norwegian TSO and a leader in applying and extending CIM/CGMES. They have been using GraphDB (and we have been working on electricity) for about 5 years. The Talk2PowerSystem project aims to "democratise power system analytics" by enabling Natural Language Querying (NLQ) over electrical KGs through SPARQL (and later GraphQL) generation, and related use cases such as integration with their enterprise systems, time-series processing, code generation for power system analytics libraries, etc. We are creating a comprehensive Q&A dataset for electricity, and will likely store it in RDF (e.g. by extending the QADO ontology). We are currently working with OpenAI models, but also plan to work with local LLMs, and perhaps train an Electricity-specific model. The project started in Feb 2025 and will continue until Mar 2026. Significant dissemination is planned (blogs but also research papers). We hope to continue it with large-scale EU funded projects, and extend it in other electrical enterprises, such as the Swedish TSO and EDF (largest French producer).

May 2025

Jun 2025

Jul 2025

Aug 2025

Sep 2025

Oct 2025

Nov 2025

Feb 2026

  • Demo of CIMon chatbot, NATO Innovation Continuum Spark event. Nikola Tulechki. GATE Big Data Institute (Sofia), 24 Feb 2026. Generated organic interest with 100 defence IT people because the chatbot works on critical infrastructure data, and because of the complexity of the data.

Mar 2026

Apr 2026

May 2026

Clone this wiki locally