ICIEA 2026 Workshop

Workshop 1: AI-Driven Stability and Control of Converter-Dominated Power Systems

Speakers:

Speaker 1: Qianwen Xu

Title: Associate Professor

Affiliation: KTH Royal Institute of Technology

Summary of workshop:

Modern power systems are rapidly evolving into converter-dominated energy systems driven by distributed energy resources, electrified transport, and emerging large-scale loads such as data centers. This transformation fundamentally reshapes the nature of grid stability and operation: stability is no longer governed by physical inertia, but by fast, complex converter interactions, and system operation must cope with increasing uncertainty and scale.

This talk presents how artificial intelligence can enable reliable and scalable operation of such systems across three layers. First, transfer learning-based approaches are developed for fast, online modeling of converter-interfaced assets, enabling accurate system representation without detailed device-level knowledge. Second, AI-driven stability assessment frameworks are developed to allow real-time evaluation of converter–grid interactions. Third, safe deep reinforcement learning methods are presented for large-scale grid operation, ensuring guaranteed safety while optimizing performance. Together, these advances point toward a new paradigm of autonomous, AI-enabled energy systems, where learning-based methods are tightly integrated with physical constraints to ensure stability, efficiency, and resilience.