An open, executable module library for engineering-grounded AI (EGAI) in power systems education lowers the entry barrier for newcomers, with a progressive difficulty ladder from DNN templates to physics-informed neural networks, delivered via IEEE online course and PES webinars.
Junjie Yin, Buxin She, Xinyu Feng, Fangxing Li — arXiv (cs.AI / eess.SY) preprint, 2026 (University of Tennessee, IEEE PES). 📄 Full text (arXiv)
Synthesis
Community survey of researchers and practitioners: 92% report at least one barrier before running an AI model and 94% want a power-specific hands-on course.
Framework is a progressive difficulty ladder mapping core AI concepts onto representative power-system tasks: DNN function approximation/load-curve fitting, domain-coupled CNN power-flow surrogate (5-bus), DNN-assisted optimization, DRL for battery storage control, and PINNs for the swing equation.
All modules are Jupyter notebooks running locally or on Google Colab, delivered through an IEEE online course and IEEE PES webinar series.
Webinar drew 590+ live attendees (top-10 most-attended IEEE PES webinars) and 344+ repository visits within two weeks.
Argues for engineering-grounded AI (EGAI): AI workflows should follow established engineering and power-system domain rules rather than acting as task-agnostic black boxes.
Related Pages
- ai-education — teaching AI itself as a subject
- stem-education — STEM learning contexts
- curriculum-design — design of AI curricula
- open-source — open educational resources
- professional-training — workforce and professional learning
- llm — LLMs as the default learning path for newcomers
Citation
APA: Junjie Yin, Buxin She, Xinyu Feng, Fangxing Li (2026). Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Framework. arXiv:2608.02599. arXiv (cs.AI / eess.SY) preprint.