Engineering Grounded Ai Power Systems

---
name: engineering-grounded-ai-power-systems
description: Engineering-Grounded AI (EGAI) framework for power systems education using hands-on executable modules that follow domain rules rather than acting as black boxes.
trigger_words:
  - engineering-grounded ai
  - power systems ai education
  - egai framework
  - ai power systems modules
---

# Engineering-Grounded AI for Power Systems Education

## Overview
This skill implements the Engineering-Grounded AI (EGAI) framework from the arXiv paper "Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Framework" (arXiv:2608.02599). The framework addresses the gap between AI applications and power systems education by providing open, executable modules that follow established engineering and power-system domain rules.

## Core Principles
1. **Engineering-Grounded AI (EGAI)**: AI workflows must follow established engineering and power-system domain rules rather than acting as task-agnostic black boxes
2. **Progressive Difficulty Ladder**: Maps core AI concepts onto representative power-system tasks with increasing complexity
3. **Hands-On Accessibility**: All modules are released as Jupyter notebooks that run locally or on Google Colab

## Module Structure
The framework consists of three progressive module levels:

### Level 1: Foundational DNN Templates
- Function approximation for power systems
- Load-curve fitting applications
- Basic deep neural network architectures

### Level 2: Domain-Coupled CNN Surrogates
- Power-flow surrogate models for small-scale systems (e.g., 5-bus system)
- Convolutional neural networks adapted for power system topology
- Domain-specific feature engineering

### Level 3: Frontier Advanced Modules
- DNN-assisted optimization techniques
- Deep reinforcement learning (DRL) for battery storage control
- Physics-informed neural networks (PINNs) for swing equation modeling

## Implementation Guidelines
1. **Start with Level 1**: Begin with foundational DNN templates to understand basic AI concepts in power systems context
2. **Progress systematically**: Move to domain-coupled CNNs once foundational concepts are mastered
3. **Apply to real problems**: Use frontier modules for advanced research and practical applications
4. **Use provided notebooks**: Leverage the Jupyter notebook implementations for immediate hands-on experience

## Use Cases
- Power systems education and training
- Interdisciplinary AI research in energy systems
- Development of domain-specific AI applications
- Bridging the gap between AI researchers and power systems engineers

## References
- Yin, J., She, B., Feng, X., & Li, F. (2026). Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Framework. arXiv:2608.02599 [eess.SY]
- IEEE Power & Energy Society (PES) webinar series
- Community survey showing 92% of researchers face barriers before running AI models in power systems

## Activation
Use this skill when working on AI applications in power and energy systems, particularly when you need to ensure that AI workflows follow established engineering principles rather than treating AI as a black box solution.