AI for Electrical & Power Engineers
 

Course Description:

This course provides a comprehensive, engineering-focused examination of AI as it is actually used in electrical and power engineering practice. Rather than emphasizing software development or data science theory, the course is structured around how licensed electrical engineers evaluate, validate, interpret, and oversee AI-assisted tools within safety-critical, regulated power systems.

Learning Objectives:

Upon completion of this course, participants will be able to:

1. Explain the fundamental differences between deterministic power system analysis and data-driven artificial intelligence models, including the implications of probabilistic outputs, uncertainty, and explainability for electrical engineering practice.
2. Identify and describe common applications of artificial intelligence across generation, transmission, and distribution systems, including forecasting, operational monitoring, predictive maintenance, and decision-support functions.
3. Evaluate the role of data quality, system telemetry, and sensor integrity in AI-based power system applications, and recognize how data limitations can affect model reliability and safety.
4. Interpret AI-generated forecasts, alerts, risk scores, and recommendations using sound engineering judgment, physical system constraints, and conservative operating principles.
5. Distinguish between traditional, condition-based, and AI-assisted predictive maintenance strategies for electrical assets, and assess their impact on reliability, safety, and asset management decisions.
6. Assess the risks, limitations, and validation requirements associated with AI use in transmission and distribution system operations, including interactions with protection and control systems.
7. Evaluate the appropriate and limited role of artificial intelligence in protection, control, and other safety-critical power system functions, with emphasis on deterministic operation, fail-safe design, and professional accountability.
8. Apply human-in-the-loop principles to AI-assisted power system decisions, including defining decision authority, escalation procedures, override mechanisms, and documentation requirements.
9. Analyze AI model risk, including bias, overfitting, model drift, and silent failure, and understand the importance of ongoing validation, monitoring, and lifecycle management.
10. Apply lessons learned from real-world case studies involving transmission asset monitoring, distribution fault detection and restoration, and DER-driven voltage regulation to professional electrical engineering practice.
11. Integrate AI-enabled tools into existing engineering, operational, and asset management frameworks in a manner consistent with regulatory requirements, ethical obligations, and the responsibility to protect public safety and system reliability.