AI for Load Forecasting, DER Hosting Capacity and Distribution Planning

In AI for Load Forecasting, DER Hosting Capacity and Distribution Planning, you'll learn ...

• The role of AI and machine learning as advisory tools for load forecasting, DER hosting capacity analysis, and distribution system planning
• The integration of short-term and long-term forecasting methods, load drivers, DER scenarios, and feeder-level analysis into utility planning
• The validation and risk-management practices needed to address AI model uncertainty, data quality, model drift, and planning reliability
• How to maintain Professional Engineer accountability, transparency, governance, documentation, and professional defensibility when using AI-assisted engineering analysis

Overview

Preview a portion of this course before purchasing it.

Credit: 1 PDH

Length: 14 pages

This course examines how artificial intelligence and machine learning can support load forecasting, distributed energy resource (DER) hosting capacity analysis, and electric distribution system planning while preserving Professional Engineer accountability. It explains how AI can identify complex load patterns, accelerate feeder-level analysis, evaluate DER adoption scenarios, and improve spatial and temporal forecasting. Participants explore short-term and long-term forecasting methods, including weather normalization, feature engineering, neural networks, gradient boosting, and scenario-based approaches.

The course also addresses the growing planning challenges associated with solar PV, battery storage, electric vehicles, reverse power flow, voltage limits, and changing net-load profiles. Particular emphasis is placed on validating AI results through conventional engineering analysis, appropriate metrics, prediction intervals, scenario analysis, and power-flow verification. Participants learn approaches for managing model uncertainty, drift, data-quality problems, overfitting, and other AI-related risks.

Governance topics include FMEA, configuration control, independent validation, ISO 9001 principles, model documentation, and auditability. Throughout the course, AI is treated as an advisory engineering tool rather than a substitute for professional judgment, with safety, reliability, ethics, transparency, and defensible decision-making remaining the engineer's responsibility.

Specific Knowledge or Skill Obtained

This course teaches the following specific knowledge and skills:

• The responsibilities of Professional Engineers when defining, reviewing, validating, and approving AI-assisted distribution planning decisions
• The principal weather, customer, temporal, economic, demographic, and DER-related factors influencing electric load forecasts
• The development of forecasting features using weather variables, degree days, holiday indicators, recent load lags, and weather normalization
• The differences between short-term and long-term load forecasting methods, applications, uncertainty levels, and planning horizons
• The use of AI and machine learning techniques to develop granular feeder-level and spatial load forecasts
• The assessment of DER hosting capacity and net-load impacts associated with solar PV, battery storage, electric vehicles, and changing operating conditions
• The use of scenario analysis, probabilistic methods, engineering margins, and power-flow verification to address DER and forecasting uncertainty
• The interpretation and application of MAE, MAPE, RMSE, coverage probability, prediction intervals, and out-of-sample validation
• The management of AI model risks through FMEA, configuration control, independent validation, periodic review, and continuous improvement
• How to document and communicate AI-assisted engineering analyses so that assumptions, data provenance, model versions, uncertainties, recommendations, and decisions remain transparent and professionally defensible

Certificate of Completion

You will be able to immediately print a certificate of completion after passing a multiple-choice quiz consisting of 12 questions. PDH credits are not awarded until the course is completed and quiz is passed.